{"meta":{"query_hash":"93e5f7b86fa9","filters":{"venue":"Scientific Data"},"cohort_total":591,"direct_labels_cover":48,"predictions_cover":591,"exported":591,"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/93e5f7b86fa9","api":"https://metacan.xera.ac/api/v1/cohort?venue=Scientific+Data"},"results":[{"id":"W1124213845","doi":"10.1038/sdata.2015.42","title":"A spatially comprehensive, hydrometeorological data set for Mexico, the U.S., and Southern Canada 1950–2013","year":2015,"lang":"en","type":"article","venue":"Scientific Data","topic":"Climate variability and models","field":"Environmental Science","cited_by":424,"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":"Bureau of Reclamation; Instituto Tecnológico de Sonora; National Science Foundation","keywords":"Hydrometeorology; Precipitation; Orographic lift; Orography; Evapotranspiration; Environmental science; Climatology; Meteorology; Geography; Geology; Ecology","score_opus":0.1784396269167633,"score_gpt":0.29465462329151954,"score_spread":0.11621499637475624,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1124213845","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":[0.91632104,0.00015272191,0.001970247,0.009997201,0.0014223428,0.0010597763,0.06807809,0.00004859822,0.00094995304],"genre_scores_gemma":[0.97872,0.000009213819,0.0041240314,0.0011316288,0.00006338502,0.000020957534,0.014629456,0.000016967873,0.0012843319],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.997919,0.00009415684,0.00019924385,0.0009849817,0.0004748604,0.00032773393],"domain_scores_gemma":[0.9961951,0.0002235118,0.00006761497,0.0032971804,0.000021276033,0.00019533125],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020200326,0.00012214168,0.00014140012,0.000013341867,0.00037309507,0.00023021032,0.002759824,0.00004258676,0.00037033358],"category_scores_gemma":[0.00036546894,0.0000784884,0.000011602771,0.00017850612,0.0007626168,0.00037093298,0.005323387,0.00009181135,0.00010473443],"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":[0.000035280817,0.00005915961,0.003226515,0.000011928346,0.00001569132,0.0000035920132,0.00058388815,0.0016037864,0.00084101775,0.000049796472,0.99067646,0.0028928688],"study_design_scores_gemma":[0.00031370108,0.000026776348,0.0008243298,0.0000034512893,0.00002691441,0.000008334529,0.0003563746,0.2232056,0.000015978754,0.0018184638,0.77325433,0.00014576068],"about_ca_topic_score_codex":0.2996491,"about_ca_topic_score_gemma":0.73949856,"teacher_disagreement_score":0.4398495,"about_ca_system_score_codex":0.00005528624,"about_ca_system_score_gemma":0.00015571406,"threshold_uncertainty_score":0.70501465},"labels":[],"label_agreement":null},{"id":"W1993975089","doi":"10.1038/sdata.2015.8","title":"A global database of lake surface temperatures collected by in situ and satellite methods from 1985–2009","year":2015,"lang":"en","type":"article","venue":"Scientific Data","topic":"Aquatic Ecosystems and Phytoplankton Dynamics","field":"Environmental Science","cited_by":240,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"International Institute for Sustainable Development; Ministry of the Environment, Conservation and Parks; York University","funders":"Division of Environmental Biology; Leibniz-Gemeinschaft; Natural Environment Research Council; U.S. Geological Survey; U.S. Fish and Wildlife Service; National Oceanic and Atmospheric Administration; Leibniz-Institut für Gewässerökologie und Binnenfischerei; National Aeronautics and Space Administration; Institut National de la Recherche Agronomique; Ministry of Business, Innovation and Employment; European Commission; Eesti Teadusfondi; U.S. Department of Agriculture; Regione del Veneto; Österreichischen Akademie der Wissenschaften; Vale Canada Limited; National Park Service; New York State Department of Environmental Conservation; National Science Foundation; University of Washington; Gordon and Betty Moore Foundation; Chinese Academy of Sciences; Russian Academy of Sciences; University of Nebraska-Lincoln; Sight Research UK; Government of Canada; Andrew W. Mellon Foundation; Irkutsk State University; Bundesministerium für Land- und Forstwirtschaft, Umwelt und Wasserwirtschaft; Cornell University Agricultural Experiment Station; Naturvårdsverket; York University; Waikato Regional Council","keywords":"Longitude; Environmental science; Latitude; Climate change; Surface water; Elevation (ballistics); Lake ecosystem; Satellite; Global change; Global warming; Database; Ecosystem; Climatology; Physical geography; Atmospheric sciences; Geography; Geology; Oceanography; Ecology","score_opus":0.033381128971521914,"score_gpt":0.30651883685899795,"score_spread":0.27313770788747604,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1993975089","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":[0.9511624,0.0011888801,0.0011753641,0.00006154124,0.00064806535,0.00026914533,0.042763997,0.00001874289,0.002711866],"genre_scores_gemma":[0.9087145,0.000052202067,0.0691432,0.000058044334,0.00001896976,0.0000030347394,0.019753538,0.000012643827,0.0022439156],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982469,0.00021761925,0.00029841228,0.00066719827,0.00035266284,0.0002172213],"domain_scores_gemma":[0.9983954,0.00009584705,0.0001074359,0.001223947,0.000013833644,0.00016355398],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019978175,0.00012224367,0.00021266048,0.000021135707,0.000070019916,0.00013158955,0.00073881133,0.000051995972,0.00017109752],"category_scores_gemma":[0.00022080044,0.000106276304,0.000011427589,0.0007758165,0.00028445458,0.00037242915,0.00092335546,0.00007470919,0.000044208144],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007202366,0.00024270579,0.37304187,0.00003888691,0.000026655927,0.000020333886,0.00085601973,0.0002528025,0.067675814,0.0001289405,0.55260307,0.0050408933],"study_design_scores_gemma":[0.002447924,0.000099313365,0.17281172,0.00021726429,0.00007231079,0.000023656828,0.0010337292,0.086488895,0.0041616373,0.0027988928,0.7289426,0.00090205605],"about_ca_topic_score_codex":0.0030694746,"about_ca_topic_score_gemma":0.08831569,"teacher_disagreement_score":0.20023014,"about_ca_system_score_codex":0.000055470708,"about_ca_system_score_gemma":0.000054854252,"threshold_uncertainty_score":0.92832017},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"observational","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W2012105696","doi":"10.1038/sdata.2014.15","title":"Tree of Sex: A database of sexual systems","year":2014,"lang":"en","type":"article","venue":"Scientific Data","topic":"Genetic and Clinical Aspects of Sex Determination and Chromosomal Abnormalities","field":"Biochemistry, Genetics and Molecular Biology","cited_by":302,"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 Calgary; University of British Columbia","funders":"National Institute of General Medical Sciences; Natural Environment Research Council; Sight Research UK; National Evolutionary Synthesis Center; National Science Foundation","keywords":"Biology; Phylogenetic tree; Context (archaeology); Evolutionary biology; Evolution of sexual reproduction; Ecology; Genetics","score_opus":0.034122245715847946,"score_gpt":0.28951405907009076,"score_spread":0.2553918133542428,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2012105696","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":[0.9899837,0.00035979785,0.0013605249,0.00002931637,0.0005453425,0.00009607892,0.0023726202,0.0000060333773,0.0052465904],"genre_scores_gemma":[0.98963344,0.000009084688,0.0004277851,0.000018761433,0.0000885105,0.0000018532559,0.003038267,0.000004900464,0.0067774067],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990036,0.000048867772,0.00027874587,0.00036443092,0.00019264634,0.000111692854],"domain_scores_gemma":[0.99840385,0.000018752418,0.00011996245,0.0013151169,0.00008951977,0.000052792824],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00064351194,0.000067497655,0.00012755343,0.000028869836,0.000041645595,0.000026263297,0.0006956185,0.00004571206,0.000039885537],"category_scores_gemma":[0.00016559551,0.000057119734,0.000018740246,0.00007299357,0.000308805,0.0000070007536,0.00047557917,0.000027828648,0.000008550849],"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":[0.00004267266,0.00029195147,0.0019684597,0.00045086775,0.000047145433,9.593235e-7,0.0000954501,0.000019533902,0.929823,0.0011273496,0.036108714,0.030023906],"study_design_scores_gemma":[0.0016412331,0.0013303581,0.0035617475,0.00010490385,0.00011809465,0.000023237117,0.004065963,0.0074084317,0.6370715,0.000228144,0.34392405,0.00052231376],"about_ca_topic_score_codex":0.000019394327,"about_ca_topic_score_gemma":0.000022956088,"teacher_disagreement_score":0.30781534,"about_ca_system_score_codex":8.4892e-7,"about_ca_system_score_gemma":0.000044495275,"threshold_uncertainty_score":0.23292752},"labels":[],"label_agreement":null},{"id":"W2027222148","doi":"10.1038/sdata.2014.31","title":"A repository of assays to quantify 10,000 human proteins by SWATH-MS","year":2014,"lang":"en","type":"article","venue":"Scientific Data","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":458,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Spinal Cord Injury BC","funders":"National Center for Research Resources; National Institute of General Medical Sciences; Suomen Kulttuurirahasto; Eidgenössische Technische Hochschule Zürich; National Human Genome Research Institute; SystemsX.ch; Kommission für Technologie und Innovation; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; European Molecular Biology Organization; National Institutes of Health; National Science Foundation","keywords":"UniProt; Computational biology; Proteome; Computer science; Human proteins; Mass spectrometry; Human proteome project; Quantitative proteomics; Tandem mass tag; Label-free quantification; Tandem mass spectrometry; Proteomics; Compendium; Data mining; Bioinformatics; Chemistry; Biology; Chromatography; Biochemistry","score_opus":0.0338103432655551,"score_gpt":0.31668508190209504,"score_spread":0.28287473863653995,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2027222148","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":[0.5064597,0.00021753612,0.26878053,0.0018469198,0.0005885308,0.0024805176,0.028841127,0.001281253,0.18950388],"genre_scores_gemma":[0.8253529,0.0000020674538,0.089907154,0.00004211338,0.00020397679,0.00030227445,0.005890697,0.000050886476,0.07824796],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9984258,0.000015137952,0.0003184794,0.0007478725,0.00027237885,0.00022037147],"domain_scores_gemma":[0.996201,0.000024914021,0.00016830931,0.0034047733,0.000092565235,0.00010842981],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00060580473,0.000114500675,0.00014868917,0.000047742345,0.00036166538,0.00012629897,0.001660411,0.00007568687,0.00033617156],"category_scores_gemma":[0.00011386044,0.00011238761,0.000031601605,0.00023027106,0.00020359154,0.00015419691,0.00072269683,0.00012805105,0.000065552835],"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":[0.0000032720372,0.0000592708,0.000054417298,0.000038506667,0.0000040278665,2.3429617e-7,0.000030573003,0.0000020209263,0.87701803,0.0016628951,0.11965026,0.0014765031],"study_design_scores_gemma":[0.000054742304,0.000009946832,0.000008662037,0.000030530067,0.000005845116,0.0000010660648,0.000009653272,0.00024998697,0.5564508,0.0009346473,0.44215164,0.00009250574],"about_ca_topic_score_codex":0.00010789572,"about_ca_topic_score_gemma":0.000015848738,"teacher_disagreement_score":0.32250136,"about_ca_system_score_codex":0.000025212441,"about_ca_system_score_gemma":0.00002880652,"threshold_uncertainty_score":0.4583034},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"bench_or_experimental","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W2093745477","doi":"10.1038/sdata.2014.49","title":"An open science resource for establishing reliability and reproducibility in functional connectomics","year":2014,"lang":"en","type":"article","venue":"Scientific Data","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":497,"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; Douglas Mental Health University Institute; Université de Montréal; Institut Universitaire de Gériatrie de Montréal","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Institute on Drug Abuse; National Institute of Biomedical Imaging and Bioengineering; National Institute of Neurological Disorders and Stroke; National Institute of Mental Health; National Key Research and Development Program of China","keywords":"Connectomics; Reliability (semiconductor); Reproducibility; Computer science; Neuroimaging; Connectome; Open science; Artificial intelligence; Functional connectivity; Psychology; Neuroscience; Statistics; Mathematics","score_opus":0.14234638286896062,"score_gpt":0.3469814610188182,"score_spread":0.2046350781498576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2093745477","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":[0.985036,0.000013393326,0.0020857248,0.005758423,0.0026938855,0.0012601076,0.0014882119,0.00009328441,0.0015709479],"genre_scores_gemma":[0.99565446,6.985337e-7,0.00250692,0.0010097339,0.00011187099,0.000045102133,0.0001865978,0.000012577463,0.0004720448],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9916981,0.0003175534,0.00032182087,0.006628861,0.00060151477,0.00043216688],"domain_scores_gemma":[0.980438,0.008017742,0.00014960382,0.010957684,0.00025180067,0.00018515682],"candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.045951333,0.0001399891,0.00021128553,0.00021328109,0.0015251766,0.0020607554,0.004274282,0.000037929338,0.000016237267],"category_scores_gemma":[0.31082746,0.00013240917,0.000014034398,0.0013198466,0.0024036733,0.004385597,0.0055266838,0.00017132556,0.000007350997],"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":[0.0009550698,0.0014025193,0.038028285,0.00019480473,0.000006193299,0.0000027102208,0.0014231217,0.0020115268,0.6608348,0.049150564,0.20107481,0.0449156],"study_design_scores_gemma":[0.0020008415,0.0003539762,0.11421809,0.000054879663,0.000017482944,0.000022839946,0.00064557116,0.20929624,0.06193011,0.067114115,0.54360527,0.0007405782],"about_ca_topic_score_codex":0.00012821886,"about_ca_topic_score_gemma":0.00048130722,"teacher_disagreement_score":0.59890467,"about_ca_system_score_codex":0.00011837585,"about_ca_system_score_gemma":0.00032684876,"threshold_uncertainty_score":0.9997747},"labels":[{"model":"gemma","categories":["metaresearch","open_science"],"domain":"reproducibility","study_design":"not_applicable","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"},{"model":"gpt","categories":["metaresearch","open_science"],"domain":"reproducibility","study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W2190609062","doi":"10.1038/sdata.2015.43","title":"Test-retest resting-state fMRI in healthy elderly persons with a family history of Alzheimer’s disease","year":2015,"lang":"en","type":"article","venue":"Scientific Data","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":39,"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; Montreal Neurological Institute and Hospital; McGill University Health Centre; McGill University; Douglas Mental Health University Institute; Institut Universitaire de Gériatrie de Montréal","funders":"Pfizer Canada; Government of Canada; McGill University; Pfizer","keywords":"Dementia; Neuroimaging; Medicine; Alzheimer's disease; Disease; Reliability (semiconductor); Clinical trial; Cohort; Psychology; Audiology; Physical medicine and rehabilitation; Psychiatry; Internal medicine","score_opus":0.19530099344636476,"score_gpt":0.3150118630483633,"score_spread":0.11971086960199856,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2190609062","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":[0.95763767,0.0045718728,0.00016648992,0.013018074,0.006207608,0.0014298424,0.010257667,0.00031090272,0.006399899],"genre_scores_gemma":[0.9937147,0.0000069010766,0.0006439769,0.001248275,0.000045042627,0.0000319349,0.00014873738,0.000028073178,0.00413236],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99697465,0.00015756137,0.0002701878,0.0012777075,0.0009336523,0.00038623973],"domain_scores_gemma":[0.99575764,0.001845476,0.0001770869,0.0017925383,0.00013002903,0.00029725514],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0015512765,0.00016290623,0.00021040998,0.000276219,0.00015652677,0.000079076686,0.0011045742,0.00002089381,0.000009426656],"category_scores_gemma":[0.020275418,0.0001435009,0.000023626892,0.0007919443,0.0011618593,0.0006310192,0.00068945484,0.00018205443,0.00006370283],"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":[0.0005898934,0.0006269905,0.02315377,0.000059811853,0.000011250431,0.00013875272,0.0018941931,0.00014884364,0.011225299,0.00011899595,0.96009636,0.0019358599],"study_design_scores_gemma":[0.005963718,0.0029155964,0.11982842,0.0005642434,0.00019287219,0.000053208983,0.00195578,0.017968353,0.0019681219,0.0018404701,0.8451906,0.0015586615],"about_ca_topic_score_codex":0.0003274649,"about_ca_topic_score_gemma":0.00060628174,"teacher_disagreement_score":0.11490578,"about_ca_system_score_codex":0.00022957285,"about_ca_system_score_gemma":0.001708655,"threshold_uncertainty_score":0.9879772},"labels":[],"label_agreement":null},{"id":"W2313381310","doi":"10.1038/sdata.2014.26","title":"An extended Arctic proxy temperature database for the past 2,000 years","year":2014,"lang":"en","type":"article","venue":"Scientific Data","topic":"Tree-ring climate responses","field":"Earth and Planetary Sciences","cited_by":166,"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 Oceanic and Atmospheric Administration; National Science Foundation","keywords":"Proxy (statistics); Arctic; Database; Climatology; Seasonality; Climate change; The arctic; Context (archaeology); Physical geography; Environmental science; Geography; Computer science; Oceanography; Geology; Archaeology","score_opus":0.033771668608765314,"score_gpt":0.27553162902992934,"score_spread":0.24175996042116402,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2313381310","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":[0.9124986,0.0009028456,0.0007912801,0.001884659,0.0064217085,0.0015248664,0.07508899,0.00028918806,0.00059788127],"genre_scores_gemma":[0.9781736,0.000009615117,0.0026913264,0.00013944707,0.00031448153,0.000004318157,0.017418278,0.0000075266807,0.001241363],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99814236,0.00013777171,0.00017682047,0.00076550245,0.00038486673,0.00039269493],"domain_scores_gemma":[0.9963494,0.0005045302,0.000067544075,0.0028845763,0.000048589976,0.0001453842],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027579735,0.00012286408,0.00011080869,0.00008660104,0.00058802223,0.000933942,0.0021761227,0.00004133602,0.0007129273],"category_scores_gemma":[0.0005385072,0.00007862087,0.000027572034,0.00035057403,0.0003289074,0.00075806153,0.00010986831,0.00013268457,0.00035755205],"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":[0.0005348952,0.00026042224,0.17245348,0.0003122155,0.00008777731,0.000028374174,0.00069649867,0.00093364005,0.0077223196,0.0005627634,0.37622708,0.44018054],"study_design_scores_gemma":[0.00030986412,0.00009220311,0.51399654,0.000036168683,0.000043528624,0.00001823512,0.00019474598,0.05202636,0.00014201643,0.0002376128,0.43268198,0.00022075883],"about_ca_topic_score_codex":0.0003219734,"about_ca_topic_score_gemma":0.0026662627,"teacher_disagreement_score":0.4399598,"about_ca_system_score_codex":0.0000030694475,"about_ca_system_score_gemma":0.00007347699,"threshold_uncertainty_score":0.9006024},"labels":[],"label_agreement":null},{"id":"W2318435655","doi":"10.1038/sdata.2014.2","title":"The systematic identification of cytoskeletal genes required for Drosophila melanogaster muscle maintenance","year":2014,"lang":"en","type":"article","venue":"Scientific Data","topic":"Muscle Physiology and Disorders","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Drosophila melanogaster; Biology; RNA interference; Computational biology; Model organism; Identification (biology); Gene; Function (biology); Metadata; Melanogaster; Drosophila (subgenus); Bioinformatics; Genetics; Computer science; RNA; World Wide Web; Ecology","score_opus":0.021877616705588094,"score_gpt":0.2732356002784352,"score_spread":0.2513579835728471,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2318435655","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":[0.89354134,0.0033418203,0.08969595,0.0013134602,0.005191203,0.002746176,0.0031599835,0.00004312091,0.00096692424],"genre_scores_gemma":[0.99608827,0.000022680817,0.00018105777,0.000036825713,0.00007974835,0.00004954754,0.002077441,0.000009044791,0.0014553779],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988387,0.00009610387,0.00031095213,0.00045498158,0.00011487369,0.00018438442],"domain_scores_gemma":[0.9977222,0.000056131714,0.00020674508,0.0018651139,0.000120166194,0.000029639954],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016381872,0.00008136369,0.00012114457,0.000021682543,0.00029071898,0.00006540492,0.00096949097,0.000054099855,0.000002355765],"category_scores_gemma":[0.00067012466,0.00005612896,0.000055600874,0.000077155964,0.00037244393,0.000012165276,0.00028096294,0.00002337236,0.000014042153],"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":[0.00004059921,0.000029435432,0.000022562,0.0007229936,0.000028108381,3.334847e-8,0.00002124389,0.00001577908,0.98115665,0.0015737538,0.015025061,0.001363759],"study_design_scores_gemma":[0.003760022,0.0007835065,0.008188408,0.0009022424,0.00040986788,0.000014457037,0.0014627167,0.037790213,0.57636285,0.02404809,0.34506658,0.0012110524],"about_ca_topic_score_codex":0.0000020455375,"about_ca_topic_score_gemma":0.000028345352,"teacher_disagreement_score":0.40479383,"about_ca_system_score_codex":0.0000027214523,"about_ca_system_score_gemma":0.000033236855,"threshold_uncertainty_score":0.22888726},"labels":[],"label_agreement":null},{"id":"W2324317819","doi":"10.1038/sdata.2016.6","title":"Female and male life tables for seven wild primate species","year":2016,"lang":"en","type":"article","venue":"Scientific Data","topic":"Primate Behavior and Ecology","field":"Psychology","cited_by":94,"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 Calgary","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Evolutionary Synthesis Center","keywords":"Gorilla; Biology; Survivorship curve; Demography; Reproductive value; Primate; Population; Ecology; Zoology","score_opus":0.12397454317852258,"score_gpt":0.36303121266904764,"score_spread":0.23905666949052506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2324317819","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":[0.9326983,0.0005991284,0.0018945565,0.0020905645,0.007938107,0.00074941246,0.03320822,0.00012715979,0.020694563],"genre_scores_gemma":[0.6067152,0.000040828214,0.002961147,0.00033500124,0.00032163502,0.0001176236,0.0036494748,0.000046552108,0.38581255],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984577,0.00003468094,0.00019487293,0.00076500984,0.00010546182,0.00044232025],"domain_scores_gemma":[0.9980982,0.00011854736,0.00007017964,0.0015499028,0.00004051965,0.000122658],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0008954052,0.00010548625,0.0001679749,0.000089929425,0.00025742847,0.00013520027,0.0008123172,0.00007379728,0.008938151],"category_scores_gemma":[0.00016033235,0.00007617981,0.000022716804,0.00010802333,0.00042759636,0.00033900188,0.0006565796,0.000037844275,0.00082589086],"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":[0.00005303429,0.00011685314,0.026204431,0.000026071726,0.000026426746,0.000007813983,0.00049912045,4.571322e-8,0.014477128,0.004025262,0.94187194,0.012691862],"study_design_scores_gemma":[0.00089020445,0.000046279136,0.05050158,0.000016531718,0.000042790107,0.000034310986,0.0006107045,0.000010523438,0.00081445946,0.00041480165,0.94642353,0.00019430822],"about_ca_topic_score_codex":0.000020466454,"about_ca_topic_score_gemma":0.00011474909,"teacher_disagreement_score":0.36511797,"about_ca_system_score_codex":0.000017375214,"about_ca_system_score_gemma":0.000053320487,"threshold_uncertainty_score":0.9999521},"labels":[],"label_agreement":null},{"id":"W2335458838","doi":"10.1038/sdata.2014.12","title":"Direct infusion mass spectrometry metabolomics dataset: a benchmark for data processing and quality control","year":2014,"lang":"en","type":"article","venue":"Scientific Data","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":139,"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 Alberta","funders":"Pfizer Canada; University of Birmingham; British Heart Foundation; Natural Environment Research Council; Advantage West Midlands; Pfizer","keywords":"Workflow; Benchmark (surveying); Computer science; Metabolomics; Data mining; Quality (philosophy); Set (abstract data type); Data quality; Quality assurance; Bioinformatics; Biology; Database; Medicine; Engineering","score_opus":0.047168274210509537,"score_gpt":0.3218757350716982,"score_spread":0.2747074608611887,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2335458838","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":[0.18303964,0.023397807,0.40854344,0.0014227922,0.0038168011,0.0022275425,0.3745099,0.000090440306,0.0029516376],"genre_scores_gemma":[0.6896641,0.0006714921,0.068261035,0.00043960204,0.0006711188,0.000031772186,0.23938648,0.000045680306,0.0008286843],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972419,0.00012084639,0.0003656631,0.0016181249,0.0002464552,0.0004070198],"domain_scores_gemma":[0.9957342,0.00009114166,0.00021427903,0.0037422376,0.00009902522,0.00011910272],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004735809,0.0002165125,0.00037014458,0.000114898685,0.0004764404,0.00035826233,0.0017558851,0.00009159158,0.000017301569],"category_scores_gemma":[0.0021190406,0.0001868118,0.000032210053,0.000262766,0.0003105944,0.000051354793,0.0021648821,0.00008373908,0.0000039816614],"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":[0.00012716143,0.00007894249,0.001059971,0.00011613964,0.0001322457,3.0097326e-7,0.00001398597,0.0000014528243,0.86320335,0.00055218005,0.12032836,0.0143859135],"study_design_scores_gemma":[0.001200178,0.00008888663,0.0014990252,0.000011861255,0.00015234992,0.0000027682179,0.00004861394,0.005363956,0.017101048,0.00033462266,0.9738571,0.00033960768],"about_ca_topic_score_codex":0.000029249602,"about_ca_topic_score_gemma":0.00013764108,"teacher_disagreement_score":0.85352874,"about_ca_system_score_codex":0.00000733908,"about_ca_system_score_gemma":0.00008637316,"threshold_uncertainty_score":0.7617964},"labels":[],"label_agreement":null},{"id":"W2357032010","doi":"10.1038/sdata.2016.32","title":"Digital elevation model and orthophotographs of Greenland based on aerial photographs from 1978–1987","year":2016,"lang":"en","type":"letter","venue":"Scientific Data","topic":"Cryospheric studies and observations","field":"Earth and Planetary Sciences","cited_by":124,"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 Ottawa","funders":"Villum Fonden","keywords":"Digital elevation model; Glacier; Geology; Geodetic datum; Elevation (ballistics); Glacier mass balance; Greenland ice sheet; Geodesy; Remote sensing; Photogrammetry; Physical geography; Geomorphology; Geography","score_opus":0.041430564278527496,"score_gpt":0.2240699001270552,"score_spread":0.1826393358485277,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2357032010","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.099158764,0.001230541,0.002630048,0.055383034,0.00979444,0.0017435851,0.8175442,0.00018803251,0.012327346],"genre_scores_gemma":[0.14554138,0.00042821348,0.006773666,0.11251678,0.00537328,0.000022391876,0.71966416,0.000068772046,0.009611331],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99739885,0.00003679929,0.00038859635,0.0010864343,0.00072362303,0.0003657038],"domain_scores_gemma":[0.9975635,0.00037027983,0.00027429964,0.0016177977,0.00009699375,0.000077139695],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000356342,0.00027548076,0.0003405736,0.00017645801,0.0003239105,0.00042577556,0.0009335476,0.00022110635,0.0009895625],"category_scores_gemma":[0.0001090503,0.00019814476,0.000089386165,0.0005239365,0.00055043073,0.00042911308,0.00012440143,0.0002710231,0.000043686458],"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":[0.000046443252,0.000012798186,0.03991011,0.000031427837,0.00004671147,0.000008629876,0.000035013112,0.0001549817,0.00002173084,0.0000016925384,0.9354686,0.024261843],"study_design_scores_gemma":[0.0005407867,0.00006394338,0.024256676,0.00012256933,0.00007404833,5.993908e-7,0.000026157206,0.072318144,0.000006730207,0.00073932495,0.9014789,0.0003721439],"about_ca_topic_score_codex":0.0013607598,"about_ca_topic_score_gemma":0.0020370034,"teacher_disagreement_score":0.09788002,"about_ca_system_score_codex":0.0000030288186,"about_ca_system_score_gemma":0.00012742126,"threshold_uncertainty_score":0.99992365},"labels":[],"label_agreement":null},{"id":"W2395631589","doi":"10.1038/sdata.2015.59","title":"Multi-contrast submillimetric 3 Tesla hippocampal subfield segmentation protocol and dataset","year":2015,"lang":"en","type":"article","venue":"Scientific Data","topic":"Neuroscience and Neuropharmacology Research","field":"Neuroscience","cited_by":113,"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":"Canadian Institutes of Health Research","keywords":"Segmentation; Hippocampal formation; Computer science; Neuroimaging; Dentate gyrus; Artificial intelligence; Pattern recognition (psychology); Temporal lobe; Neuroscience; Biology; Epilepsy","score_opus":0.3282191305563179,"score_gpt":0.4502045408260256,"score_spread":0.12198541026970772,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2395631589","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":[0.81689036,0.000071608025,0.0011860415,0.002326184,0.0071425084,0.11332171,0.05783802,0.0004596835,0.0007639081],"genre_scores_gemma":[0.961957,0.000030050529,0.0021342998,0.0053112544,0.0003782793,0.018160451,0.003821364,0.00009352201,0.008113776],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99644125,0.00035142378,0.00026453758,0.0015593269,0.00082795386,0.00055549026],"domain_scores_gemma":[0.9977368,0.00027798166,0.000097635966,0.0014169354,0.00006572925,0.00040493475],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019454869,0.00016384655,0.00014528031,0.0003832037,0.0005146971,0.00076430105,0.0019396327,0.000048994036,0.00009204654],"category_scores_gemma":[0.002735021,0.00013806771,0.000014139465,0.0016293771,0.0010244556,0.0014867231,0.0015911474,0.000282671,0.0004031028],"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":[0.00006144586,0.00019345657,0.0011277954,0.000016220178,0.0000010948452,0.000078143974,0.000059166112,0.0000015689106,0.81072235,0.000010023138,0.18449534,0.003233393],"study_design_scores_gemma":[0.0027896394,0.0002113229,0.0009342376,0.000007949935,0.000013901051,0.00010684098,0.000096598706,0.010593981,0.8562029,0.000074020834,0.12868686,0.0002817495],"about_ca_topic_score_codex":0.000018092634,"about_ca_topic_score_gemma":0.000011384837,"teacher_disagreement_score":0.14506666,"about_ca_system_score_codex":0.000022732798,"about_ca_system_score_gemma":0.0002376249,"threshold_uncertainty_score":0.7370172},"labels":[],"label_agreement":null},{"id":"W2415986366","doi":"10.1038/sdata.2016.28","title":"MycoDB, a global database of plant response to mycorrhizal fungi","year":2016,"lang":"en","type":"article","venue":"Scientific Data","topic":"Mycorrhizal Fungi and Plant Interactions","field":"Agricultural and Biological Sciences","cited_by":105,"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; Okanagan University College; University of British Columbia, Okanagan Campus; University of British Columbia","funders":"University of Pennsylvania","keywords":"Biology; Symbiosis; Abiotic component; Context (archaeology); Ecology; Ecosystem; Mycorrhizal fungi; Mutualism (biology); Biomass (ecology); Phylogenetic tree; Inoculation","score_opus":0.03651476630220665,"score_gpt":0.25812701480581557,"score_spread":0.22161224850360892,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2415986366","genre_codex":"dataset","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":[0.44014287,0.00013212895,0.00008953288,0.0015307802,0.0013304002,0.00018637913,0.555787,0.000045284967,0.00075562065],"genre_scores_gemma":[0.9363874,0.000111021836,0.0008802838,0.0002556102,0.00029091735,0.0000133107305,0.05668097,0.0000016101764,0.0053788647],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982449,0.00012587936,0.0002656261,0.00067681924,0.00036234834,0.00032444802],"domain_scores_gemma":[0.99735427,0.001627683,0.00008090462,0.00062768813,0.00008308594,0.00022636089],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0012159684,0.00012280402,0.00014783672,0.00002792298,0.0001958118,0.000113278744,0.0014478079,0.000044820175,0.0074975067],"category_scores_gemma":[0.0013120433,0.000039648156,0.00004565679,0.0006824305,0.000027257849,0.00041004407,0.00082831015,0.000046781053,0.0034257565],"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":[0.0005150131,0.00005664474,0.004272453,0.0000029079254,0.000005822228,0.000008474364,0.000011073251,2.0787606e-7,0.53685176,0.0004226532,0.4481046,0.0097483685],"study_design_scores_gemma":[0.00006155376,0.00012563395,0.008139215,0.00017724387,0.000014146448,0.000050285103,0.000075053256,0.00005354057,0.0053868317,0.00020146793,0.9855391,0.00017592651],"about_ca_topic_score_codex":0.0004093597,"about_ca_topic_score_gemma":0.0006697331,"teacher_disagreement_score":0.5374345,"about_ca_system_score_codex":0.000025904113,"about_ca_system_score_gemma":0.000038538812,"threshold_uncertainty_score":0.9973502},"labels":[],"label_agreement":null},{"id":"W2418133265","doi":"10.1038/sdata.2016.37","title":"Electricity, water, and natural gas consumption of a residential house in Canada from 2012 to 2014","year":2016,"lang":"en","type":"article","venue":"Scientific Data","topic":"Building Energy and Comfort Optimization","field":"Engineering","cited_by":288,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Simon Fraser University","funders":"British Columbia Institute of Technology","keywords":"Electricity; Consumption (sociology); Sustainability; Environmental economics; Power consumption; Computer science; Natural resource; Natural gas; Power (physics); Engineering; Economics; Ecology; Waste management","score_opus":0.01223721011083671,"score_gpt":0.20241991080083227,"score_spread":0.19018270068999557,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2418133265","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":[0.9957343,0.00025526798,0.0025633757,0.00006912276,0.0009477604,0.00004639293,0.0003456456,0.000030943575,0.0000071985696],"genre_scores_gemma":[0.9990676,0.000045848385,0.00041460773,0.0000070837555,0.000016641829,0.000001487411,0.00029329932,0.000007619953,0.00014578342],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994302,0.000011666689,0.00011299462,0.00018864006,0.00012120188,0.00013531341],"domain_scores_gemma":[0.9995367,0.00002028608,0.000011400442,0.00038255408,0.0000138614805,0.000035180798],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015676166,0.00004878968,0.00006517907,0.00008530446,0.000026889616,0.000031355175,0.00024546054,0.00001824804,0.000055343324],"category_scores_gemma":[0.000015464186,0.00003446959,0.0000039109127,0.000088636196,0.000021572485,0.0002745495,0.0001379663,0.000032845503,0.0000054726024],"study_design_candidate":"bench_or_experimental","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":[0.00006241004,0.000026476237,0.016783956,0.000052777097,0.000044755387,0.000009750075,0.00018759756,0.0524685,0.44448063,0.00012686996,0.45469716,0.031059103],"study_design_scores_gemma":[0.0021469772,0.00002830268,0.055387933,0.00037458137,0.000057363548,0.000009441352,0.000033605924,0.30697334,0.58911484,0.0009096406,0.044067644,0.00089633046],"about_ca_topic_score_codex":0.16644205,"about_ca_topic_score_gemma":0.7960443,"teacher_disagreement_score":0.62960225,"about_ca_system_score_codex":0.000055421347,"about_ca_system_score_gemma":0.000045892564,"threshold_uncertainty_score":0.8391087},"labels":[],"label_agreement":null},{"id":"W2508921413","doi":"10.1038/sdata.2016.67","title":"Global terrestrial Human Footprint maps for 1993 and 2009","year":2016,"lang":"en","type":"article","venue":"Scientific Data","topic":"Marine animal studies overview","field":"Environmental Science","cited_by":817,"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 Northern British Columbia","funders":"Australian Research Council; James Cook University; Wildlife Conservation Society","keywords":"Footprint; Ecological footprint; Environmental science; Environmental resource management; Land use; Physical geography; Geography; Remote sensing; Ecology; Sustainability; Archaeology","score_opus":0.06895880683861093,"score_gpt":0.3052505647130123,"score_spread":0.23629175787440138,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2508921413","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":[0.93377817,0.00039283567,0.0013195748,0.0030929015,0.003190281,0.0017486569,0.01613598,0.00015815128,0.04018348],"genre_scores_gemma":[0.98672384,0.000036598412,0.0033078254,0.0001453636,0.00026030996,0.00003581378,0.0005360605,0.000015336707,0.00893887],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985084,0.000020160845,0.00016461847,0.00075976586,0.0002544482,0.00029259056],"domain_scores_gemma":[0.9987961,0.000030960764,0.000055800825,0.0010152145,0.0000042479846,0.00009769206],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007486148,0.00010137334,0.00010980794,0.000010994685,0.00035284486,0.00012472794,0.0009429983,0.000024906565,0.0006077405],"category_scores_gemma":[0.00015853079,0.00006708467,0.000023949735,0.00015099751,0.00048336218,0.00021265527,0.0037257406,0.000019640609,0.00023924037],"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":[0.00002312165,0.000052582876,0.07178781,0.000009741029,0.0000115950625,0.0000021094631,0.000013859284,2.6233815e-7,0.0021930686,0.000835143,0.6545734,0.27049732],"study_design_scores_gemma":[0.00048204573,0.0000421742,0.12766258,0.000011826751,0.000012376088,0.000002218432,0.000008629738,0.000020034946,0.000065681925,0.0035433534,0.86803114,0.00011792992],"about_ca_topic_score_codex":0.0009519706,"about_ca_topic_score_gemma":0.0072794114,"teacher_disagreement_score":0.2703794,"about_ca_system_score_codex":0.000074284275,"about_ca_system_score_gemma":0.000008291741,"threshold_uncertainty_score":0.66543317},"labels":[],"label_agreement":null},{"id":"W2511183000","doi":"10.1038/sdata.2016.70","title":"Mean hydrography on the continental shelf from 26 repeat glider deployments along Southeastern Australia","year":2016,"lang":"en","type":"article","venue":"Scientific Data","topic":"Marine and coastal ecosystems","field":"Earth and Planetary Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ocean Networks Canada Society","funders":"Australian Government","keywords":"Continental shelf; Oceanography; Hydrography; Glider; Geology; Boundary current; Stratification (seeds); Continental margin; Upwelling; Ocean current; Water mass; Current (fluid); Paleontology","score_opus":0.05478621495191094,"score_gpt":0.2405939781581103,"score_spread":0.18580776320619935,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2511183000","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":[0.98016834,0.000056706078,0.000035380035,0.0008928636,0.0024055054,0.0002513956,0.012888683,0.000085412576,0.0032157241],"genre_scores_gemma":[0.9902737,0.0000026604382,0.000033378525,0.000092119146,0.00017313598,0.0000015362377,0.0019396169,0.0000066261655,0.0074771857],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99776,0.00012242858,0.00028773822,0.00084309856,0.000586213,0.0004005094],"domain_scores_gemma":[0.9976184,0.0001553947,0.00010955743,0.0019335981,0.000022306982,0.00016079361],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00092447846,0.00017135924,0.00014696577,0.000078928555,0.00034364412,0.00051137304,0.0016000795,0.00004168811,0.006760658],"category_scores_gemma":[0.000049682392,0.00008463916,0.00006646031,0.00025531647,0.00023025226,0.00047833583,0.00023412333,0.000089575406,0.005530264],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048385176,0.000040335643,0.89003944,0.000005949133,0.00006740549,0.000026868038,0.00016569147,0.0000023941889,0.00029893877,0.00008362224,0.07348315,0.0357378],"study_design_scores_gemma":[0.0011378082,0.00014872882,0.52688813,0.00025816442,0.00008267943,0.000018599085,0.0008887445,0.002562994,0.0011480051,0.0016274513,0.46454284,0.0006958916],"about_ca_topic_score_codex":0.011836763,"about_ca_topic_score_gemma":0.052530613,"teacher_disagreement_score":0.39105967,"about_ca_system_score_codex":0.00000220712,"about_ca_system_score_gemma":0.000022880127,"threshold_uncertainty_score":0.995244},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W2518992676","doi":"10.1038/sdata.2016.79","title":"Single-cell transcriptome and epigenomic reprogramming of cardiomyocyte-derived cardiac progenitor cells","year":2016,"lang":"en","type":"letter","venue":"Scientific Data","topic":"Congenital heart defects research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":20,"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":"Cedars-Sinai Medical Center; Division of Chemistry; Massachusetts General Hospital; Heart and Stroke Foundation of Canada; National Cancer Institute; National Institutes of Health; National Science Foundation","keywords":"Epigenomics; Reprogramming; Transcriptome; Biology; DNA methylation; Cell biology; Differentially methylated regions; Myocyte; Regeneration (biology); Induced pluripotent stem cell; Cell; Genetics; Embryonic stem cell; Gene expression; Gene","score_opus":0.03993420189386562,"score_gpt":0.27213786819127384,"score_spread":0.2322036662974082,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2518992676","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":[0.82789856,0.042600334,0.0005473994,0.02402076,0.012950614,0.0059600915,0.08316413,0.00013284582,0.002725227],"genre_scores_gemma":[0.6532077,0.0019088746,0.008287437,0.0128053,0.02601911,0.00046363097,0.1328141,0.0011630745,0.16333078],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.996191,0.00023201169,0.00039148863,0.0019114999,0.00055850344,0.00071547553],"domain_scores_gemma":[0.9955584,0.000045641224,0.00014208921,0.0038982972,0.00021984636,0.00013576586],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010656847,0.00032987533,0.00046666418,0.00019461688,0.00016069203,0.00024790375,0.0014290403,0.0005251796,0.000029414567],"category_scores_gemma":[0.000078534584,0.000291362,0.00020879805,0.00019585146,0.0008525744,0.000015669115,0.0014144896,0.0003880842,0.00005768304],"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":[0.000016690046,0.000015302821,0.000023482453,0.000262307,0.000085559164,0.00002057711,0.000020356563,2.3160952e-8,0.66691726,5.350739e-8,0.3172929,0.015345495],"study_design_scores_gemma":[0.00015951079,0.000078039884,0.0000046942946,0.000029370587,0.000056796453,0.0000057857096,0.000011190709,0.000001808712,0.40411767,0.0000024825629,0.5953288,0.0002038256],"about_ca_topic_score_codex":0.000029138277,"about_ca_topic_score_gemma":0.00001028914,"teacher_disagreement_score":0.2780359,"about_ca_system_score_codex":0.000033084085,"about_ca_system_score_gemma":0.00033945317,"threshold_uncertainty_score":0.99995387},"labels":[],"label_agreement":null},{"id":"W2530539846","doi":"10.1038/sdata.2016.82","title":"Data from a pre-publication independent replication initiative examining ten moral judgement effects","year":2016,"lang":"en","type":"article","venue":"Scientific Data","topic":"Psychology of Moral and Emotional Judgment","field":"Neuroscience","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University of Manitoba","funders":"","keywords":"Replication (statistics); Judgement; Psychology; Political science; Biology; Law","score_opus":0.40607369125410125,"score_gpt":0.36454883497262675,"score_spread":0.04152485628147451,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2530539846","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":[0.87731916,0.00012313073,0.02079123,0.025964519,0.007832482,0.0020135785,0.05719194,0.0004953892,0.008268585],"genre_scores_gemma":[0.9791345,0.000015698719,0.0013006219,0.0015363175,0.00019682698,0.000059469832,0.014576027,0.000016006363,0.00316453],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9957538,0.00023987217,0.0003378934,0.0025828148,0.00075523736,0.00033037356],"domain_scores_gemma":[0.9923386,0.00038297617,0.00024800014,0.0068040458,0.00009109167,0.00013529357],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00175571,0.0001558237,0.00013987806,0.000148083,0.00034467858,0.0002919577,0.003993411,0.000063713574,0.00037419135],"category_scores_gemma":[0.00303308,0.00010889372,0.000015820237,0.0003882521,0.0003709261,0.0021139032,0.0030100322,0.0001104539,0.0014992732],"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":[0.0000621171,0.00041014035,0.0028633357,0.000012312235,0.000021688436,0.0000092584505,0.00017977471,8.62131e-7,0.38390097,0.0009845629,0.5282256,0.08332936],"study_design_scores_gemma":[0.002856388,0.00022423925,0.5926462,0.00032301995,0.000098543256,0.000021084285,0.00009268807,0.0044684983,0.15517692,0.013902895,0.22939508,0.0007944341],"about_ca_topic_score_codex":0.00002462783,"about_ca_topic_score_gemma":0.000027959006,"teacher_disagreement_score":0.5897829,"about_ca_system_score_codex":0.00007334333,"about_ca_system_score_gemma":0.00008664699,"threshold_uncertainty_score":0.9992782},"labels":[],"label_agreement":null},{"id":"W2530955115","doi":"10.1038/sdata.2016.87","title":"Long-term, high frequency in situ measurements of intertidal mussel bed temperatures using biomimetic sensors","year":2016,"lang":"en","type":"article","venue":"Scientific Data","topic":"Physiological and biochemical adaptations","field":"Environmental Science","cited_by":98,"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":"Natural Environment Research Council; National Research Foundation; National Oceanic and Atmospheric Administration; Sight Research UK; National Aeronautics and Space Administration; David and Lucile Packard Foundation; National Geographic Society; National Science Foundation","keywords":"Intertidal zone; Ectotherm; Mussel; Environmental science; Habitat; Data logger; Intertidal ecology; Oceanography; Atmospheric sciences; Ecology; Biology; Geology","score_opus":0.08470878739218475,"score_gpt":0.28391623266699606,"score_spread":0.19920744527481132,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2530955115","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":[0.99885756,0.000018889901,0.000073903706,0.0001654909,0.00024202332,0.00011555441,0.00038998658,0.000013135565,0.00012346506],"genre_scores_gemma":[0.9976898,0.0000012648525,0.0018815019,0.000027015747,0.000013591556,0.0000018411301,0.00020420188,0.0000041356757,0.00017667214],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99851334,0.00006136142,0.00025513797,0.0005865017,0.000345178,0.00023847156],"domain_scores_gemma":[0.9990575,0.000047773654,0.000074996286,0.00072733517,0.00001520994,0.00007721893],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037633113,0.00010379021,0.00012789173,0.000051965373,0.00007819535,0.000038552087,0.0008758267,0.000041910247,0.00067829655],"category_scores_gemma":[0.00023804135,0.00005948619,0.00002808181,0.00043152267,0.0006291932,0.00032912096,0.0007244388,0.000053015316,0.00015231431],"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":[0.000007929623,0.00012718103,0.021833533,0.000004963123,0.0000046288924,0.0000025055294,0.000024652649,0.000004517002,0.9762167,0.0000033906035,0.0005810436,0.0011889538],"study_design_scores_gemma":[0.000325649,0.000018929835,0.18869607,0.000101988444,0.000012375831,0.0000019415509,0.000010805781,0.000099122386,0.8096905,0.00085442356,0.000028981349,0.00015925677],"about_ca_topic_score_codex":0.00016297813,"about_ca_topic_score_gemma":0.00024641227,"teacher_disagreement_score":0.16686255,"about_ca_system_score_codex":0.000068177644,"about_ca_system_score_gemma":0.000014560515,"threshold_uncertainty_score":0.7426871},"labels":[],"label_agreement":null},{"id":"W2550462889","doi":"10.1038/sdata.2016.97","title":"A variant reference data set for the Africanized honeybee, Apis mellifera","year":2016,"lang":"en","type":"article","venue":"Scientific Data","topic":"Plant and animal studies","field":"Agricultural and Biological Sciences","cited_by":30,"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":"Ontario Ministry of Research and Innovation; Natural Sciences and Engineering Research Council of Canada; Fundação de Amparo à Pesquisa do Estado de São Paulo; York University","keywords":"Biology; SNP; Beekeeping; Population; Single-nucleotide polymorphism; Honey bee; Evolutionary biology; Population genetics; Genetics; Zoology; Ecology; Gene; Genotype; Demography","score_opus":0.4006907821873715,"score_gpt":0.29471166432926116,"score_spread":0.10597911785811032,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2550462889","genre_codex":"dataset","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":[0.18773407,0.004666059,0.0016436466,0.06917829,0.003354274,0.0025150522,0.72855186,0.00047682028,0.0018799119],"genre_scores_gemma":[0.97910815,0.00038725327,0.0006634654,0.00023175954,0.00059291936,0.000034363522,0.009673367,0.0000017284384,0.009306993],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99838233,0.000041406685,0.000161207,0.00081781193,0.000264551,0.00033267142],"domain_scores_gemma":[0.99836355,0.0008977394,0.00007407396,0.0005319052,0.00006714968,0.00006555589],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014238419,0.000112338115,0.00013494337,0.0000070535225,0.0008764721,0.00031375588,0.003877245,0.000033523604,0.0003435238],"category_scores_gemma":[0.00049251947,0.000024612104,0.00002360264,0.00031765437,0.00024117908,0.00036565817,0.0021865922,0.000045873767,0.00020931145],"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":[0.00004502066,0.00003468795,0.00023211612,0.0000034687382,0.000031485426,0.0000028885725,0.000030216386,2.0308855e-8,0.23159833,0.0009557918,0.70526856,0.061797384],"study_design_scores_gemma":[0.00015997511,0.000042412397,0.004406234,0.000022913746,0.000031325184,0.0000064739793,0.00020329806,0.00026671245,0.00059225515,0.000927145,0.9931877,0.00015351037],"about_ca_topic_score_codex":0.00015292429,"about_ca_topic_score_gemma":0.0037513913,"teacher_disagreement_score":0.7913741,"about_ca_system_score_codex":0.0000074198374,"about_ca_system_score_gemma":0.000017310627,"threshold_uncertainty_score":0.72049505},"labels":[],"label_agreement":null},{"id":"W2551102403","doi":"10.1038/sdata.2016.95","title":"Systematic chemical-genetic and chemical-chemical interaction datasets for prediction of compound synergism","year":2016,"lang":"en","type":"article","venue":"Scientific Data","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Research in Immunology and Cancer; Université de Montréal; Lunenfeld-Tanenbaum Research Institute; Mount Sinai Hospital; McMaster University","funders":"National Institutes of Health; Génome Québec; National Center for Research Resources; Canada Research Chairs; Wellcome Trust","keywords":"Benchmarking; Pairwise comparison; Benchmark (surveying); Chemical similarity; Computer science; Computational biology; Drug discovery; Data mining; Artificial intelligence; Bioinformatics; Biology; Cluster analysis","score_opus":0.05635813174344787,"score_gpt":0.3235587407957939,"score_spread":0.267200609052346,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2551102403","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":[0.123997524,0.00015150761,0.86136836,0.00040994832,0.001501792,0.0006508033,0.011805463,0.00008249087,0.0000321004],"genre_scores_gemma":[0.8149089,0.0000059449276,0.18054725,0.00003188596,0.00010039151,0.000058704336,0.004254009,0.000016152995,0.000076744895],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99770117,0.00010491948,0.00054910185,0.0009733105,0.00045131502,0.00022017656],"domain_scores_gemma":[0.99634427,0.0011197217,0.00025138454,0.0020451725,0.00013032705,0.00010912135],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013697307,0.00014179746,0.00026432917,0.00012838587,0.00007430449,0.00026048516,0.0017997477,0.000054819695,0.000006167757],"category_scores_gemma":[0.0010820756,0.000104794846,0.000042803655,0.0003106708,0.00028069102,0.0011485692,0.0016169823,0.000056062367,0.000012107356],"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":[0.0000250412,0.00015744225,0.000024736668,0.002401734,0.000068246634,0.0000020900427,0.00012363828,0.000031067437,0.95371,0.0035785257,0.027104419,0.012773024],"study_design_scores_gemma":[0.0014497782,0.000046582543,0.0002667597,0.0033178881,0.00013906795,0.0001711909,0.000039797967,0.58580697,0.38462865,0.019682063,0.004003195,0.00044807268],"about_ca_topic_score_codex":0.000004083564,"about_ca_topic_score_gemma":5.6868237e-7,"teacher_disagreement_score":0.6909114,"about_ca_system_score_codex":0.00006109412,"about_ca_system_score_gemma":0.00008297004,"threshold_uncertainty_score":0.42734098},"labels":[],"label_agreement":null},{"id":"W2552656952","doi":"10.1038/sdata.2016.99","title":"Cross-cultural dataset for the evolution of religion and morality project","year":2016,"lang":"en","type":"article","venue":"Scientific Data","topic":"Cultural Differences and Values","field":"Psychology","cited_by":85,"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":"Social Sciences and Humanities Research Council of Canada; Aarhus Universitet; Canadian Institute for Advanced Research; Masarykova Univerzita; Canada Excellence Research Chairs, Government of Canada; John Templeton Foundation","keywords":"Morality; Epistemology; Sociology; Philosophy","score_opus":0.24840185657579653,"score_gpt":0.47470366138294146,"score_spread":0.22630180480714493,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2552656952","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":[0.8312143,0.00074891554,0.00050590246,0.000942502,0.0019028395,0.00054660864,0.16395831,0.000018461198,0.00016217769],"genre_scores_gemma":[0.9812609,0.000019925581,0.00013681831,0.000017063332,0.00007830417,0.000020234002,0.011022799,0.000003294015,0.0074406792],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99911743,0.000038780516,0.00015024317,0.00042987565,0.00011826717,0.00014542374],"domain_scores_gemma":[0.99854827,0.0001057112,0.00008093973,0.0011553329,0.00008932535,0.000020410389],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007557028,0.000061422936,0.00007589707,0.000020813042,0.00021657748,0.00017281684,0.00063094974,0.000031230873,0.00008679671],"category_scores_gemma":[0.0001929943,0.000024518178,0.000018895642,0.00011532377,0.00066383893,0.00044960115,0.0003050262,0.000024931984,0.000025405847],"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":[0.000057082605,0.000026650063,0.006580506,0.000015061988,0.000018066808,1.3184558e-7,0.00020200043,3.2941333e-8,0.004108376,0.010809463,0.9675296,0.01065305],"study_design_scores_gemma":[0.000772129,0.00007338705,0.22705555,0.00003943624,0.000053325926,0.000007894892,0.0006316248,0.0002202133,0.0002689692,0.0024715557,0.7682682,0.00013770924],"about_ca_topic_score_codex":0.0016959201,"about_ca_topic_score_gemma":0.00031230846,"teacher_disagreement_score":0.22047505,"about_ca_system_score_codex":0.000013727035,"about_ca_system_score_gemma":0.000020865009,"threshold_uncertainty_score":0.25637352},"labels":[],"label_agreement":null},{"id":"W2560741446","doi":"10.1038/sdata.2016.102","title":"Sharing brain mapping statistical results with the neuroimaging data model","year":2016,"lang":"en","type":"article","venue":"Scientific Data","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":68,"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","funders":"National Center for Research Resources; Laura and John Arnold Foundation; National Institute on Drug Abuse; National Institute of Neurological Disorders and Stroke; National Institute of Mental Health; Medical Research Council; U.S. National Library of Medicine; National Institute on Alcohol Abuse and Alcoholism; Ludmer Centre for Neuroinformatics and Mental Health; National Institute of Biomedical Imaging and Bioengineering; Wellcome Trust; National Institutes of Health","keywords":"Metadata; Computer science; Neuroimaging; Software; Representation (politics); Univariate; Data sharing; Data science; External Data Representation; Information retrieval; Data mining; Artificial intelligence; Machine learning; World Wide Web; Programming language; Psychology","score_opus":0.24801594761508433,"score_gpt":0.3328507910988038,"score_spread":0.08483484348371945,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2560741446","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":[0.01616325,0.000042216387,0.56651795,0.3250126,0.0022988047,0.00075714017,0.08244254,0.00042993424,0.0063355546],"genre_scores_gemma":[0.97133535,0.0000054023494,0.0051540853,0.006039927,0.00021899915,0.000015552467,0.0010819011,0.000050083294,0.016098686],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99597764,0.00011906088,0.00021416188,0.0024878501,0.0007587218,0.00044258736],"domain_scores_gemma":[0.98539585,0.007685945,0.000107257896,0.006669062,0.000057501344,0.000084363186],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0029016347,0.00015513462,0.00012555446,0.00009417725,0.0012366758,0.00063196465,0.004707631,0.000016380078,0.000021952255],"category_scores_gemma":[0.032600243,0.00008005823,0.000010475181,0.0005386446,0.0011030571,0.0015902767,0.007579752,0.00015818978,0.00017270929],"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":[0.00006185336,0.000026591837,0.00008646692,0.000009263883,0.000007643397,0.000025070573,0.00016322584,0.00015604802,0.07521239,0.005854346,0.9122017,0.0061953743],"study_design_scores_gemma":[0.0009146842,0.000026994876,0.001092754,0.00009897549,0.000019858848,0.000051901658,0.00016467927,0.5963106,0.0014939798,0.0045155683,0.3949506,0.0003593794],"about_ca_topic_score_codex":0.000019106741,"about_ca_topic_score_gemma":0.00012574058,"teacher_disagreement_score":0.9551721,"about_ca_system_score_codex":0.000040025283,"about_ca_system_score_gemma":0.00015950638,"threshold_uncertainty_score":0.97554857},"labels":[],"label_agreement":null},{"id":"W2572195345","doi":"10.1038/sdata.2016.127","title":"A dataset of human decision-making in teamwork management","year":2017,"lang":"en","type":"article","venue":"Scientific Data","topic":"Cognitive Science and Mapping","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Natural Science Foundation of China; Nanyang Technological University; National Research Foundation","keywords":"Teamwork; Task (project management); Computer science; Bridge (graph theory); Baseline (sea); Knowledge management; Scale (ratio); Business decision mapping; Resource (disambiguation); Data science; Decision support system; Management science; Artificial intelligence; Engineering; Systems engineering","score_opus":0.09217427782541991,"score_gpt":0.39287430398431183,"score_spread":0.3007000261588919,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2572195345","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":[0.091899365,0.00021888544,0.85017693,0.0010454996,0.0080577275,0.0012834236,0.01181505,0.00013034837,0.035372768],"genre_scores_gemma":[0.9513673,0.0000037981174,0.047663435,0.000057800768,0.000021356766,0.0000040379414,0.0006466081,0.0000031430095,0.00023250084],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99794465,0.000025208205,0.00027718217,0.0009536802,0.00051136763,0.00028789014],"domain_scores_gemma":[0.99304795,0.00006022837,0.00020099554,0.006593554,0.000048202084,0.0000490536],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0029725125,0.00008288697,0.000121807076,0.0002908196,0.0007909365,0.0013442346,0.010983896,0.000018433426,0.00003153152],"category_scores_gemma":[0.0002955143,0.000075480006,0.000018081857,0.0004721572,0.00035617632,0.0025218243,0.010299515,0.00007342363,0.000083534076],"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":[0.000003482313,0.00013059574,0.0027469117,0.000031551503,0.0000093232875,0.00009338095,0.0004074856,0.0000062034965,0.00079585484,0.017402982,0.13338418,0.84498805],"study_design_scores_gemma":[0.0018953625,0.000096113545,0.2935562,0.003575454,0.000039388502,0.000022280185,0.001046721,0.07355669,0.0011846182,0.17805958,0.44570303,0.0012645576],"about_ca_topic_score_codex":0.00003386179,"about_ca_topic_score_gemma":0.0002986824,"teacher_disagreement_score":0.859468,"about_ca_system_score_codex":0.000016309947,"about_ca_system_score_gemma":0.000044005636,"threshold_uncertainty_score":0.99969244},"labels":[],"label_agreement":null},{"id":"W2574380552","doi":"10.1038/sdata.2016.129","title":"Two replications of an investigation on empathy and utilitarian judgement across socioeconomic status","year":2017,"lang":"en","type":"review","venue":"Scientific Data","topic":"Psychological Well-being and Life Satisfaction","field":"Psychology","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":"Western University","funders":"","keywords":"Empathy; Socioeconomic status; Judgement; Psychology; Social psychology; Sociology; Demography; Political science","score_opus":0.3656238084735312,"score_gpt":0.5101224505794041,"score_spread":0.14449864210587288,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2574380552","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":[0.009551764,0.9395292,0.000022742073,0.00015382029,0.008015662,0.0015391181,0.027885599,0.0001181101,0.013184016],"genre_scores_gemma":[0.004830706,0.9281871,0.0008785535,0.00014354546,0.0005200643,0.00025231505,0.055923503,0.00008550749,0.009178748],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99651843,0.000393125,0.0007020675,0.0018042057,0.00018773174,0.00039443423],"domain_scores_gemma":[0.9921522,0.00014914511,0.0008636199,0.006573271,0.000049226583,0.00021253928],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028339943,0.00026784404,0.00070456386,0.0001635676,0.00064473844,0.00033530832,0.0013964911,0.00022980684,0.00039296318],"category_scores_gemma":[0.00018344846,0.00022949056,0.000094131006,0.000120567696,0.0009089481,0.00030972075,0.000420788,0.0003394973,0.00077791046],"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":[0.000007834938,0.00008963422,0.00007555653,0.00033462874,0.00007277957,0.0000013252361,0.00094755174,1.344795e-7,5.82048e-7,0.0015555379,0.019728992,0.9771854],"study_design_scores_gemma":[0.0002502681,0.00007808428,0.0032242357,0.0005423325,0.0001455723,0.000006869413,0.00034029968,0.000013498742,5.0094343e-7,0.0014060572,0.99377275,0.00021952977],"about_ca_topic_score_codex":0.00047133965,"about_ca_topic_score_gemma":0.00021527552,"teacher_disagreement_score":0.9769659,"about_ca_system_score_codex":0.000075137126,"about_ca_system_score_gemma":0.0001456689,"threshold_uncertainty_score":0.99987245},"labels":[],"label_agreement":null},{"id":"W2577333108","doi":"10.1038/sdata.2016.132","title":"Whole genome sequencing data and de novo draft assemblies for 66 teleost species","year":2017,"lang":"en","type":"article","venue":"Scientific Data","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":85,"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 Science Council; Chiba University; Universitetet i Oslo; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; McGill University; Norges Forskningsråd; Norwegian Sequencing Centre; Thünen-Institut; Pinngortitaleriffik; Norges Teknisk-Naturvitenskapelige Universitet; National Science Foundation","keywords":"Phylogenetic tree; Biology; Genome; Evolutionary biology; Computational biology; Phylogenetics; Genomics; Whole genome sequencing; Comparative genomics; Genetics; Gene","score_opus":0.10669312967114036,"score_gpt":0.3204797343100458,"score_spread":0.21378660463890542,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2577333108","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":[0.96395516,0.0025283727,0.0017855008,0.0006458295,0.0007718009,0.0002704542,0.02877758,0.0000049016867,0.0012604113],"genre_scores_gemma":[0.97647387,0.00024663197,0.007944902,0.00007770117,0.000432027,0.000008930958,0.009106059,0.000018658046,0.0056912377],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985868,0.000014025413,0.00014054094,0.00086108345,0.000098428354,0.00029917705],"domain_scores_gemma":[0.99558324,0.000016383286,0.00010094141,0.0041534714,0.00007346441,0.000072506395],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00090508146,0.00012263401,0.00012586408,0.000030366697,0.0010355816,0.00074646826,0.0023995885,0.00005606012,0.000005535918],"category_scores_gemma":[0.0004634121,0.00011428089,0.000020064088,0.000026957561,0.00045911432,0.000010937307,0.0044797165,0.000039268554,0.0000065978124],"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":[0.000009132903,0.000010690438,0.0024768594,0.000022785365,0.000045279055,0.0000015018488,0.00007592166,0.000002216075,0.97797215,0.000042438438,0.017574918,0.0017660906],"study_design_scores_gemma":[0.000287858,0.000039257964,0.018337,0.000008741278,0.0000359349,0.000013688259,0.00031076703,0.00046968384,0.019871281,0.00025532756,0.9601724,0.00019803272],"about_ca_topic_score_codex":0.000025563055,"about_ca_topic_score_gemma":0.0005096371,"teacher_disagreement_score":0.95810086,"about_ca_system_score_codex":0.000009508981,"about_ca_system_score_gemma":0.00015711277,"threshold_uncertainty_score":0.7964961},"labels":[],"label_agreement":null},{"id":"W2580202562","doi":"10.1038/sdata.2016.120","title":"A 4-study replication of the moderating effects of greed on socioeconomic status and unethical behaviour","year":2017,"lang":"en","type":"review","venue":"Scientific Data","topic":"Experimental Behavioral Economics Studies","field":"Social Sciences","cited_by":25,"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":"Socioeconomic status; Replication (statistics); Psychology; Social psychology; Sociology; Biology; Demography; Virology","score_opus":0.27686203510584495,"score_gpt":0.48794559857871705,"score_spread":0.2110835634728721,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2580202562","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":[0.059092816,0.93151677,5.125535e-7,0.00008821622,0.0021165588,0.003777542,0.002059221,0.000022351409,0.0013260085],"genre_scores_gemma":[0.12160061,0.87605333,0.00013195856,0.000009467466,0.0001043492,0.00017297403,0.0005145086,0.000039885377,0.0013729207],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975666,0.00039835565,0.0005521,0.0009839752,0.000263188,0.00023579525],"domain_scores_gemma":[0.99512094,0.00028453994,0.0010595232,0.0034188079,0.000052802196,0.00006341185],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0027915488,0.00018022413,0.00079675263,0.00007887362,0.0013038315,0.00025451634,0.0019148313,0.00014155537,0.000007185983],"category_scores_gemma":[0.00074146717,0.0001354707,0.000115116236,0.000082392406,0.0017568241,0.00021632737,0.0017088397,0.00025031588,0.000010507157],"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":[0.000007162677,0.00083612924,0.006783401,0.0029085341,0.00020364994,0.0000024232804,0.024335012,4.1232417e-7,0.000026060436,0.0043618805,0.002946694,0.9575886],"study_design_scores_gemma":[0.0018864782,0.0006499082,0.011207361,0.01656665,0.0046193455,0.0000043026234,0.020197934,0.00006707077,0.00025411198,0.0016672113,0.940811,0.002068652],"about_ca_topic_score_codex":0.002060818,"about_ca_topic_score_gemma":0.001891671,"teacher_disagreement_score":0.95552,"about_ca_system_score_codex":0.00016065678,"about_ca_system_score_gemma":0.00049156544,"threshold_uncertainty_score":0.99999636},"labels":[],"label_agreement":null},{"id":"W2607313420","doi":"10.1038/sdata.2017.35","title":"A geographically-diverse collection of 418 human gut microbiome pathway genome databases","year":2017,"lang":"en","type":"article","venue":"Scientific Data","topic":"Gut microbiota and health","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","funders":"Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; Genome Alberta; King Abdullah University of Science and Technology; Genome British Columbia; Genome Canada; Tula Foundation; School of Medicine, Stanford University; Compute Canada; National Institute of General Medical Sciences; Canadian Institute for Advanced Research","keywords":"Metagenomics; Microbiome; Human Microbiome Project; Compendium; Human microbiome; Computational biology; Annotation; Biology; Data science; Genome; Bioinformatics; Computer science; Genetics; Gene; Geography","score_opus":0.07441962437904774,"score_gpt":0.336488425230079,"score_spread":0.26206880085103124,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2607313420","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":[0.9842228,0.00024164408,0.00016549329,0.00011188115,0.000802423,0.00024187022,0.01358143,0.000011453343,0.0006209699],"genre_scores_gemma":[0.9679075,0.000067347355,0.0012541977,0.00005113785,0.0001244764,0.00000349985,0.025610438,0.000013933837,0.0049674623],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99856764,0.000039943614,0.00023136944,0.00076366833,0.00012373498,0.00027366178],"domain_scores_gemma":[0.9958752,0.0000036169697,0.00023299486,0.003670656,0.0001235913,0.000093956885],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00071394956,0.00011936661,0.00014464535,0.00011937217,0.0011329539,0.00016844479,0.0015921061,0.000076376156,0.00013612112],"category_scores_gemma":[0.000099642835,0.000115494935,0.000054820055,0.00012460603,0.0006787038,0.000023848077,0.0016943315,0.0000700651,0.000032043266],"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":[0.000016791155,0.00009396248,0.002267977,0.00004029074,0.000023795827,0.000002207684,0.00002025246,2.3996031e-7,0.96014714,0.00004856566,0.037023522,0.00031524219],"study_design_scores_gemma":[0.0007455849,0.00013253168,0.09355474,0.000037446833,0.000034820656,0.000017645478,0.000069601345,0.000010872025,0.13518798,0.000027955342,0.76991326,0.0002675603],"about_ca_topic_score_codex":0.00033429853,"about_ca_topic_score_gemma":0.0012509044,"teacher_disagreement_score":0.82495916,"about_ca_system_score_codex":0.000008870437,"about_ca_system_score_gemma":0.00018120135,"threshold_uncertainty_score":0.87138796},"labels":[],"label_agreement":null},{"id":"W2612115609","doi":"10.1038/sdata.2017.65","title":"Modern pollen data from the Canadian Arctic, 1972–1973","year":2017,"lang":"en","type":"article","venue":"Scientific Data","topic":"Geology and Paleoclimatology Research","field":"Earth and Planetary Sciences","cited_by":1,"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":"University of Colorado Boulder; National Science Foundation","keywords":"Pollen; Arctic; Taiga; Tundra; Physical geography; Transect; Environmental science; Vegetation (pathology); Moss; Sampling (signal processing); Boreal; Geography; Ecology; Geology; Oceanography; Forestry; Biology; Archaeology","score_opus":0.17918023584812012,"score_gpt":0.3210715420865105,"score_spread":0.14189130623839039,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2612115609","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":[0.47988775,0.0058135875,0.0000705036,0.09259708,0.015258995,0.0010428017,0.25397637,0.000102457976,0.15125045],"genre_scores_gemma":[0.95170534,0.000022455262,0.0002933737,0.00030230772,0.00014965265,4.243181e-7,0.044055242,0.0000022879362,0.0034689216],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9976959,0.00016479022,0.00014911735,0.0009917496,0.00036965063,0.0006287928],"domain_scores_gemma":[0.9886819,0.00030550687,0.000081517544,0.0105720665,0.00005988603,0.00029908487],"candidate_categories":["sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002784423,0.000111161426,0.00013527281,0.00006634122,0.005434528,0.00148179,0.014034066,0.000108481974,0.0068181357],"category_scores_gemma":[0.0012706894,0.00007364309,0.000016938722,0.00010048553,0.001829561,0.0009761489,0.0010861136,0.00034746592,0.0066486285],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000065289787,0.0000037618327,0.8743035,0.0000019956733,0.000019892075,0.000030560706,0.00006987971,0.000004702641,7.568389e-7,0.000032714077,0.121406384,0.0041192807],"study_design_scores_gemma":[0.00011771334,0.0000050311646,0.80974406,0.0000078793555,0.000016588958,0.00001356303,0.00004716007,0.028564516,0.0000017140177,0.0037666133,0.15761796,0.00009719965],"about_ca_topic_score_codex":0.63534087,"about_ca_topic_score_gemma":0.996546,"teacher_disagreement_score":0.47181758,"about_ca_system_score_codex":0.0000019573095,"about_ca_system_score_gemma":0.00078295264,"threshold_uncertainty_score":0.99955475},"labels":[],"label_agreement":null},{"id":"W2624462411","doi":"10.1038/sdata.2017.88","title":"A global multiproxy database for temperature reconstructions of the Common Era","year":2017,"lang":"en","type":"article","venue":"Scientific Data","topic":"Tree-ring climate responses","field":"Earth and Planetary Sciences","cited_by":532,"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; University of Regina; University of Ottawa; University of Toronto; Institut National de la Recherche Scientifique","funders":"U.S. Geological Survey; National Centers for Environmental Information; National Oceanic and Atmospheric Administration; Natural Environment Research Council; Sight Research UK","keywords":"Proxy (statistics); Database; Temperature record; Climate change; Sea surface temperature; Climatology; Geology; Physical geography; Oceanography; Geography; Computer science","score_opus":0.059064136772069696,"score_gpt":0.30584740734923593,"score_spread":0.24678327057716623,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2624462411","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":[0.8138793,0.00014721665,0.000014311265,0.00069739,0.003999238,0.00034700893,0.17973612,0.000024019846,0.0011553545],"genre_scores_gemma":[0.9905133,0.0000060368816,0.0042362395,0.000021028081,0.0000667341,0.000001268888,0.0044123265,0.0000021582605,0.0007408584],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9988682,0.00005312631,0.00017291325,0.0004523381,0.00023365373,0.00021972274],"domain_scores_gemma":[0.9958192,0.0001243715,0.00017600125,0.0037564225,0.00005607987,0.00006790127],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.00083208596,0.000086520544,0.00011687232,0.00003139432,0.0016098106,0.0005928107,0.0028442922,0.000039462768,0.00021280345],"category_scores_gemma":[0.0008470828,0.000055850764,0.000043374384,0.00015711953,0.0008061797,0.0006906871,0.0003289637,0.00008040385,0.00003990757],"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":[0.00009184222,0.000034834975,0.86905587,0.000065909684,0.000025612271,0.0000024991286,0.000043991917,0.00006272725,0.0010659788,0.00021448656,0.07363285,0.055703405],"study_design_scores_gemma":[0.00032936505,0.000016243619,0.9365037,0.00007380939,0.000030387544,0.000028619237,0.00010107335,0.004774453,0.00066981895,0.00042160475,0.056932747,0.00011815586],"about_ca_topic_score_codex":0.0012841925,"about_ca_topic_score_gemma":0.03493645,"teacher_disagreement_score":0.17663401,"about_ca_system_score_codex":0.0000036238794,"about_ca_system_score_gemma":0.00015929474,"threshold_uncertainty_score":0.99968994},"labels":[],"label_agreement":null},{"id":"W2724559516","doi":"10.1038/sdata.2017.77","title":"Matched computed tomography segmentation and demographic data for oropharyngeal cancer radiomics challenges","year":2017,"lang":"en","type":"article","venue":"Scientific Data","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":82,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Columbia College","funders":"Division of Mathematical Sciences; National Cancer Institute; National Science Foundation; National Institutes of Health; Andrew Sabin Family Foundation; National Institute of Dental and Craniofacial Research; University of Texas MD Anderson Cancer Center; Radiological Society of North America; Varian Medical Systems","keywords":"Radiomics; Head and neck cancer; Medicine; Data extraction; Workflow; Segmentation; Leverage (statistics); Radiation therapy; Medical physics; Computer science; Artificial intelligence; Radiology; MEDLINE; Database; Biology","score_opus":0.09448940482926785,"score_gpt":0.37674825807600376,"score_spread":0.28225885324673594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2724559516","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":[0.77799064,0.044782482,0.047226593,0.08535209,0.015092096,0.0043260613,0.023820817,0.0004084453,0.0010007658],"genre_scores_gemma":[0.8541233,0.0059711267,0.09470906,0.00088159397,0.0013393855,0.00006149003,0.04199309,0.00009815163,0.0008227955],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982206,0.000028670382,0.00021470328,0.000972508,0.00028787358,0.00027564066],"domain_scores_gemma":[0.9958059,0.00007293848,0.00017976286,0.0036602835,0.00008052671,0.00020054872],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016351898,0.00013556996,0.00029148805,0.00017628864,0.0007912761,0.0005112151,0.0015824379,0.000053928452,0.000020198542],"category_scores_gemma":[0.00038430045,0.00011653217,0.000031423337,0.00011146228,0.00063385715,0.0006070396,0.0011329748,0.00017800427,0.0000023798852],"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":[0.00018174564,0.00022938062,0.03498465,0.00095561094,0.0004250823,0.000032544944,0.0004903716,0.0000061262185,0.018744119,0.0004938665,0.16410421,0.7793523],"study_design_scores_gemma":[0.006485338,0.00013107811,0.21285935,0.00054791546,0.0008018622,0.0000906389,0.0004557519,0.6111767,0.00061480823,0.0009736704,0.16533661,0.0005262312],"about_ca_topic_score_codex":0.00010959691,"about_ca_topic_score_gemma":0.00009736188,"teacher_disagreement_score":0.77882606,"about_ca_system_score_codex":0.000012793372,"about_ca_system_score_gemma":0.000096831245,"threshold_uncertainty_score":0.6085936},"labels":[],"label_agreement":null},{"id":"W2734439118","doi":"10.1038/sdata.2017.90","title":"A multi-protease, multi-dissociation, bottom-up-to-top-down proteomic view of the Loxosceles intermedia venom","year":2017,"lang":"en","type":"article","venue":"Scientific Data","topic":"Venomous Animal Envenomation and Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"IONICS Mass Spectrometry (Canada)","funders":"National Institutes of Health; Fundação Carlos Chagas Filho de Amparo à Pesquisa do Estado do Rio de Janeiro; Conselho Nacional de Desenvolvimento Científico e Tecnológico; National Institute of General Medical Sciences; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior","keywords":"Orbitrap; Venom; Trypsin; Proteome; Proteomics; Mass spectrometry; Protease; Chemistry; Computational biology; Tandem mass spectrometry; Chromatography; Shotgun proteomics; Biochemistry; Biology; Enzyme","score_opus":0.05228829954185441,"score_gpt":0.31943914345594576,"score_spread":0.26715084391409133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2734439118","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":[0.9901866,0.00051373924,0.0016950828,0.0011494936,0.0017806204,0.0011659785,0.0032583654,0.000016446726,0.00023370078],"genre_scores_gemma":[0.9902759,0.000024197496,0.0027670069,0.00008992419,0.00008562374,0.000038337086,0.0005578182,0.000013405725,0.00614778],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9987385,0.000059848,0.00025216176,0.0005528168,0.00018951276,0.00020715619],"domain_scores_gemma":[0.99711806,0.0000047115573,0.00027873923,0.0023722295,0.0001570668,0.00006921969],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006828154,0.00012584025,0.00016076925,0.000032682932,0.0007645614,0.0002007971,0.00199221,0.00006396892,0.000020999325],"category_scores_gemma":[0.001146882,0.000093157425,0.000069119655,0.00007447377,0.00040233557,0.000017210661,0.0017930571,0.000080868194,0.000053654065],"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":[0.000040636376,0.00023918979,0.01324175,0.00009976885,0.00010068917,0.0000011237297,0.00091166503,0.000005189719,0.9345074,0.000053822318,0.043224204,0.007574509],"study_design_scores_gemma":[0.002169709,0.00017501958,0.47147244,0.00025334195,0.000088758825,0.000006713015,0.00069790083,0.002647327,0.19128947,0.00006615762,0.33050188,0.0006312858],"about_ca_topic_score_codex":0.00006702842,"about_ca_topic_score_gemma":0.0005339006,"teacher_disagreement_score":0.743218,"about_ca_system_score_codex":0.000015629326,"about_ca_system_score_gemma":0.00013518234,"threshold_uncertainty_score":0.58804655},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"bench_or_experimental","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W2739179469","doi":"10.1038/sdata.2017.92","title":"A metagenomic survey of forest soil microbial communities more than a decade after timber harvesting","year":2017,"lang":"en","type":"article","venue":"Scientific Data","topic":"Forest Ecology and Biodiversity Studies","field":"Agricultural and Biological Sciences","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 British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Genome British Columbia; Genome Canada","keywords":"Ecology; Metagenomics; Forest ecology; Environmental science; Agroforestry; Amplicon sequencing; Ecosystem; Logging; Geography; Biology","score_opus":0.1239401510660578,"score_gpt":0.2728545170211218,"score_spread":0.148914365955064,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2739179469","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":[0.98792106,0.00008918013,3.749328e-7,0.00044377174,0.00047920752,0.00010081512,0.0107139265,0.000015716538,0.00023594838],"genre_scores_gemma":[0.9945384,0.000008384387,0.00008848717,0.000040777995,0.000037563335,0.0000015648208,0.0030944715,5.383253e-7,0.0021897617],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9990257,0.00010431611,0.00016158188,0.0003175759,0.00013405505,0.00025676948],"domain_scores_gemma":[0.9988733,0.00017008444,0.00018354013,0.0006118062,0.000113572605,0.000047725214],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0013285293,0.000109547655,0.00018765753,0.00001620104,0.0018232686,0.00036581204,0.0023027947,0.00006630929,0.00020618162],"category_scores_gemma":[0.00030075866,0.000046182722,0.000045609402,0.00009876608,0.0015982657,0.00043583903,0.002927698,0.00010220003,0.000092309354],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041073206,0.000053325824,0.98368555,0.000008103325,0.00003607411,0.0000039110905,0.00024112054,0.0000016915395,0.0015344016,0.000007523118,0.013578038,0.0008091735],"study_design_scores_gemma":[0.000090507114,0.000027486434,0.9924834,0.00001752134,0.0000250396,0.0000022475815,0.0003985758,0.000068907946,0.00016897997,0.000032992233,0.006575693,0.00010864662],"about_ca_topic_score_codex":0.018135078,"about_ca_topic_score_gemma":0.38693482,"teacher_disagreement_score":0.36879975,"about_ca_system_score_codex":0.0000082046,"about_ca_system_score_gemma":0.000016788728,"threshold_uncertainty_score":0.9994762},"labels":[],"label_agreement":null},{"id":"W2739974442","doi":"10.1038/sdata.2017.97","title":"Morphology of Dbx1 respiratory neurons in the preBötzinger complex and reticular formation of neonatal mice","year":2017,"lang":"en","type":"article","venue":"Scientific Data","topic":"Neuroscience of respiration and sleep","field":"Neuroscience","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":"Women and Children’s Health Research Institute; University of Alberta","funders":"National Institute of Neurological Disorders and Stroke; National Heart, Lung, and Blood Institute; National Institutes of Health","keywords":"Reticular connective tissue; Brainstem; Neuroscience; Reticular formation; Biology; Respiratory system; Biological neural network; Medulla; Medulla oblongata; Neuron; Anatomy; Central nervous system","score_opus":0.18026719664256857,"score_gpt":0.34651966745746965,"score_spread":0.16625247081490108,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2739974442","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":[0.9968766,0.00002491431,0.00024961203,0.0008032333,0.00039840254,0.00024905687,0.00048117177,0.0000061840433,0.00091081613],"genre_scores_gemma":[0.999291,0.000004987257,0.0001404073,0.00046623874,0.000009662018,0.0000024360472,0.00002260985,0.0000035669439,0.000059083195],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99848,0.00021160785,0.00027365718,0.00047213968,0.00039995575,0.00016260483],"domain_scores_gemma":[0.9975502,0.0001177828,0.00029020882,0.0019697712,0.000038387385,0.00003366591],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014062264,0.00006944129,0.00011198914,0.00013339691,0.0004333904,0.00024695945,0.0022495713,0.000026336784,0.000023449009],"category_scores_gemma":[0.0021293254,0.000051719846,0.000017610437,0.0002060133,0.001735833,0.0008074455,0.0006829853,0.000098907665,0.000005725065],"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":[0.000010007828,0.000032803004,0.00027589605,0.000016576174,2.0331537e-7,0.000009709943,0.0003402305,0.0000053120502,0.9914537,0.0008438262,0.0036617192,0.0033499931],"study_design_scores_gemma":[0.0011074499,0.00020985084,0.056380197,0.00004330611,0.000017973434,0.00010014673,0.0005004948,0.024064533,0.72637075,0.00058890664,0.19036731,0.0002490567],"about_ca_topic_score_codex":0.00001302592,"about_ca_topic_score_gemma":0.000040551564,"teacher_disagreement_score":0.26508296,"about_ca_system_score_codex":0.0000033108283,"about_ca_system_score_gemma":0.000037172507,"threshold_uncertainty_score":0.6395749},"labels":[],"label_agreement":null},{"id":"W2744041574","doi":"10.1038/sdata.2017.101","title":"Long-term chloride concentrations in North American and European freshwater lakes","year":2017,"lang":"en","type":"article","venue":"Scientific Data","topic":"Smart Materials for Construction","field":"Environmental Science","cited_by":64,"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 Biodiversity Monitoring Institute; University of Waterloo; Ministry of the Environment, Conservation and Parks; Queen's University","funders":"U.S. Geological Survey; Ministry of Environment; Analyses et Expérimentations pour les Ecosystèmes; Global Lake Ecological Observatory Network; Suomen Ympäristökeskus; Institut National de la Recherche Agronomique; Alberta Environment and Parks; U.S. Environmental Protection Agency; Watershed Watch Salmon Society; Wisconsin Department of Natural Resources; National Science Foundation","keywords":"Impervious surface; Environmental science; Water quality; Chloride; Limnology; Precipitation; Drainage basin; Hydrology (agriculture); Freshwater ecosystem; Ecosystem; Watershed; Ecology; Lake ecosystem; Physical geography; Geography; Geology; Chemistry; Biology","score_opus":0.028046134789227534,"score_gpt":0.2566401330719734,"score_spread":0.22859399828274587,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2744041574","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":[0.9970126,0.000002971024,0.000020283831,0.00014156915,0.0010360489,0.00010993176,0.0007792003,0.000020285544,0.00087707845],"genre_scores_gemma":[0.99870366,0.000005276535,0.00029860294,0.000019513524,0.00005012393,0.0000020337143,0.0006763516,0.0000070792657,0.00023733069],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9989197,0.000041659,0.00014257841,0.0005229493,0.00016948013,0.00020358783],"domain_scores_gemma":[0.9982078,0.000007777204,0.000108727894,0.0015997054,0.00000417202,0.00007180041],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046445854,0.000076813274,0.00007986152,0.000028421426,0.00052511395,0.0007921182,0.0009780199,0.000007719956,0.00031487524],"category_scores_gemma":[0.00008064175,0.000069023634,0.000007755293,0.00009735629,0.0016890545,0.0009710939,0.0012539283,0.00004611694,0.000555278],"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":[0.0000039519327,0.00001377442,0.98885787,0.0000018652527,0.0000016287372,0.000011100396,0.00009302532,0.0000029446144,0.0052813757,0.0000050008866,0.0019042124,0.003823239],"study_design_scores_gemma":[0.0001241891,0.000005761815,0.98867047,0.0000047711187,0.0000047439157,0.0000070904707,0.000016497908,0.00015261435,0.0014112036,0.000010136605,0.009505401,0.000087112385],"about_ca_topic_score_codex":0.00065128563,"about_ca_topic_score_gemma":0.17494464,"teacher_disagreement_score":0.17429335,"about_ca_system_score_codex":0.000025539535,"about_ca_system_score_gemma":0.000007317369,"threshold_uncertainty_score":0.8401105},"labels":[],"label_agreement":null},{"id":"W2750304043","doi":"10.1038/sdata.2017.112","title":"FANTOM5 CAGE profiles of human and mouse samples","year":2017,"lang":"en","type":"article","venue":"Scientific Data","topic":"Immunotherapy and Immune Responses","field":"Immunology and Microbiology","cited_by":362,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Child and Family Research Institute; University of British Columbia","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; Diamantina Institute, University of Queensland; RIKEN; Tokyo Medical and Dental University; Biotechnology and Biological Sciences Research Council; Universitätsklinikum Regensburg; Deutsches Zentrum für Neurodegenerative Erkrankungen; Karolinska Institutet; Universiteit van Amsterdam; International Centre for Genetic Engineering and Biotechnology; University of Queensland; University of Cape Town; Ministry of Education, Culture, Sports, Science and Technology; South African Medical Research Council; Medical Research Council; University of Texas Health Science Center at Houston; Wellcome Trust; National Institute on Deafness and Other Communication Disorders; Child and Family Research Institute; National Cancer Institute; Eidgenössische Technische Hochschule Zürich; Melanoma Research Alliance","keywords":"Biology; Computational biology; Transcription (linguistics); Cage; Genome; Promoter; Gene; Pipeline (software); Workflow; Gene expression; Cell biology; Genetics; Computer science; Database","score_opus":0.08039608286432703,"score_gpt":0.3263989378373338,"score_spread":0.24600285497300678,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2750304043","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":[0.9912811,0.003955258,0.00001842092,0.00009833983,0.0007884635,0.00014943615,0.003118836,0.000025369525,0.00056478835],"genre_scores_gemma":[0.9661128,0.000076191165,0.00010406048,0.00001032887,0.000009507888,0.0000033160964,0.00194655,0.000008799429,0.03172846],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990539,0.0000973687,0.00019906374,0.00039855312,0.000037198082,0.00021392084],"domain_scores_gemma":[0.9968587,0.000055387452,0.0001910799,0.0028394463,0.000045007353,0.000010374931],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.00086776854,0.000098855715,0.00018409302,0.00008755303,0.0013618696,0.00019075451,0.0015813066,0.000081405655,0.00040517407],"category_scores_gemma":[0.00027627446,0.00008069646,0.000025080526,0.00003537716,0.001837314,0.00039859893,0.0009135972,0.00010079762,0.00008487485],"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":[0.00005923555,0.000051290564,0.001706296,0.00001870064,0.00005496746,7.730594e-7,0.0002770536,1.2167916e-8,0.9733546,0.00072454737,0.016412277,0.0073402664],"study_design_scores_gemma":[0.00066812045,0.00006226732,0.032595247,0.000037449303,0.000019572606,0.000012455465,0.0002285719,0.0000013582884,0.77782756,0.00013681414,0.18828279,0.00012780039],"about_ca_topic_score_codex":0.00036909225,"about_ca_topic_score_gemma":0.00008391684,"teacher_disagreement_score":0.19552702,"about_ca_system_score_codex":0.0000041672947,"about_ca_system_score_gemma":0.000049375158,"threshold_uncertainty_score":0.99993825},"labels":[],"label_agreement":null},{"id":"W2751862616","doi":"10.1038/sdata.2017.105","title":"RefEx, a reference gene expression dataset as a web tool for the functional analysis of genes","year":2017,"lang":"en","type":"article","venue":"Scientific Data","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","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 Bioscience Database Center; Institute of Genetics; Japan Science and Technology Agency; Ministry of Education, Culture, Sports, Science and Technology","keywords":"Annotation; Gene; Computational biology; Metadata; Gene ontology; Gene Annotation; Gene nomenclature; Expression (computer science); Biology; Gene expression; Information retrieval; Gene expression profiling; Computer science; Database; Bioinformatics; Genetics; World Wide Web; Genome","score_opus":0.12038063034953955,"score_gpt":0.36283514841942693,"score_spread":0.24245451806988738,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2751862616","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":[0.62982386,0.004269079,0.07008297,0.0021421118,0.0044002654,0.0014420301,0.28688398,0.00003107206,0.0009246247],"genre_scores_gemma":[0.81897646,0.0002266246,0.0021032589,0.00010545137,0.00016751852,0.00007628618,0.17398435,0.000009651564,0.004350402],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987948,0.000030368505,0.00018001793,0.0006400058,0.00022885678,0.00012593214],"domain_scores_gemma":[0.99496686,0.000019057916,0.00023882999,0.004605688,0.00013146357,0.00003807129],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006597041,0.00008133443,0.000101093894,0.000070716356,0.000650298,0.00019949452,0.0016429754,0.000060971048,0.0001134695],"category_scores_gemma":[0.00029864578,0.000054855038,0.000053786865,0.00013050962,0.00022626323,0.000020701946,0.0008493607,0.000034610097,0.000008475773],"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":[0.00005727704,0.000021029753,0.00030421067,0.0000046107953,0.00007612059,6.462924e-8,0.0000037026346,0.00004001763,0.6950383,0.000029678804,0.30068985,0.0037351467],"study_design_scores_gemma":[0.0001952992,0.00001642532,0.004738125,0.000005446107,0.00016659514,5.850317e-7,0.000025895904,0.0020193753,0.24200271,0.000018546016,0.7507408,0.00007019124],"about_ca_topic_score_codex":0.000017148366,"about_ca_topic_score_gemma":0.000088397646,"teacher_disagreement_score":0.4530356,"about_ca_system_score_codex":0.0000045896713,"about_ca_system_score_gemma":0.00016010473,"threshold_uncertainty_score":0.50016326},"labels":[],"label_agreement":null},{"id":"W2755202310","doi":"10.1038/sdata.2017.127","title":"Machine-learned and codified synthesis parameters of oxide materials","year":2017,"lang":"en","type":"article","venue":"Scientific Data","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":175,"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":"Office of Naval Research; Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Computer science; Scale (ratio); Artificial intelligence; Computation; Machine learning; Programming language","score_opus":0.08278359054886814,"score_gpt":0.3268148658449304,"score_spread":0.24403127529606228,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2755202310","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":[0.9905173,0.00005663545,0.00032641197,0.00054147025,0.002515672,0.00022904148,0.0047785873,0.000078160185,0.0009566776],"genre_scores_gemma":[0.9699031,0.000014881896,0.02877776,0.000029030805,0.000032620854,0.000011706361,0.00014994113,0.000020086225,0.0010608641],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99683934,0.00028836678,0.00051758526,0.0012615398,0.00063401466,0.00045913697],"domain_scores_gemma":[0.9933129,0.00025956496,0.00073391997,0.005453164,0.00008859202,0.00015183893],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0070464252,0.00021225879,0.00043253825,0.00017339704,0.0011712258,0.0027436984,0.005080384,0.000073069496,0.0013164632],"category_scores_gemma":[0.005893897,0.00017606637,0.0000264463,0.00013068074,0.0022764537,0.0011883462,0.0033348922,0.000081870094,0.00032611433],"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":[0.00003957024,0.000028810227,0.0007509161,0.00007976012,0.0000050624876,0.000005742706,0.00007747504,0.000015374711,0.99481845,0.0007272279,0.0018254576,0.0016261658],"study_design_scores_gemma":[0.00025145343,0.000024970153,0.012181394,0.00011194911,0.000043379125,0.00001803394,0.000052255127,0.0022557366,0.97960734,0.0010750424,0.004071803,0.00030666808],"about_ca_topic_score_codex":0.0008478404,"about_ca_topic_score_gemma":0.000047083828,"teacher_disagreement_score":0.028451348,"about_ca_system_score_codex":0.0000145426775,"about_ca_system_score_gemma":0.0000900756,"threshold_uncertainty_score":0.9995965},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W2765275410","doi":"10.1038/sdata.2017.159","title":"A compendium of geochemical information from the Saanich Inlet water column","year":2017,"lang":"en","type":"article","venue":"Scientific Data","topic":"Marine and coastal ecosystems","field":"Earth and Planetary Sciences","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Genome British Columbia; Fisheries and Oceans Canada; Concordia University; University of British Columbia","funders":"University of Victoria","keywords":"Biogeochemical cycle; Water column; Oceanography; Anoxic waters; Biogeochemistry; Fjord; Environmental science; Compendium; Oxygen minimum zone; Hydrology (agriculture); Geology; Environmental chemistry; Chemistry; Geography","score_opus":0.031415893320049106,"score_gpt":0.22344968093053444,"score_spread":0.19203378761048534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2765275410","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":[0.94740033,0.000048416674,0.00009720814,0.0010194464,0.0024322907,0.00022827389,0.022183595,0.000018439043,0.02657201],"genre_scores_gemma":[0.97633886,0.0000017910938,0.000085288186,0.000059229787,0.00006879449,3.2880334e-7,0.023053452,6.772104e-7,0.0003915665],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991504,0.000026064357,0.00019439163,0.00018694707,0.0002826525,0.00015952182],"domain_scores_gemma":[0.9978339,0.00004527095,0.00011067687,0.0019230302,0.000041475432,0.00004564129],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00079332583,0.00005543989,0.000089838155,0.000017903549,0.00050793565,0.0007927815,0.0021958968,0.000027032642,0.0029446583],"category_scores_gemma":[0.000099666766,0.000030457642,0.000017745086,0.000038104703,0.00021193476,0.0011632332,0.00049087417,0.00006844339,0.0010894245],"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":[0.00004868603,0.000019461751,0.37281072,0.00004040818,0.000036128953,0.0000029097412,0.0009103999,0.000014134672,0.00069572363,0.000067176996,0.51251763,0.11283661],"study_design_scores_gemma":[0.0001946742,0.0000134800275,0.14258802,0.000017066355,0.000012856616,0.0000027677781,0.00023083997,0.018075796,0.0015470631,0.00057809916,0.83664536,0.00009398907],"about_ca_topic_score_codex":0.017224073,"about_ca_topic_score_gemma":0.030287521,"teacher_disagreement_score":0.3241277,"about_ca_system_score_codex":9.597845e-7,"about_ca_system_score_gemma":0.00003516466,"threshold_uncertainty_score":0.9996883},"labels":[],"label_agreement":null},{"id":"W2765768951","doi":"10.1038/sdata.2017.157","title":"Small non-coding RNA transcriptome of the NCI-60 cell line panel","year":2017,"lang":"en","type":"article","venue":"Scientific Data","topic":"MicroRNA in disease regulation","field":"Biochemistry, Genetics and Molecular Biology","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Occupational Cancer Research Centre; BC Cancer Agency","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; Canadian Institutes of Health Research; National Institutes of Health; University of British Columbia","keywords":"Small nucleolar RNA; Biology; microRNA; Transcriptome; Computational biology; Gene; RNA; Genetics; Untranslated region; Non-coding RNA; Gene expression","score_opus":0.07912659260418488,"score_gpt":0.2810783434949748,"score_spread":0.20195175089078993,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2765768951","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":[0.99286586,0.00025614275,0.0018065738,0.00018230999,0.0013067372,0.00020081078,0.001892676,0.0000048412326,0.0014840502],"genre_scores_gemma":[0.9945353,0.00001141556,0.00040184407,0.000021556036,0.000111739326,0.000002087577,0.0013013704,0.000010059763,0.0036045774],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990515,0.000023643122,0.00015995983,0.00045443745,0.00014992076,0.000160547],"domain_scores_gemma":[0.9959944,0.0000033624044,0.00016979569,0.0037090413,0.00007319762,0.000050216495],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004979585,0.000084568455,0.000079686324,0.000022616465,0.00035494467,0.00014894851,0.0021839505,0.000060663726,0.000026881866],"category_scores_gemma":[0.00011752073,0.00006475136,0.000059288668,0.000052989333,0.00031900682,0.000011896248,0.0007996736,0.00004772306,0.000013034874],"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":[0.0000088868655,0.000036958318,0.00021989805,0.000036819558,0.000009340258,5.6901837e-7,0.000026336764,0.000011521793,0.9880836,0.0000055474147,0.010613344,0.00094720634],"study_design_scores_gemma":[0.00028140677,0.000011717976,0.012556462,0.000027749205,0.000030187184,0.000001296116,0.000017871424,0.0008874432,0.9521299,0.00003448724,0.033926528,0.00009494139],"about_ca_topic_score_codex":0.000020943013,"about_ca_topic_score_gemma":0.000055342218,"teacher_disagreement_score":0.035953663,"about_ca_system_score_codex":0.000005577983,"about_ca_system_score_gemma":0.00009858844,"threshold_uncertainty_score":0.405836},"labels":[],"label_agreement":null},{"id":"W2765918031","doi":"10.1038/sdata.2017.158","title":"Monitoring microbial responses to ocean deoxygenation in a model oxygen minimum zone","year":2017,"lang":"en","type":"article","venue":"Scientific Data","topic":"Microbial Community Ecology and Physiology","field":"Environmental Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Genome British Columbia; University of British Columbia; Canadian Institute for Advanced Research","funders":"","keywords":"Biogeochemistry; Anoxic waters; Climate change; Deoxygenation; Ecology; Marine ecosystem; Ecosystem; Global change; Environmental science; Oceanography; Environmental resource management; Biology; Geology","score_opus":0.07998527387381889,"score_gpt":0.3227257224829786,"score_spread":0.24274044860915972,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2765918031","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":[0.9966086,0.0000074319755,0.00022481084,0.0007360403,0.0008687231,0.00018825069,0.000482397,0.000016804706,0.0008669146],"genre_scores_gemma":[0.9919334,0.0000032097794,0.0028017599,0.00008799336,0.000038464026,0.0000026311845,0.00029034313,0.000007595908,0.004834589],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9986846,0.00012763635,0.00018043743,0.0005675608,0.00012165016,0.0003181103],"domain_scores_gemma":[0.99705464,0.000049452796,0.00008577361,0.0027169366,0.0000091725515,0.00008402761],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0014556625,0.0001010261,0.000120978686,0.00008491948,0.0010839372,0.00021390138,0.0031220978,0.00007550571,0.00045899444],"category_scores_gemma":[0.0003403064,0.00010534353,0.00001798668,0.00012352537,0.00041326007,0.0006078447,0.0040564984,0.00016538177,0.0009810505],"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":[0.00014047841,0.00013531884,0.014442702,0.0000049937116,0.000005145364,0.0000067648966,0.0011599882,0.0014554762,0.8415392,0.000015491798,0.13848123,0.00261319],"study_design_scores_gemma":[0.001211893,0.00010372593,0.84459037,0.00008179531,0.000022841587,0.000012754144,0.00028577473,0.031366482,0.023185717,0.0020885698,0.0962727,0.0007773797],"about_ca_topic_score_codex":0.00046777414,"about_ca_topic_score_gemma":0.004830715,"teacher_disagreement_score":0.8301477,"about_ca_system_score_codex":0.00008476364,"about_ca_system_score_gemma":0.00003872357,"threshold_uncertainty_score":0.9997968},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"bench_or_experimental","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W2766255725","doi":"10.1038/sdata.2017.160","title":"A compendium of multi-omic sequence information from the Saanich Inlet water column","year":2017,"lang":"en","type":"article","venue":"Scientific Data","topic":"Microbial Community Ecology and Physiology","field":"Environmental Science","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Genome British Columbia; Concordia University; University of British Columbia","funders":"Pacific Northwest National Laboratory; Biological and Environmental Research; Natural Sciences and Engineering Research Council of Canada; Office of Science; Consejo Nacional de Ciencia y Tecnología; Genome British Columbia; Joint Genome Institute; Battelle; Canadian Institute for Advanced Research; Tula Foundation; U.S. Department of Energy","keywords":"Biogeochemical cycle; Water column; Anoxic waters; Oceanography; Fjord; Compendium; Climate change; Microbial population biology; Environmental science; Biogeochemistry; Ecology; Inlet; Metagenomics; Biology; Geology; Geography","score_opus":0.08973939690447069,"score_gpt":0.2984716612417852,"score_spread":0.2087322643373145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2766255725","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":[0.99294776,0.000005597963,0.00016708144,0.000946216,0.00096737366,0.00020053942,0.0036770348,0.000010838723,0.001077583],"genre_scores_gemma":[0.9933752,0.0000026325574,0.00047088016,0.0002817033,0.000011470603,0.0000022014249,0.0055487216,0.0000021810351,0.0003050353],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99922043,0.00012080419,0.00017499464,0.00020100905,0.00010536857,0.00017741609],"domain_scores_gemma":[0.99663424,0.000064445885,0.0001412096,0.003120284,0.000011355979,0.000028431696],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0009969553,0.000064576685,0.00009558369,0.000011018656,0.0012562998,0.00017958073,0.00407791,0.000049656184,0.004956202],"category_scores_gemma":[0.00012804447,0.00004146873,0.000016751565,0.000037007558,0.0015305328,0.0010645217,0.0042938413,0.00014812518,0.0028943813],"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":[0.00004288807,0.00010026116,0.02956682,0.000008943207,0.000025838022,0.0000011716128,0.004528995,0.000081433944,0.42248175,0.00007645179,0.53768224,0.0054032016],"study_design_scores_gemma":[0.0006078522,0.000030865755,0.26629162,0.00001644152,0.000025014675,0.0000036233635,0.0002824108,0.0066345115,0.019709071,0.0015031296,0.70469254,0.00020291141],"about_ca_topic_score_codex":0.0042790137,"about_ca_topic_score_gemma":0.016613482,"teacher_disagreement_score":0.4027727,"about_ca_system_score_codex":0.000022410792,"about_ca_system_score_gemma":0.000016733135,"threshold_uncertainty_score":0.997882},"labels":[],"label_agreement":null},{"id":"W2766580836","doi":"10.1038/sdata.2017.140","title":"Targeted metabolomics and medication classification data from participants in the ADNI1 cohort","year":2017,"lang":"en","type":"article","venue":"Scientific Data","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":75,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institutes of Health; Genentech; National Institute of Neurological Disorders and Stroke; IXICO; H. Lundbeck A/S; Servier; Eisai; Northern California Institute for Research and Education; University of California, San Diego; Pfizer; Biogen; BioClinica; F. Hoffmann-La Roche; University of Southern California; Eli Lilly and Company; U.S. Department of Defense; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; Novartis Pharmaceuticals Corporation; Bristol-Myers Squibb; National Institute on Aging; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Cohort; Metabolomics; Cohort study; Medicine; Computational biology; Data science; Bioinformatics; Computer science; Internal medicine; Biology","score_opus":0.1522656983292253,"score_gpt":0.3638493541484873,"score_spread":0.211583655819262,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2766580836","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":[0.9872871,0.002921286,0.000528904,0.0019373925,0.0008856672,0.00028018205,0.0056719203,0.00000566245,0.00048189735],"genre_scores_gemma":[0.97281784,0.0010744396,0.0010208362,0.000089880545,0.00014104345,0.000013892958,0.024667004,0.0000064383385,0.00016860942],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9984066,0.000083061175,0.000204304,0.000884243,0.0002118538,0.00020994133],"domain_scores_gemma":[0.9937274,0.00002471847,0.0001754175,0.0059876884,0.000037768175,0.00004702223],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002520315,0.00009561069,0.000131096,0.000037001482,0.00048467028,0.00037414706,0.0030177184,0.000059574795,0.000017936465],"category_scores_gemma":[0.0014162476,0.000069000904,0.000010620126,0.00007021773,0.00041755475,0.000040252184,0.0020340346,0.00007813773,0.000013147758],"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":[0.000044753742,0.00020049562,0.23330177,0.0000130989,0.00023860026,0.0000024895153,0.00021423357,7.023677e-7,0.52279705,0.0012410876,0.22728346,0.014662219],"study_design_scores_gemma":[0.00029598916,0.000010016859,0.74408674,0.000004428341,0.000080569866,7.5158994e-7,0.00023547582,0.0035518943,0.0029665807,0.00044837603,0.2482034,0.00011576852],"about_ca_topic_score_codex":0.00019413223,"about_ca_topic_score_gemma":0.0015758143,"teacher_disagreement_score":0.51983047,"about_ca_system_score_codex":0.0000039752017,"about_ca_system_score_gemma":0.00006197226,"threshold_uncertainty_score":0.5607722},"labels":[],"label_agreement":null},{"id":"W2772764433","doi":"10.1038/sdata.2017.187","title":"Temporally inter-comparable maps of terrestrial wilderness and the Last of the Wild","year":2017,"lang":"en","type":"article","venue":"Scientific Data","topic":"Species Distribution and Climate Change","field":"Environmental Science","cited_by":144,"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 Northern British Columbia","funders":"Australian Research Council; Wildlife Conservation Society","keywords":"Wilderness; Wilderness area; Natural (archaeology); Geography; Biodiversity; Habitat; Disturbance (geology); Ecology; Underpinning; Environmental resource management; Environmental science; Archaeology; Biology; Geology","score_opus":0.06972847364218235,"score_gpt":0.28492402393358307,"score_spread":0.21519555029140072,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2772764433","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":[0.9572704,0.00004946272,0.000035762947,0.0019223825,0.0020441706,0.00034912542,0.004354565,0.000009072449,0.03396505],"genre_scores_gemma":[0.99818385,0.0000053853223,0.000014315112,0.000022750783,0.000015394804,0.0000022920694,0.00021327671,0.0000026788293,0.0015400491],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99908906,0.000045756056,0.00017436846,0.00027257187,0.00029266314,0.00012555094],"domain_scores_gemma":[0.9974816,0.000029798046,0.00024639204,0.00220402,0.000007108336,0.00003112561],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0010137114,0.00006251279,0.00011593719,0.00000886754,0.0004907324,0.00021635518,0.0024887188,0.000020748379,0.0017442242],"category_scores_gemma":[0.00019484066,0.000032782667,0.00003135703,0.00009047083,0.0036166671,0.00030253833,0.0027411128,0.00005792583,0.00005998782],"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":[0.000103711194,0.00013226701,0.106854886,0.000020227923,0.00001732964,5.508024e-7,0.0005066562,0.0000033587696,0.0047245063,0.001828035,0.88134915,0.0044593285],"study_design_scores_gemma":[0.0022396436,0.000018865738,0.33934814,0.000070427464,0.000039611747,0.0000055994046,0.0016119602,0.0006676861,0.0036541407,0.0010332398,0.65116143,0.00014923514],"about_ca_topic_score_codex":0.0008264385,"about_ca_topic_score_gemma":0.0020302862,"teacher_disagreement_score":0.23249327,"about_ca_system_score_codex":0.00002081352,"about_ca_system_score_gemma":0.000012837521,"threshold_uncertainty_score":0.99916834},"labels":[],"label_agreement":null},{"id":"W2780601052","doi":"10.1038/sdata.2017.181","title":"An open resource for transdiagnostic research in pediatric mental health and learning disorders","year":2017,"lang":"en","type":"article","venue":"Scientific Data","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":723,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Baycrest Hospital; University of Toronto","funders":"Stavros Niarchos Foundation; National Institute of Environmental Health Sciences; Child Mind Institute; Strong; Hearst Foundations","keywords":"Biobank; Neuroimaging; Open science; Mental health; Psychology; Psychopathology; Data sharing; Data science; Computer science; Medicine; Psychiatry; Bioinformatics; Alternative medicine","score_opus":0.30330965426452183,"score_gpt":0.46182131394146975,"score_spread":0.1585116596769479,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2780601052","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":[0.8760987,0.0006835111,0.00020232196,0.10827079,0.0022822882,0.0043688603,0.0041107778,0.000087945096,0.003894792],"genre_scores_gemma":[0.9974062,0.00015450228,0.0002839955,0.0003131155,0.00008109813,0.000061786835,0.00031393784,0.0000163252,0.001369052],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99722046,0.0004676699,0.0001449087,0.0013250378,0.00041885747,0.00042304167],"domain_scores_gemma":[0.9943545,0.0038806414,0.000077166995,0.0015316228,0.000024414581,0.00013168385],"candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.007430441,0.0000817558,0.00012798148,0.00021997748,0.005654069,0.0017042872,0.0028378302,0.00002189329,0.000006730496],"category_scores_gemma":[0.024380751,0.000080239704,0.000009035674,0.00030372327,0.00065777666,0.0013510709,0.002066996,0.00026483167,0.000012382978],"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":[0.00059023494,0.0012152038,0.09755458,0.00043555893,0.000009470301,0.000011299888,0.0131734,0.00013776621,0.006304896,0.0034365521,0.7095942,0.16753684],"study_design_scores_gemma":[0.0023013358,0.00095595117,0.058149766,0.0000790593,0.0000059041045,0.000005695504,0.0034392867,0.0125800455,0.00028177974,0.004225035,0.91760874,0.00036739925],"about_ca_topic_score_codex":0.00029394985,"about_ca_topic_score_gemma":0.002958644,"teacher_disagreement_score":0.20801455,"about_ca_system_score_codex":0.0000400324,"about_ca_system_score_gemma":0.00019067219,"threshold_uncertainty_score":0.999332},"labels":[],"label_agreement":null},{"id":"W2780974917","doi":"10.1038/sdata.2017.179","title":"Sequence data and association statistics from 12,940 type 2 diabetes cases and controls","year":2017,"lang":"en","type":"article","venue":"Scientific Data","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":43,"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 Health Centre; McGill University; McGill University and Génome Québec Innovation Centre","funders":"National Institute of Diabetes and Digestive and Kidney Diseases; Wellcome Trust; Steno Diabetes Center Copenhagen; National Human Genome Research Institute; National Heart, Lung, and Blood Institute; National Institute on Aging; Novo Nordisk Fonden; National Institute of General Medical Sciences; National Institute for Health and Care Research; Medical Research Council; National Institutes of Health; Lundbeckfonden; British Heart Foundation","keywords":"Exome; Imputation (statistics); Minor allele frequency; Biology; Genetics; Genetic association; Allele frequency; Indel; Single-nucleotide polymorphism; 1000 Genomes Project; Genome-wide association study; Genotype; Genetic variation; Exome sequencing; Whole genome sequencing; Gene; Computational biology; Genome; Missing data; Phenotype; Statistics","score_opus":0.09003116363464679,"score_gpt":0.3437257837775208,"score_spread":0.25369462014287397,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2780974917","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":[0.94719195,0.001145053,0.00048029426,0.0005449237,0.0006923575,0.00009893702,0.04976736,0.000005029218,0.00007406964],"genre_scores_gemma":[0.9524722,0.00038203693,0.007788453,0.00011872988,0.00014277334,0.0000020199313,0.037814368,0.0000070975548,0.0012722971],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9988305,0.000072628325,0.00015169656,0.00065124815,0.00010117433,0.00019273687],"domain_scores_gemma":[0.99718475,0.00016624326,0.00023293564,0.002266079,0.00008646922,0.00006354148],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0012159926,0.000079854944,0.00013126982,0.000013830477,0.000477125,0.0004010225,0.00085046014,0.0000942825,0.00001480251],"category_scores_gemma":[0.008759763,0.00007469685,0.000005510395,0.000016967866,0.0002296766,0.000023403682,0.0017066222,0.000050182512,0.000008020332],"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":[0.000007941932,0.000017970486,0.69902486,0.0000067212272,0.00009460241,0.0000023729474,0.00001778445,9.244365e-7,0.048938494,0.000049821923,0.2421821,0.009656423],"study_design_scores_gemma":[0.0006065934,0.00008905323,0.6403466,0.000014659533,0.00013854026,0.000003177167,0.000059666247,0.0123703275,0.00070358155,0.0010489912,0.344343,0.000275834],"about_ca_topic_score_codex":0.00024004272,"about_ca_topic_score_gemma":0.00092616194,"teacher_disagreement_score":0.1021609,"about_ca_system_score_codex":0.0000085816755,"about_ca_system_score_gemma":0.00007100175,"threshold_uncertainty_score":0.99958986},"labels":[],"label_agreement":null},{"id":"W2789589646","doi":"10.1038/sdata.2018.18","title":"A database of chlorophyll a in Australian waters","year":2018,"lang":"en","type":"article","venue":"Scientific Data","topic":"Marine and coastal ecosystems","field":"Earth and Planetary Sciences","cited_by":27,"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":"Department of Science, Information Technology and Innovation, Queensland Government; Australian Antarctic Division; Directorate for Biological Sciences; School of Civil, Environmental and Mining Engineering, University of Adelaide; South Australian Research and Development Institute; Griffith University; Flinders University; Antarctic Climate and Ecosystems Cooperative Research Centre; University of New South Wales; University of Technology Sydney; Macquarie University; University of Tasmania; Universität Bremen; Australian Government; Commonwealth Scientific and Industrial Research Organisation; Great Barrier Reef Marine Park Authority; University of Queensland; NSW Office of Environment and Heritage; Université de Genève; Australian Institute of Marine Science","keywords":"Phytoplankton; Environmental science; Biomass (ecology); Zooplankton; Trophic level; Chlorophyll a; Abundance (ecology); Oceanography; Chlorophyll; Ecosystem; Food web; Fishery; Ecology; Biology; Nutrient; Botany","score_opus":0.04969863586566379,"score_gpt":0.2530766676749467,"score_spread":0.2033780318092829,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2789589646","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":[0.9704579,0.00002854789,0.000022525295,0.00015393806,0.0017401325,0.00016189495,0.01069732,0.000017280097,0.016720435],"genre_scores_gemma":[0.9900155,0.0000018624107,0.00032818053,0.00001853034,0.00007111784,2.2957e-7,0.0058628237,0.0000012892141,0.0037004864],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99888265,0.00003194033,0.00020533593,0.00041892982,0.00023006352,0.00023106078],"domain_scores_gemma":[0.9986487,0.00001646398,0.00005084815,0.0011773212,0.000030484352,0.00007617551],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008841486,0.000064740605,0.000102005135,0.00012905391,0.00007054387,0.00009671641,0.0009878852,0.000019761375,0.003188955],"category_scores_gemma":[0.000043814445,0.000050428705,0.00001253744,0.0004778725,0.00025386768,0.00047208605,0.0001780715,0.000049858623,0.0007569701],"study_design_candidate":"not_applicable","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":[0.00013974418,0.00012368223,0.5957501,0.00026143165,0.000023820645,0.00007542506,0.0009569103,0.000034744833,0.0026598158,0.00012773102,0.2469301,0.15291652],"study_design_scores_gemma":[0.0006550851,0.0002133655,0.21713926,0.00015797118,0.000016381371,0.000019878353,0.0007490843,0.027582437,0.0031895833,0.00039949705,0.7494901,0.00038738194],"about_ca_topic_score_codex":0.011276492,"about_ca_topic_score_gemma":0.049201272,"teacher_disagreement_score":0.50255996,"about_ca_system_score_codex":0.0000012782872,"about_ca_system_score_gemma":0.000055417855,"threshold_uncertainty_score":0.99772227},"labels":[],"label_agreement":null},{"id":"W2791403874","doi":"10.1038/sdata.2018.36","title":"Global quantitative analysis of the human brain proteome in Alzheimer’s and Parkinson’s Disease","year":2018,"lang":"en","type":"article","venue":"Scientific Data","topic":"Alzheimer's disease research and treatments","field":"Medicine","cited_by":268,"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; Emory University; Alzheimer's Disease Research Center, Emory University; Weston Brain Institute; National Institute of Neurological Disorders and Stroke; Alzheimer's Association; Michael J. Fox Foundation for Parkinson's Research","keywords":"Isobaric labeling; Neuroscience; Tandem mass tag; Neuropathology; Human brain; Proteome; Parkinson's disease; Posterior cingulate; Disease; Alzheimer's disease; Alzheimer's Disease Neuroimaging Initiative; Proteomics; Cognitive impairment; Computational biology; Biology; Bioinformatics; Medicine; Quantitative proteomics; Cortex (anatomy); Gene; Cognition; Pathology; Genetics","score_opus":0.12041218200452913,"score_gpt":0.41467726213894535,"score_spread":0.2942650801344162,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2791403874","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":[0.9861192,0.0030941525,0.000012436485,0.0012524157,0.000093950475,0.000744843,0.008287767,0.000012325497,0.00038287992],"genre_scores_gemma":[0.9980018,0.0000043513123,0.00019124284,0.000050741277,0.000017199509,0.000016002883,0.00163036,0.0000048740762,0.000083422354],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99830663,0.00011772752,0.0001989961,0.0005972374,0.0005280924,0.00025134295],"domain_scores_gemma":[0.9979023,0.00003726055,0.00007627226,0.0015948069,0.000118451964,0.0002709482],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006636253,0.00009958267,0.00021466719,0.00021289062,0.00020978182,0.00006958163,0.0004592478,0.000022038823,0.0001375575],"category_scores_gemma":[0.00031814192,0.00006394649,0.000063321466,0.0020141327,0.0012065037,0.00018095797,0.0005833392,0.00005225869,0.0000211217],"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":[0.00027139272,0.0006989576,0.9674344,0.000031767126,0.012276832,0.000049859325,0.00023909185,0.0000011533433,0.0002660778,0.0007929854,0.016940437,0.0009970496],"study_design_scores_gemma":[0.00067323644,0.00006244804,0.9911563,0.00005306654,0.0031833053,8.0380335e-7,0.00009306971,0.002071262,0.00006548896,0.00050367275,0.0020721767,0.00006517221],"about_ca_topic_score_codex":0.00030353264,"about_ca_topic_score_gemma":0.001951527,"teacher_disagreement_score":0.0237219,"about_ca_system_score_codex":0.000033847387,"about_ca_system_score_gemma":0.00027948967,"threshold_uncertainty_score":0.4445413},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"bench_or_experimental","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W2791916662","doi":"10.1038/sdata.2018.8","title":"Dynamic contrast-enhanced magnetic resonance imaging for head and neck cancers","year":2018,"lang":"en","type":"article","venue":"Scientific Data","topic":"MRI in cancer diagnosis","field":"Medicine","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto; University Health Network","funders":"University of Texas Health Science Center at Houston; Division of Mathematical Sciences; National Cancer Institute; National Institutes of Health; National Science Foundation; Andrew Sabin Family Foundation; National Institute of Dental and Craniofacial Research; University of Texas MD Anderson Cancer Center; Cancer Prevention and Research Institute of Texas; Elekta; University of Texas at Austin","keywords":"DICOM; Generalizability theory; Flip angle; Magnetic resonance imaging; Computer science; Head and neck; Contrast (vision); Software; Dynamic contrast; Scanner; Data set; Nuclear medicine; Cancer imaging; Medical physics; Radiology; Medicine; Artificial intelligence; Cancer; Mathematics","score_opus":0.032866982660721536,"score_gpt":0.3416893605712519,"score_spread":0.30882237791053035,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2791916662","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":[0.8283706,0.062906615,0.015462216,0.028957605,0.019652406,0.006980192,0.027107237,0.0005539193,0.010009257],"genre_scores_gemma":[0.9605705,0.00052254426,0.023722984,0.001507796,0.0004358122,0.00018332034,0.0018593066,0.00006103478,0.011136659],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99804634,0.00001559017,0.00022381966,0.0010049962,0.0002798437,0.0004294247],"domain_scores_gemma":[0.99779296,0.00009265403,0.0000648071,0.0016837427,0.00020293727,0.00016290191],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000582846,0.00013781198,0.00021903019,0.00010183597,0.0002749068,0.00016752437,0.0004842815,0.000032944936,0.00031131954],"category_scores_gemma":[0.0002250913,0.00013020173,0.000024869683,0.00033222255,0.00089908065,0.00027567334,0.00027323366,0.00008373154,0.000055042427],"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":[0.00021298767,0.000051465566,0.004638567,0.0001415128,0.000011594377,0.0000065599884,0.000349707,5.1673806e-7,0.015011024,0.00005626608,0.5874048,0.39211503],"study_design_scores_gemma":[0.0033050824,0.00027181747,0.029959062,0.0005825387,0.00011557657,0.00002291666,0.00015968006,0.035945088,0.0061403476,0.00033908972,0.9228979,0.0002609225],"about_ca_topic_score_codex":0.00016443538,"about_ca_topic_score_gemma":0.001537596,"teacher_disagreement_score":0.3918541,"about_ca_system_score_codex":0.00015593413,"about_ca_system_score_gemma":0.0003219876,"threshold_uncertainty_score":0.53094727},"labels":[],"label_agreement":null},{"id":"W2792092426","doi":"10.1038/sdata.2018.40","title":"A suite of global, cross-scale topographic variables for environmental and biodiversity modeling","year":2018,"lang":"en","type":"article","venue":"Scientific Data","topic":"Species Distribution and Climate Change","field":"Environmental Science","cited_by":858,"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":"McGill University; Deutsche Forschungsgemeinschaft; Yale University; National Aeronautics and Space Administration; National Science Foundation","keywords":"Digital elevation model; Landform; Scale (ratio); Terrain; Elevation (ballistics); Physical geography; Topographic Wetness Index; Variable (mathematics); Spatial analysis; Geography; Spatial variability; Cartography; Environmental science; Geology; Remote sensing; Statistics; Mathematics; Geometry","score_opus":0.058784412206377,"score_gpt":0.28447914166515603,"score_spread":0.22569472945877903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2792092426","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":[0.9651699,0.000043905082,0.0010603551,0.000060698538,0.00030685827,0.00015394864,0.031275313,0.000015518839,0.0019135154],"genre_scores_gemma":[0.9968251,0.000015031284,0.0006109481,0.000042807354,0.000013959394,0.0000023233135,0.0022176357,0.0000021019175,0.00027006923],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9989394,0.00001049033,0.00012395934,0.00050318526,0.00021612574,0.00020685373],"domain_scores_gemma":[0.9992213,0.000010008187,0.000048322257,0.00063236913,0.000008364755,0.00007958161],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00048236112,0.00007365537,0.000081011654,0.000014621984,0.00040776122,0.00012748613,0.0005585848,0.000036825062,0.009027781],"category_scores_gemma":[0.000020809855,0.000070387425,0.00002499188,0.0001889683,0.0014568449,0.00035676738,0.0011520607,0.000020914225,0.00024582446],"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":[0.00007240598,0.0002666385,0.8704814,0.00003092749,0.000020050384,7.081286e-7,0.00024003476,0.000017770635,0.031321306,0.00038050918,0.09437155,0.0027967142],"study_design_scores_gemma":[0.0021860825,0.0002413612,0.588865,0.00002320981,0.00012760724,0.000015415162,0.0037283048,0.053949144,0.0047209156,0.0018149324,0.3435696,0.000758454],"about_ca_topic_score_codex":0.00013571087,"about_ca_topic_score_gemma":0.0004618835,"teacher_disagreement_score":0.2816164,"about_ca_system_score_codex":0.00008214095,"about_ca_system_score_gemma":0.000005589136,"threshold_uncertainty_score":0.9918781},"labels":[],"label_agreement":null},{"id":"W2792542239","doi":"10.1038/sdata.2018.22","title":"GlobTherm, a global database on thermal tolerances for aquatic and terrestrial organisms","year":2018,"lang":"en","type":"article","venue":"Scientific Data","topic":"Physiological and biochemical adaptations","field":"Environmental Science","cited_by":253,"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; University of British Columbia; Université du Québec à Rimouski","funders":"Deutsches Zentrum für integrative Biodiversitätsforschung Halle-Jena-Leipzig; Universidad de Alcalá; Deutsche Forschungsgemeinschaft","keywords":"Database; Environmental science; Computer science; Ecology; Biology","score_opus":0.062428838694399545,"score_gpt":0.29662381250183206,"score_spread":0.2341949738074325,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2792542239","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":[0.99270254,0.000011464032,0.00058285793,0.0005084319,0.0005467128,0.00023773753,0.0036404761,0.000028662236,0.0017411137],"genre_scores_gemma":[0.99536324,7.2494464e-7,0.0028073627,0.00026017468,0.00016641973,0.0000067817837,0.0010612275,0.000002690053,0.00033139638],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989036,0.00002028177,0.00010721574,0.0005813136,0.0001915113,0.00019611354],"domain_scores_gemma":[0.9992255,0.00004844909,0.00003546867,0.000600187,0.0000035114208,0.00008687399],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002526032,0.000081317434,0.00007368578,0.0000055238283,0.00028944237,0.00011355492,0.00067276316,0.000025973346,0.00062413816],"category_scores_gemma":[0.0001627548,0.00005288933,0.0000140624325,0.00019332269,0.0008750084,0.0002217309,0.00062201504,0.000030069623,0.00048762085],"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":[0.00013019363,0.00020102247,0.00043900695,0.000003912695,0.0000075507496,9.86166e-7,0.00005030301,0.0000038882213,0.85868186,0.00025316235,0.10241173,0.037816383],"study_design_scores_gemma":[0.00481917,0.0016473446,0.0747972,0.00013824698,0.00015369273,0.000013265492,0.00032604532,0.09078153,0.15190876,0.062142465,0.6115918,0.0016804825],"about_ca_topic_score_codex":0.00006542848,"about_ca_topic_score_gemma":0.00016507381,"teacher_disagreement_score":0.7067731,"about_ca_system_score_codex":0.000019000234,"about_ca_system_score_gemma":0.000011489796,"threshold_uncertainty_score":0.6833875},"labels":[],"label_agreement":null},{"id":"W2793992791","doi":"10.1038/sdata.2018.39","title":"Simplifying research access to genomics and health data with Library Cards","year":2018,"lang":"en","type":"article","venue":"Scientific Data","topic":"Ethics in Clinical Research","field":"Medicine","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Data science; Process (computing); Data access; Authentication (law); Protocol (science); Genomics; World Wide Web; Database; Biology; Genome; Medicine; Computer security","score_opus":0.933510998259124,"score_gpt":0.7230294947196095,"score_spread":0.21048150353951445,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2793992791","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":[0.37019533,0.0029547224,0.004492181,0.5299573,0.003992917,0.0072851786,0.03656359,0.0004950446,0.04406376],"genre_scores_gemma":[0.77970314,0.001747862,0.113563314,0.017258879,0.004138965,0.000045140823,0.033813145,0.00027091845,0.049458615],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9947011,0.00019322037,0.00036621906,0.0019601695,0.0020102386,0.00076905166],"domain_scores_gemma":[0.9840975,0.0021190767,0.000068217974,0.012014871,0.0006272923,0.001073044],"candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.031193165,0.000108108085,0.00025891798,0.00036187412,0.000871663,0.001609054,0.0057882974,0.00011225624,0.00023415421],"category_scores_gemma":[0.008252871,0.00008192217,0.000008931773,0.00159211,0.0022513948,0.0013479578,0.026142785,0.0013629767,0.00026343184],"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":[0.00018392783,0.00008941391,0.011965708,0.00035136892,0.00003211321,0.000026721515,0.0003807536,2.3175191e-7,0.0002706525,0.00090733275,0.9557606,0.030031165],"study_design_scores_gemma":[0.0006993183,0.00072592444,0.021612972,0.0006726908,0.000017042945,0.000028852117,0.0005300752,0.0018363423,0.0005610944,0.0049416027,0.9681893,0.00018480724],"about_ca_topic_score_codex":0.0003000945,"about_ca_topic_score_gemma":0.0020436025,"teacher_disagreement_score":0.5126984,"about_ca_system_score_codex":0.00006879942,"about_ca_system_score_gemma":0.004710132,"threshold_uncertainty_score":0.9995909},"labels":[],"label_agreement":null},{"id":"W2794106486","doi":"10.1038/sdata.2018.20","title":"A new, short-recorded photoplethysmogram dataset for blood pressure monitoring in China","year":2018,"lang":"en","type":"article","venue":"Scientific Data","topic":"Non-Invasive Vital Sign Monitoring","field":"Engineering","cited_by":207,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"B.C. Women's Hospital & Health Centre; BC Children's Hospital; Children's & Women's Health Centre of British Columbia; University of British Columbia","funders":"Division of Graduate Education; Guilin University of Electronic Technology; National Natural Science Foundation of China","keywords":"Photoplethysmogram; Diabetes mellitus; Medicine; Blood pressure; Disease; Data mining; Computer science; Intensive care medicine; Internal medicine","score_opus":0.03882169248641047,"score_gpt":0.2928124533598392,"score_spread":0.2539907608734287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2794106486","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":[0.64176977,0.0046722703,0.05014115,0.00012902328,0.072450094,0.005282979,0.22185367,0.0017068434,0.0019942017],"genre_scores_gemma":[0.9455468,0.000015718408,0.033221725,0.000004734222,0.002340019,0.00008161691,0.018081807,0.000095364034,0.0006121938],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979375,0.000019228753,0.00030397513,0.0008277175,0.00031109652,0.000600509],"domain_scores_gemma":[0.99737823,0.000068936235,0.00002923493,0.0023005428,0.000044319106,0.00017871577],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00072291703,0.00022437128,0.00020717745,0.00023017719,0.00018624119,0.00044827454,0.0017838583,0.00008535301,0.000072775794],"category_scores_gemma":[0.00020260192,0.00024003646,0.000031685853,0.000691576,0.0001083641,0.0008575166,0.000618065,0.00018693923,0.00006186565],"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":[0.00003064818,0.00011702526,0.01600456,0.00025550878,0.00019555245,0.00002130932,0.0005060655,0.00032292222,0.5182766,0.000018799028,0.42216787,0.04208318],"study_design_scores_gemma":[0.001161498,0.00010156474,0.0049189534,0.00025810944,0.00022534294,0.000010822333,0.0001111626,0.0067308354,0.47583148,0.0004374632,0.5094115,0.00080126943],"about_ca_topic_score_codex":0.00023394806,"about_ca_topic_score_gemma":0.0003992779,"teacher_disagreement_score":0.30377704,"about_ca_system_score_codex":0.000024439873,"about_ca_system_score_gemma":0.0000611618,"threshold_uncertainty_score":0.9788403},"labels":[],"label_agreement":null},{"id":"W2802068140","doi":"10.1038/sdata.2018.76","title":"An optimal filter for short photoplethysmogram signals","year":2018,"lang":"en","type":"article","venue":"Scientific Data","topic":"Non-Invasive Vital Sign Monitoring","field":"Engineering","cited_by":230,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"B.C. Women's Hospital & Health Centre; BC Children's Hospital; Children's & Women's Health Centre of British Columbia; University of British Columbia","funders":"Division of Graduate Education; Guilin University of Electronic Technology; National Natural Science Foundation of China","keywords":"Photoplethysmogram; Chebyshev filter; Filter (signal processing); Computer science; SIGNAL (programming language); Signal processing; Wearable computer; Noise (video); Interference (communication); Artificial intelligence; Computer vision; Telecommunications; Channel (broadcasting); Digital signal processing; Computer hardware; Embedded system","score_opus":0.06778257964544786,"score_gpt":0.31755129122592674,"score_spread":0.24976871158047886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2802068140","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":[0.61975247,0.0002606938,0.34486425,0.000035251986,0.017158203,0.0013924392,0.0111547625,0.0012452155,0.004136751],"genre_scores_gemma":[0.96473324,0.000001434177,0.03147609,0.000016682721,0.0010626729,0.00004441003,0.0023215946,0.000051082625,0.00029281],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9985033,0.000014123942,0.00018675005,0.0006112996,0.00024817637,0.00043634285],"domain_scores_gemma":[0.9977849,0.00005138927,0.000014532895,0.001895924,0.000106357285,0.0001468929],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007467471,0.00014865065,0.00012731885,0.00011514079,0.00022859492,0.0004921216,0.0014117606,0.00005579028,0.00025029958],"category_scores_gemma":[0.00007038857,0.00014869931,0.00003489778,0.00031527676,0.00022054437,0.00087299984,0.00025168585,0.000078522775,0.00019534065],"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":[0.00000912877,0.00003447969,0.00025648507,0.00003352092,0.000025320578,0.0000031214809,0.00014811708,0.00029255968,0.8676183,0.000014304481,0.11062026,0.020944402],"study_design_scores_gemma":[0.00017089878,0.000105621875,0.00017285721,0.00003364006,0.000024505465,0.00000407113,0.000091851674,0.040383868,0.7964695,0.00016574473,0.16201878,0.0003586356],"about_ca_topic_score_codex":0.0000048527245,"about_ca_topic_score_gemma":0.000019786788,"teacher_disagreement_score":0.34498078,"about_ca_system_score_codex":0.000030005964,"about_ca_system_score_gemma":0.00002539893,"threshold_uncertainty_score":0.6063782},"labels":[],"label_agreement":null},{"id":"W2803508903","doi":"10.1038/sdata.2018.97","title":"HormoneBase, a population-level database of steroid hormone levels across vertebrates","year":2018,"lang":"en","type":"article","venue":"Scientific Data","topic":"Animal Behavior and Reproduction","field":"Agricultural and Biological 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":"Simon Fraser University","funders":"","keywords":"Biology; Hormone; Evolutionary biology; Phenotype; Population; Steroid hormone; Database; Bioinformatics; Endocrinology; Genetics; Gene; Demography; Computer science","score_opus":0.16280903919880477,"score_gpt":0.3270080089994612,"score_spread":0.16419896980065643,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2803508903","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":[0.9784747,0.00018734633,0.000033812797,0.00017813584,0.00066925096,0.00015110118,0.020192405,0.000042278458,0.000070989074],"genre_scores_gemma":[0.9880929,0.0000062329796,0.00039056985,0.00001818868,0.0002996939,0.0000026591972,0.009832564,0.0000010659356,0.0013561316],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99828815,0.000039504874,0.00026323192,0.00077858655,0.00035326567,0.00027726154],"domain_scores_gemma":[0.999003,0.000026699361,0.000120025295,0.0005909301,0.00017627998,0.000083073675],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00092139933,0.000111320944,0.0001373155,0.000015071392,0.00054132263,0.00016479072,0.0009061677,0.000052538224,0.0003567886],"category_scores_gemma":[0.00011617513,0.000044581953,0.00003319672,0.0006176813,0.0004353718,0.000731878,0.00071030034,0.000066590546,0.00015534036],"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":[0.000026472935,0.000098020384,0.0058550155,0.000003874757,0.000004837212,8.533463e-7,0.00007353296,7.534678e-8,0.9369997,0.000025011404,0.022324508,0.03458809],"study_design_scores_gemma":[0.00013015229,0.0001844044,0.95240325,0.000017924674,0.00001790658,0.0000070358224,0.0003749149,0.00016571347,0.033751827,0.00009126118,0.0126761,0.00017951024],"about_ca_topic_score_codex":0.0007556836,"about_ca_topic_score_gemma":0.0012351777,"teacher_disagreement_score":0.9465482,"about_ca_system_score_codex":0.000010774701,"about_ca_system_score_gemma":0.00001057483,"threshold_uncertainty_score":0.41634706},"labels":[],"label_agreement":null},{"id":"W2807820258","doi":"10.1038/sdata.2018.107","title":"Warping an atlas derived from serial histology to 5 high-resolution MRIs","year":2018,"lang":"en","type":"article","venue":"Scientific Data","topic":"Advanced Neuroimaging Techniques and Applications","field":"Medicine","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Montreal Neurological Institute and Hospital; Western University; McGill University; Douglas Mental Health University Institute","funders":"","keywords":"Atlas (anatomy); Image warping; Histology; Computer science; High resolution; Artificial intelligence; Computer vision; Medicine; Anatomy; Pathology; Remote sensing; Geology","score_opus":0.1620349504297906,"score_gpt":0.3946804462657199,"score_spread":0.2326454958359293,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2807820258","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":[0.7839587,0.000029680621,0.2058075,0.0049767415,0.0018042388,0.00052049255,0.0021361636,0.0004308882,0.0003355959],"genre_scores_gemma":[0.7363564,0.0000036329955,0.252576,0.0006999499,0.0006648335,0.000024582903,0.008710485,0.00002230805,0.0009418495],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99863464,0.000024820172,0.00016622758,0.0008039621,0.00015460349,0.00021572968],"domain_scores_gemma":[0.99739236,0.000018934212,0.000053216452,0.002283815,0.000101067584,0.00015060126],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002168848,0.00008439528,0.00013689372,0.00008972595,0.00030389984,0.00005919685,0.00058982475,0.000039738705,0.00019708881],"category_scores_gemma":[0.00015077594,0.0000805628,0.000014568854,0.0002905109,0.00031002198,0.00022857219,0.0005130089,0.000083393374,0.0003232016],"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":[0.00008624437,0.000107001346,0.00026808618,0.000005402574,0.000007437238,0.0000069354564,0.00016710752,0.0000021435021,0.7680967,0.0006693399,0.21905887,0.011524719],"study_design_scores_gemma":[0.0005192665,0.00020424974,0.009879001,0.00004750924,0.00006373487,0.000019415787,0.0000442912,0.0054478166,0.06893549,0.0035226564,0.9111119,0.00020468977],"about_ca_topic_score_codex":0.00034708806,"about_ca_topic_score_gemma":0.00020428516,"teacher_disagreement_score":0.69916123,"about_ca_system_score_codex":0.000046038524,"about_ca_system_score_gemma":0.00006259534,"threshold_uncertainty_score":0.41542104},"labels":[],"label_agreement":null},{"id":"W2809461164","doi":"10.1038/sdata.2018.110","title":"MEG-BIDS, the brain imaging data structure extended to magnetoencephalography","year":2018,"lang":"en","type":"article","venue":"Scientific Data","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":178,"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":"Horizon 2020 Framework Programme; National Institutes of Health; Medical Research Council; AXA Research Fund; National Institute of Biomedical Imaging and Bioengineering; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Wellcome Trust; Fondation Brain Canada","keywords":"Magnetoencephalography; Metadata; Computer science; Neuroimaging; Data acquisition; Data sharing; Data science; Psychology; Neuroscience; Electroencephalography; World Wide Web; Medicine","score_opus":0.08310562985708746,"score_gpt":0.32680331047269123,"score_spread":0.24369768061560376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2809461164","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":[0.18739991,0.0012365518,0.012693459,0.54007673,0.064728424,0.004507989,0.1690103,0.0015387466,0.018807916],"genre_scores_gemma":[0.96892464,0.0000040751443,0.0020862783,0.023059973,0.0009544282,0.000012618709,0.0013998862,0.00003510117,0.003522977],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9955911,0.00021903375,0.00022067397,0.0025543717,0.0008789125,0.00053587777],"domain_scores_gemma":[0.9892965,0.0019249761,0.00008616526,0.008440272,0.00012612228,0.00012598214],"candidate_categories":["metaresearch","sts","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0019104067,0.00020504283,0.00015001457,0.00022303971,0.0017852376,0.0009234925,0.0076592313,0.000026514352,0.0004072767],"category_scores_gemma":[0.019795492,0.00014287862,0.000028979704,0.0020281966,0.0020282546,0.0013135975,0.008167167,0.00020056296,0.00042687144],"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":[0.000014454775,0.000024032892,0.00022437065,0.0000040570917,0.000005806804,0.000005815126,0.00022541682,0.000001381845,0.09719143,0.00084182055,0.8866815,0.014779894],"study_design_scores_gemma":[0.00016142896,0.000037559166,0.005031057,0.000014000064,0.000016471258,0.00003652808,0.00024837794,0.0034975316,0.008258999,0.003967979,0.9784939,0.0002361335],"about_ca_topic_score_codex":0.00005164012,"about_ca_topic_score_gemma":0.0007352685,"teacher_disagreement_score":0.7815248,"about_ca_system_score_codex":0.00002063134,"about_ca_system_score_gemma":0.000110075904,"threshold_uncertainty_score":0.99985456},"labels":[],"label_agreement":null},{"id":"W2883298629","doi":"10.1038/sdata.2018.141","title":"MANTA2, update of the Mongo database for the analysis of transcription factor binding site alterations","year":2018,"lang":"en","type":"article","venue":"Scientific Data","topic":"Genomics and Chromatin Dynamics","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":"BC Children's Hospital; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Norges Forskningsråd; Universitetet i Oslo; European Molecular Biology Laboratory; Western Canada Research Grid; Weston Brain Institute; BC Children's Hospital; Children's Hospital Foundation; Compute Canada; Canadian Institutes of Health Research; Genome Canada","keywords":"DNA binding site; Genome; Binding site; Biology; Transcription factor; 1000 Genomes Project; Computational biology; Genetics; Database; Single-nucleotide polymorphism; Computer science; Gene; Promoter; Gene expression; Genotype","score_opus":0.033160377393625574,"score_gpt":0.2848577802092167,"score_spread":0.2516974028155911,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2883298629","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":[0.93003386,0.000083222054,0.02186672,0.000102368744,0.0004646137,0.00017086884,0.047258224,0.0000015085051,0.000018586483],"genre_scores_gemma":[0.98049843,0.00002903397,0.0012839893,0.000021006195,0.000045062206,0.000004037729,0.017762689,0.000005083587,0.0003506359],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993287,0.000020878671,0.00017710723,0.00027354516,0.000103372295,0.000096442454],"domain_scores_gemma":[0.998123,0.000011953846,0.00011822771,0.0016292887,0.00010061423,0.000016924407],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037727653,0.000055417797,0.00007683662,0.00005203872,0.00022995265,0.000045358476,0.000734659,0.000026140251,0.000030990737],"category_scores_gemma":[0.000046829828,0.000034436078,0.00007781528,0.00032624742,0.0002440904,0.000008638519,0.00026940825,0.00002198102,0.0000023661685],"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":[0.000008005094,0.0000231773,0.00034508228,0.000010859517,0.00017418212,1.5680845e-8,0.00010458042,0.00008283225,0.99323004,0.000101482925,0.0054225754,0.00049717544],"study_design_scores_gemma":[0.00047999673,0.00006885178,0.009749421,0.000022832954,0.0014398661,0.0000015069155,0.00033649418,0.2549517,0.5871673,0.000055334905,0.14550911,0.00021761464],"about_ca_topic_score_codex":0.000021668613,"about_ca_topic_score_gemma":0.0010095598,"teacher_disagreement_score":0.40606272,"about_ca_system_score_codex":0.0000035309715,"about_ca_system_score_gemma":0.000040767154,"threshold_uncertainty_score":0.17686331},"labels":[],"label_agreement":null},{"id":"W2884066197","doi":"10.1038/sdata.2018.129","title":"Leukocyte Tracking Database, a collection of immune cell tracks from intravital 2-photon microscopy videos","year":2018,"lang":"en","type":"article","venue":"Scientific Data","topic":"Immunotherapy and Immune Responses","field":"Immunology and Microbiology","cited_by":39,"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":"SystemsX.ch; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"Ground truth; Computer science; Intravital microscopy; Visualization; Tracking (education); Benchmarking; Immune system; Artificial intelligence; Computer vision; Biology; In vivo; Immunology","score_opus":0.02924483496951172,"score_gpt":0.28607389184270215,"score_spread":0.2568290568731904,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2884066197","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":[0.97216946,0.0117537435,0.0011033837,0.000049252863,0.006448163,0.00042297965,0.0074698953,0.00007520401,0.0005079194],"genre_scores_gemma":[0.9733059,0.00015627146,0.00095603237,0.000042779633,0.000067104396,0.000010561507,0.015333857,0.000030795716,0.01009673],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9974898,0.0003295344,0.0007112214,0.0008871105,0.00010644265,0.00047586666],"domain_scores_gemma":[0.9965992,0.00022358578,0.0003629063,0.0025867778,0.00020466695,0.000022889466],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001466524,0.00024060604,0.00041522644,0.00028049428,0.0007426995,0.00015245001,0.0016482692,0.00021127242,0.0025539696],"category_scores_gemma":[0.0002305984,0.0002261097,0.00010624677,0.00061421766,0.0015485896,0.0007470986,0.0005531867,0.0003069012,0.00087116065],"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":[0.0010321976,0.00026786717,0.00015376316,0.000017556238,0.00012745179,0.0000020547009,0.000970013,1.1344501e-7,0.9595535,0.000010249293,0.03289208,0.0049731494],"study_design_scores_gemma":[0.0013550268,0.00018848653,0.0025818036,0.00009614186,0.00006451193,0.000018223987,0.0003683042,0.000023966357,0.8518812,0.00003836962,0.14317614,0.00020780753],"about_ca_topic_score_codex":0.0012303846,"about_ca_topic_score_gemma":0.000155193,"teacher_disagreement_score":0.11028407,"about_ca_system_score_codex":0.000045839013,"about_ca_system_score_gemma":0.0002859167,"threshold_uncertainty_score":0.9999068},"labels":[],"label_agreement":null},{"id":"W2893400158","doi":"10.1038/sdata.2018.187","title":"Mimi-PAGE, an open-source implementation of the PAGE09 integrated assessment model","year":2018,"lang":"en","type":"article","venue":"Scientific Data","topic":"Climate Change Policy and Economics","field":"Economics, Econometrics and Finance","cited_by":29,"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":"Resources for the Future; Alfred P. Sloan Foundation; National Science Foundation","keywords":"Computer science; Documentation; Implementation; License; Source code; Modular design; Python (programming language); Open source; Coding (social sciences); World Wide Web; Software engineering; Database; Programming language; Operating system; Software","score_opus":0.3275247813131548,"score_gpt":0.3978441427766766,"score_spread":0.0703193614635218,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2893400158","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":[0.9239035,0.00006363941,0.0105364425,0.0015377097,0.0024524177,0.00070764654,0.04221984,0.000037386435,0.018541403],"genre_scores_gemma":[0.9901121,0.000018376148,0.0036150008,0.00034047416,0.00009181642,0.000013597529,0.0031206594,0.00002121722,0.0026667607],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99849784,0.000021136711,0.00052969134,0.0006551728,0.00004215488,0.000253993],"domain_scores_gemma":[0.99721116,0.000014964579,0.00040383873,0.0022564088,0.000050261326,0.00006334912],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0019863695,0.00010485693,0.00020452477,0.0001237976,0.00035899787,0.0005491289,0.0027584876,0.00004253832,0.0012124564],"category_scores_gemma":[0.00004654641,0.00009480101,0.000029917946,0.00034768012,0.00027315947,0.0010299085,0.0017688643,0.00008191581,0.00018406646],"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":[0.000055222965,0.0009793998,0.066407815,0.00011587878,0.00020269098,7.237423e-7,0.011292328,0.0005236326,0.0044344338,0.36637783,0.51849526,0.03111476],"study_design_scores_gemma":[0.0010941223,0.00011913391,0.017347874,0.000028707807,0.000023096123,0.000002400286,0.003351705,0.65159845,0.0020781867,0.04221134,0.28167552,0.00046945066],"about_ca_topic_score_codex":0.0015773907,"about_ca_topic_score_gemma":0.0041219904,"teacher_disagreement_score":0.6510748,"about_ca_system_score_codex":0.000079842604,"about_ca_system_score_gemma":0.0000875885,"threshold_uncertainty_score":0.99970055},"labels":[],"label_agreement":null},{"id":"W2895302239","doi":"10.1038/sdata.2018.201","title":"Free-electron laser data for multiple-particle fluctuation scattering analysis","year":2018,"lang":"en","type":"article","venue":"Scientific Data","topic":"Atomic and Subatomic Physics Research","field":"Physics and Astronomy","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Burnaby Hospital","funders":"SLAC National Accelerator Laboratory; National Institute of Allergy and Infectious Diseases; National Institute of General Medical Sciences; Office of Science; Basic Energy Sciences; National Energy Research Scientific Computing Center; U.S. Department of Energy; National Science Foundation; National Institutes of Health; Advanced Scientific Computing Research; Max-Planck-Gesellschaft","keywords":"Scattering; Diffraction; Optics; Laser; Physics; Computational physics; Materials science","score_opus":0.08264920372629775,"score_gpt":0.3614613696515484,"score_spread":0.27881216592525065,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2895302239","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":[0.5681992,0.000016411526,0.4006038,0.00034933977,0.00045231608,0.0004098746,0.029202411,0.000046184803,0.0007204741],"genre_scores_gemma":[0.966337,2.3485985e-7,0.0011379686,0.000016295717,0.0004612573,0.000014563628,0.030581735,0.000013652395,0.0014372602],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980692,0.000038315502,0.00021329256,0.0009386628,0.000301558,0.00043895387],"domain_scores_gemma":[0.99461484,0.00010430559,0.00007331365,0.00496353,0.00014260916,0.000101373655],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011920476,0.00011014313,0.00016474233,0.00010009844,0.0004956594,0.00040972335,0.0029916742,0.00001912719,0.00041677212],"category_scores_gemma":[0.00008690094,0.00010324631,0.000051116338,0.00084943144,0.00028047906,0.0007341101,0.0020540238,0.00007660977,0.00019281013],"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":[0.00014404677,0.0004147371,0.058563374,0.000033583223,0.0017811828,6.9564965e-7,0.0008168232,0.00011990039,0.1038168,0.006748644,0.63414824,0.19341199],"study_design_scores_gemma":[0.0004788363,0.000008267295,0.0007795451,0.000004181607,0.00017632944,6.644178e-8,0.00014902657,0.9378257,0.029484563,0.0035090756,0.027430033,0.00015436872],"about_ca_topic_score_codex":0.00019872651,"about_ca_topic_score_gemma":0.00018216736,"teacher_disagreement_score":0.9377058,"about_ca_system_score_codex":0.000028751652,"about_ca_system_score_gemma":0.0001762566,"threshold_uncertainty_score":0.5559325},"labels":[],"label_agreement":null},{"id":"W2896057756","doi":"10.1038/sdata.2018.209","title":"In-depth data on the network structure and hourly activity of the Central Chilean power grid","year":2018,"lang":"en","type":"article","venue":"Scientific Data","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Comisión Nacional de Investigación Científica y Tecnológica; Instituto de Sistemas Complejos de Ingeniería; National Research Foundation of Korea; National Research Foundation; University of Calgary","keywords":"Computer science; Raw data; Grid; Filter (signal processing); Stability (learning theory); Data mining; Distributed computing; Focus (optics); Real-time computing; Data structure; Machine learning; Geography","score_opus":0.03140422013737429,"score_gpt":0.28508400135533163,"score_spread":0.2536797812179573,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2896057756","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":[0.98549986,0.00002877312,0.0004986244,0.00092502916,0.0013344112,0.00033598772,0.00874062,0.000018438117,0.002618264],"genre_scores_gemma":[0.9982362,6.148324e-7,0.00018494629,0.000050429273,0.0005868529,9.0715804e-7,0.0008007045,0.0000075306243,0.000131859],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9986581,0.00012138311,0.00014286181,0.0005616941,0.0002421507,0.0002738175],"domain_scores_gemma":[0.9953682,0.00006704364,0.00013051089,0.0043688794,0.000029361046,0.0000359997],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00076487433,0.00011005954,0.00013569757,0.000023985494,0.00031220814,0.00018044928,0.002712721,0.000019089184,0.0005049843],"category_scores_gemma":[0.000019113015,0.000061140156,0.000026930453,0.0005363421,0.00053103274,0.00028708534,0.002633177,0.00019001578,0.000004301017],"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":[0.00001649482,0.00008361689,0.06337173,0.0000025966685,0.000064756336,2.3320938e-7,0.00017081323,0.000013953936,0.000711589,0.008270091,0.91530454,0.011989605],"study_design_scores_gemma":[0.0003507424,0.0000561512,0.6370185,0.00013768235,0.0001198253,0.0000012149825,0.00017242851,0.014708321,0.005790198,0.028760381,0.31247056,0.0004139657],"about_ca_topic_score_codex":0.0002763747,"about_ca_topic_score_gemma":0.000974272,"teacher_disagreement_score":0.602834,"about_ca_system_score_codex":0.00000771196,"about_ca_system_score_gemma":0.00004890771,"threshold_uncertainty_score":0.55292237},"labels":[],"label_agreement":null},{"id":"W2896064861","doi":"10.1038/sdata.2018.229","title":"Combining tensile testing and structural analysis at the single collagen fibril level","year":2018,"lang":"en","type":"article","venue":"Scientific Data","topic":"Collagen: Extraction and Characterization","field":"Materials Science","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":"Saint Mary's University; Institut National de la Recherche Scientifique; Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Fibril; Ultimate tensile strength; Microscopy; Materials science; Tensile testing; Collagen fibril; Tendon; Biophysics; Composite material; Biomedical engineering; Anatomy; Optics; Biology","score_opus":0.1541988817359119,"score_gpt":0.3086584682149464,"score_spread":0.15445958647903452,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2896064861","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":[0.9951239,0.00002548534,0.0003116511,0.00021747478,0.001360523,0.00011463045,0.0018351293,0.00005531784,0.00095585466],"genre_scores_gemma":[0.9912589,3.8263104e-7,0.0012915111,0.00008271817,0.00012424795,0.0000016329581,0.0008903646,0.000006855687,0.0063433647],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986154,0.00007004251,0.00020532672,0.00059105124,0.0003040449,0.00021416463],"domain_scores_gemma":[0.99835753,0.00013400929,0.00015305333,0.0010931704,0.000196664,0.000065587],"candidate_categories":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009253927,0.000091779155,0.00012154291,0.000094295574,0.0014179915,0.0010522134,0.0005180446,0.000029103088,0.0015106469],"category_scores_gemma":[0.00053158903,0.00006616331,0.000018114659,0.0011512227,0.000524337,0.0004875284,0.0008855506,0.000024786872,0.00020846051],"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":[0.000007295917,0.000006412134,0.0015438667,0.000003404624,0.0000129426735,0.0000010538048,0.00031199117,0.000008992514,0.98518616,0.000007248739,0.00988839,0.0030222517],"study_design_scores_gemma":[0.0005813061,0.000114948154,0.2811198,0.000041864005,0.00058089,0.00010138026,0.0010760982,0.099572085,0.5279482,0.0002567466,0.087964594,0.00064210297],"about_ca_topic_score_codex":0.00007884261,"about_ca_topic_score_gemma":0.000735154,"teacher_disagreement_score":0.45723796,"about_ca_system_score_codex":0.00003384063,"about_ca_system_score_gemma":0.000049110426,"threshold_uncertainty_score":0.9999848},"labels":[],"label_agreement":null},{"id":"W2898434771","doi":"10.1038/sdata.2018.240","title":"Meta-mining of copy number profiles of high-risk neuroblastoma tumors","year":2018,"lang":"en","type":"article","venue":"Scientific Data","topic":"Neuroblastoma Research and Treatments","field":"Medicine","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Neuroblastoma; Copy-number variation; Biology; Segmentation; Cluster (spacecraft); Oncology; Bioinformatics; Internal medicine; Computational biology; Computer science; Medicine; Gene; Genetics; Genome; Artificial intelligence","score_opus":0.10163417764522263,"score_gpt":0.3493303079652971,"score_spread":0.24769613032007448,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2898434771","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":[0.9938679,0.000032985565,0.000043621003,0.00009587016,0.00037561794,0.0003482838,0.0038320785,0.000032458935,0.0013712317],"genre_scores_gemma":[0.9916366,0.0000056191902,0.0040601566,0.000016766537,0.000057454847,0.000009254536,0.00067673833,0.000020118305,0.0035173323],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99774987,0.00010483503,0.00037097326,0.0006724624,0.0007719019,0.00032998197],"domain_scores_gemma":[0.9970005,0.00011478462,0.00023266076,0.0021523843,0.0003146038,0.00018505836],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007432559,0.00014360882,0.00044088118,0.00017809082,0.00013421869,0.00003853859,0.0006427216,0.00003077645,0.0013557822],"category_scores_gemma":[0.00050963624,0.00010219219,0.00008738728,0.00067243306,0.0010749415,0.00023649952,0.00067019224,0.000111040186,0.00034491078],"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":[0.0027828212,0.004408978,0.16129892,0.0011567008,0.0076509872,0.00065964274,0.0012280879,0.000004758984,0.22411814,0.00094395305,0.5665629,0.02918412],"study_design_scores_gemma":[0.0024793956,0.001537097,0.051615424,0.000178028,0.0020713701,0.00011437049,0.00013619238,0.000513344,0.9328898,0.00027522785,0.008001214,0.00018848646],"about_ca_topic_score_codex":0.00017090079,"about_ca_topic_score_gemma":0.000060485163,"teacher_disagreement_score":0.7087717,"about_ca_system_score_codex":0.0000114543745,"about_ca_system_score_gemma":0.00022057931,"threshold_uncertainty_score":0.99955714},"labels":[],"label_agreement":null},{"id":"W2899177940","doi":"10.1038/sdata.2018.236","title":"Datasets from a research project examining the role of politics in social psychological research","year":2018,"lang":"en","type":"article","venue":"Scientific Data","topic":"Academic Freedom and Politics","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Marsden Fund; Knut och Alice Wallenbergs Stiftelse","keywords":"Politics; Leverage (statistics); Relevance (law); Social research; Empirical research; Perception; Psychology; Psychological research; Publication bias; Test (biology); Social science; Social psychology; Political science; Data science; Sociology; MEDLINE; Epistemology; Computer science; Law; Ecology; Biology","score_opus":0.5869583855402817,"score_gpt":0.5763533724244022,"score_spread":0.01060501311587947,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2899177940","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":[0.78832346,0.0007569028,0.000018623956,0.0037546228,0.0021471279,0.0011989181,0.03674149,0.000057268913,0.16700158],"genre_scores_gemma":[0.9932694,0.0000173095,0.00035301578,0.000046778125,0.0025627608,0.00001146313,0.0017220827,0.000008214034,0.0020089909],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99342257,0.0025499712,0.0003077513,0.00073575124,0.0019296664,0.0010542879],"domain_scores_gemma":[0.9963514,0.0015109294,0.000059881975,0.0016169186,0.0003622503,0.00009862731],"candidate_categories":["metaresearch","sts"],"consensus_categories":["sts"],"category_scores_codex":[0.030162023,0.00007225552,0.00013445498,0.00030997145,0.0025915666,0.00031501273,0.004830982,0.00019659846,0.00023125975],"category_scores_gemma":[0.005461103,0.000053119245,0.000013465602,0.0022502725,0.01311056,0.00032834036,0.0020612665,0.00086334004,0.00019618169],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013113805,0.00010627027,0.0029347513,0.0000036946253,0.0000055602154,0.0000026509315,0.026111087,2.3267315e-8,0.00053459924,0.09246053,0.8707516,0.007076117],"study_design_scores_gemma":[0.0001211768,0.00004508454,0.0036011434,0.000020514532,0.0000034173938,3.3081105e-7,0.043979283,0.00011305043,0.000116249284,0.05357532,0.8983551,0.00006927825],"about_ca_topic_score_codex":0.028841062,"about_ca_topic_score_gemma":0.009669637,"teacher_disagreement_score":0.20494592,"about_ca_system_score_codex":0.00009085757,"about_ca_system_score_gemma":0.00086155185,"threshold_uncertainty_score":0.99870694},"labels":[],"label_agreement":null},{"id":"W2900302900","doi":"10.1038/sdata.2018.244","title":"X-ray computed microtomography of Megachirella wachtleri","year":2018,"lang":"en","type":"article","venue":"Scientific Data","topic":"Paleontology and Evolutionary Biology","field":"Earth and Planetary Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Killam Trusts; Natural Sciences and Engineering Research Council of Canada; Midwestern University","keywords":"X-ray microtomography; Computed tomography; Geology; Medicine; Radiology","score_opus":0.03846653945708901,"score_gpt":0.2500899514856179,"score_spread":0.2116234120285289,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2900302900","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":[0.9376489,0.003308522,0.0018571465,0.00040348317,0.008391856,0.00033530546,0.011413319,0.00010508767,0.036536377],"genre_scores_gemma":[0.99075675,0.000006435838,0.00421154,0.000059553782,0.00011608229,1.9472549e-7,0.004479111,0.0000010315028,0.00036932406],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9988165,0.00009946413,0.00019217595,0.0004971648,0.00013673968,0.00025794018],"domain_scores_gemma":[0.99869585,0.000071467344,0.000079713296,0.001008733,0.0000699873,0.00007423363],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00080803706,0.000081316015,0.00013180244,0.00014191712,0.00030725318,0.000028046568,0.0012206717,0.0000699462,0.002331353],"category_scores_gemma":[0.000046500703,0.000064739535,0.000028913742,0.0005050425,0.002099855,0.00020258118,0.00009060601,0.00007085608,0.00079890655],"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":[0.00007276913,0.00005439565,0.8335335,0.000015843285,0.000054694734,0.000005792788,0.00013899709,0.000036658897,0.0017129607,0.00013599926,0.13223532,0.032003064],"study_design_scores_gemma":[0.00014848074,0.00009051636,0.8345178,0.000010389348,0.000012404251,0.000010228874,0.000028181174,0.01618597,0.00019423645,0.00050281704,0.14819424,0.000104773404],"about_ca_topic_score_codex":0.00030207395,"about_ca_topic_score_gemma":0.003042726,"teacher_disagreement_score":0.05310782,"about_ca_system_score_codex":6.876983e-7,"about_ca_system_score_gemma":0.000057650865,"threshold_uncertainty_score":0.9999791},"labels":[],"label_agreement":null},{"id":"W2901044913","doi":"10.1038/sdata.2018.263","title":"Generation and quality control of lipidomics data for the alzheimer’s disease neuroimaging initiative cohort","year":2018,"lang":"en","type":"article","venue":"Scientific Data","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":66,"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 Diabetes and Digestive and Kidney Diseases; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institutes of Health; Genentech; National Institute of Neurological Disorders and Stroke; IXICO; H. Lundbeck A/S; Servier; Eisai; Northern California Institute for Research and Education; University of California, San Diego; Pfizer; Biogen; BioClinica; F. Hoffmann-La Roche; University of Southern California; Eli Lilly and Company; U.S. Department of Defense; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; Novartis Pharmaceuticals Corporation; Bristol-Myers Squibb; National Institute on Aging; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Lipidomics; Alzheimer's Disease Neuroimaging Initiative; Neuroimaging; Metabolomics; Cohort; Disease; Etiology; Alzheimer's disease; Medicine; Metabolome; Computational biology; Bioinformatics; Internal medicine; Biology; Psychiatry","score_opus":0.21299411330994492,"score_gpt":0.3785598212245248,"score_spread":0.1655657079145799,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2901044913","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":[0.49608755,0.033580832,0.28924686,0.005540818,0.009160511,0.0035664232,0.16218275,0.000029493056,0.00060475233],"genre_scores_gemma":[0.98833334,0.00028222246,0.0012887125,0.00025924962,0.0005408449,0.00001200745,0.009201632,0.000007839647,0.00007415406],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99888206,0.000062735715,0.000187668,0.00062138453,0.00011397839,0.00013218037],"domain_scores_gemma":[0.9974478,0.0000647867,0.000121907215,0.0021565603,0.00016411842,0.000044830496],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017284383,0.00007928261,0.000117977484,0.000024070825,0.00030797216,0.00009302056,0.0007910774,0.000018735376,0.0000056292124],"category_scores_gemma":[0.0010878446,0.000057422425,0.0000182671,0.00007795383,0.0005629095,0.000018849772,0.0010742565,0.000028134276,9.554957e-7],"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":[0.00038388552,0.00013543427,0.019481469,0.00003985597,0.0008409831,3.2655723e-7,0.00009093023,0.0000066701077,0.68570036,0.0041364487,0.27602926,0.013154382],"study_design_scores_gemma":[0.0021632814,0.00016452472,0.05867042,0.000011212432,0.0011230089,0.0000018944961,0.00021661073,0.08616303,0.046229567,0.0005691202,0.8042513,0.0004360276],"about_ca_topic_score_codex":0.000013538682,"about_ca_topic_score_gemma":0.000087921464,"teacher_disagreement_score":0.6394708,"about_ca_system_score_codex":0.0000015980227,"about_ca_system_score_gemma":0.00007729246,"threshold_uncertainty_score":0.2368704},"labels":[],"label_agreement":null},{"id":"W2901175140","doi":"10.1038/sdata.2018.257","title":"Anthropomorphic breast model repository for research and development of microwave breast imaging technologies","year":2018,"lang":"en","type":"article","venue":"Scientific Data","topic":"Microwave Imaging and Scattering Analysis","field":"Engineering","cited_by":21,"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 Calgary","funders":"Alberta Innovates; Killam Trusts","keywords":"Breast imaging; Microwave imaging; Computer science; Documentation; Mammography; Breast MRI; Medical physics; Microwave; Flexibility (engineering); Imaging technology; Systems engineering; Breast cancer; Radiology; Medicine; Engineering","score_opus":0.0909992141427596,"score_gpt":0.3269898645212841,"score_spread":0.23599065037852449,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2901175140","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":[0.46018985,0.0022741118,0.5265202,0.0011106939,0.0015007078,0.00057371764,0.0053408467,0.0011248465,0.0013650572],"genre_scores_gemma":[0.95841473,0.0000064190876,0.040891152,0.0000017082832,0.00003129459,0.000007382689,0.00029546308,0.000019900934,0.00033194106],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99858546,0.000013220408,0.00026841517,0.00054479024,0.00022988509,0.00035823116],"domain_scores_gemma":[0.99832845,0.000031386444,0.0000362806,0.0012850983,0.00027434196,0.00004446572],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013947319,0.00011247268,0.00015336824,0.00035927247,0.00052063924,0.00024512605,0.0008110646,0.000036206042,0.000004673476],"category_scores_gemma":[0.00002995429,0.00010799159,0.000016616203,0.00037855472,0.0014915839,0.00021311198,0.0006434531,0.00011470701,0.000011517906],"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":[0.000009361113,0.000039000755,0.000519356,0.00019308914,0.00006200257,0.00000214978,0.00069515704,0.00008324878,0.8591643,0.000028301998,0.057530396,0.08167362],"study_design_scores_gemma":[0.00021468278,0.000008404043,0.00025104173,0.00017823768,0.000023508228,0.00020959938,0.0013200056,0.6689496,0.3227306,0.00045123426,0.00539499,0.00026809587],"about_ca_topic_score_codex":0.000014721326,"about_ca_topic_score_gemma":0.000029805022,"teacher_disagreement_score":0.66886634,"about_ca_system_score_codex":0.000041363717,"about_ca_system_score_gemma":0.00008498998,"threshold_uncertainty_score":0.5495803},"labels":[],"label_agreement":null},{"id":"W2901467993","doi":"10.1038/sdata.2018.249","title":"GloPL, a global data base on pollen limitation of plant reproduction","year":2018,"lang":"en","type":"article","venue":"Scientific Data","topic":"Plant and animal studies","field":"Agricultural and Biological Sciences","cited_by":64,"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 Calgary","funders":"Deutsches Zentrum für integrative Biodiversitätsforschung Halle-Jena-Leipzig; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Fundação de Amparo à Pesquisa do Estado de São Paulo; Deutsche Forschungsgemeinschaft; Alexander von Humboldt-Stiftung; Case Western Reserve University; National Science Foundation","keywords":"Pollen; Plant reproduction; Pollination; Biology; Outcrossing; Pollen source; Biome; Stamen; Reproduction; Pollinator; Botany; Abiotic component; Zoophily; Ecology; Ecosystem","score_opus":0.292284396659378,"score_gpt":0.29168242477216005,"score_spread":0.0006019718872179447,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2901467993","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":[0.9234622,0.00015421647,0.0000030743522,0.0018675647,0.00067309564,0.00014175978,0.07175786,0.00004684795,0.0018933854],"genre_scores_gemma":[0.97712064,0.0000254746,0.00020231663,0.000048646136,0.0005421315,9.74469e-7,0.021465538,3.2969206e-7,0.0005939381],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99863887,0.000032755706,0.00014630306,0.0007596417,0.00026711304,0.00015532368],"domain_scores_gemma":[0.999379,0.000044932967,0.000084030646,0.00038781573,0.00006579289,0.00003843348],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000835578,0.000070551694,0.000091901944,0.0000082890365,0.00032947777,0.000091713715,0.0011421194,0.000025240102,0.00009276435],"category_scores_gemma":[0.00034404,0.000026657104,0.000012891997,0.00042587766,0.00022060383,0.0003071146,0.0008606911,0.00002978111,0.00019292855],"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":[0.00009930993,0.00015154852,0.004017229,0.0000065961212,0.000016713986,0.0000023557404,0.000044882443,1.7163346e-7,0.0854662,0.00037104753,0.8562663,0.053557646],"study_design_scores_gemma":[0.00012771957,0.00032470186,0.22837223,0.00005610769,0.000025411837,0.000009771912,0.0004494554,0.0006980843,0.0031446903,0.0005185249,0.76608944,0.00018388154],"about_ca_topic_score_codex":0.00017120481,"about_ca_topic_score_gemma":0.004183932,"teacher_disagreement_score":0.224355,"about_ca_system_score_codex":0.000009334616,"about_ca_system_score_gemma":0.000010228307,"threshold_uncertainty_score":0.253411},"labels":[],"label_agreement":null},{"id":"W2902209191","doi":"10.1038/sdata.2018.270","title":"In-vivo probabilistic atlas of human thalamic nuclei based on diffusion- weighted magnetic resonance imaging","year":2018,"lang":"en","type":"article","venue":"Scientific Data","topic":"Advanced Neuroimaging Techniques and Applications","field":"Medicine","cited_by":118,"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 Hospitalier Universitaire Sainte-Justine; Université de Sherbrooke","funders":"Centre d'Imagerie BioMédicale; Université de Lausanne; Université de Genève; Hôpitaux Universitaires de Genève; École Polytechnique Fédérale de Lausanne; Centre Hospitalier Universitaire Vaudois; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Atlas (anatomy); Segmentation; Computer science; Magnetic resonance imaging; Artificial intelligence; Thalamus; Cluster analysis; Diffusion MRI; Diffusion-Weighted Magnetic Resonance Imaging; Pattern recognition (psychology); Probabilistic logic; Brain atlas; Functional magnetic resonance imaging; Neuroimaging; Neuroscience; Biology; Anatomy; Medicine; Radiology","score_opus":0.05710554135325454,"score_gpt":0.3492608401373721,"score_spread":0.29215529878411756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2902209191","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":[0.9669144,0.000385245,0.0025644545,0.0079955235,0.0008095491,0.002690176,0.0025721288,0.00047813242,0.015590385],"genre_scores_gemma":[0.98590297,0.000004001395,0.010134803,0.0003234769,0.000072930045,0.000027349355,0.00038895005,0.000026793756,0.0031187283],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99843377,0.000025457146,0.00025060243,0.00075632724,0.00030221237,0.00023162144],"domain_scores_gemma":[0.9971032,0.00005514406,0.0000872312,0.0025844646,0.00010658422,0.000063386346],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033300673,0.00011695214,0.00016945582,0.00020817839,0.00017579945,0.000035792473,0.0006491856,0.000022952285,0.00037453294],"category_scores_gemma":[0.00014269867,0.00010175967,0.000025212863,0.000663199,0.00076762325,0.000124661,0.00030964357,0.00013116695,0.00004237207],"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":[0.00014834446,0.0016111458,0.019658078,0.00020413606,0.0000023806167,0.00006117199,0.00016447256,0.0000025024249,0.6433306,0.006934433,0.30616766,0.021715118],"study_design_scores_gemma":[0.0028892176,0.00058235624,0.053484477,0.0014316076,0.00008359838,0.000031001535,0.000047324655,0.24269366,0.0626092,0.017353518,0.61825985,0.0005341848],"about_ca_topic_score_codex":0.000023062157,"about_ca_topic_score_gemma":0.000016053044,"teacher_disagreement_score":0.5807214,"about_ca_system_score_codex":0.000036664725,"about_ca_system_score_gemma":0.00006697513,"threshold_uncertainty_score":0.4149639},"labels":[],"label_agreement":null},{"id":"W2905179958","doi":"10.1038/sdata.2018.286","title":"On the privacy-conscientious use of mobile phone data","year":2018,"lang":"en","type":"editorial","venue":"Scientific Data","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":168,"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 du Québec à Montréal","funders":"Belgian Federal Science Policy Office; Fonds De La Recherche Scientifique - FNRS; Agence Nationale de la Recherche; UNICEF; Natural Sciences and Engineering Research Council of Canada; Agence Française de Développement; Bill and Melinda Gates Foundation","keywords":"Mobile phone; Internet privacy; Computer science; Data science; Phone; Field (mathematics); Scale (ratio); Social media; Mobile device; Computational sociology; World Wide Web; Telecommunications; Geography; Cartography","score_opus":0.09751765212507633,"score_gpt":0.32438209284749736,"score_spread":0.226864440722421,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2905179958","genre_codex":"editorial","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013220975,0.00025580788,0.020891111,0.0022434676,0.86037314,0.00084249413,0.11441688,0.00065345946,0.00019145034],"genre_scores_gemma":[0.00040001693,0.0004313019,0.43659058,0.0002452565,0.32633793,0.00018007812,0.22549818,0.00023888239,0.010077752],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9884858,0.000353491,0.0010049656,0.0053397208,0.003846048,0.00096993434],"domain_scores_gemma":[0.64232534,0.0067595863,0.0015703031,0.34808725,0.0010505363,0.00020696652],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.010186872,0.00057674403,0.00065672403,0.0006403179,0.0008582388,0.0041841166,0.43705496,0.00070247275,0.00020746411],"category_scores_gemma":[0.2991443,0.00041530724,0.00008887408,0.0028977308,0.0035496976,0.0044664065,0.69849586,0.0014078823,0.0010694066],"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":[0.000007611581,0.00016368603,0.0000013982647,0.00004864667,0.000059781654,0.000010711905,0.000035448767,8.3398936e-7,0.00011070593,0.00030449138,0.99500364,0.004253059],"study_design_scores_gemma":[0.00019026513,0.00006799359,0.0000019451827,0.00025330076,0.0000404007,0.0000027612623,0.000010027907,0.03390707,0.00051828753,0.020789413,0.9437985,0.0004200451],"about_ca_topic_score_codex":0.00016190916,"about_ca_topic_score_gemma":0.0001139992,"teacher_disagreement_score":0.5340352,"about_ca_system_score_codex":0.00011836434,"about_ca_system_score_gemma":0.0015738996,"threshold_uncertainty_score":0.9998299},"labels":[],"label_agreement":null},{"id":"W2908989331","doi":"10.1038/s41597-018-0005-2","title":"Author Correction: A compendium of geochemical information from the Saanich Inlet water column","year":2019,"lang":"en","type":"erratum","venue":"Scientific Data","topic":"Geological Studies and Exploration","field":"Earth and Planetary Sciences","cited_by":186,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Genome British Columbia; Fisheries and Oceans Canada; Concordia University; Canadian Institute for Advanced Research; University of British Columbia","funders":"","keywords":"Compendium; Table (database); Inlet; Column (typography); Water column; Geology; Chemistry; Oceanography; Mathematics; Computer science; Database; History; Archaeology","score_opus":0.04358805088912733,"score_gpt":0.2293282728724539,"score_spread":0.18574022198332657,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2908989331","genre_codex":"editorial","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017110575,0.003303378,0.0009859402,0.01473358,0.75454354,0.0024631312,0.13175043,0.00020580077,0.07490363],"genre_scores_gemma":[0.044393543,0.0000879546,0.0002057782,0.00041359456,0.0013077217,0.000003475802,0.8594835,0.0000046902355,0.094099775],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99808055,0.000087016255,0.0004240631,0.00047183392,0.00063330255,0.0003032035],"domain_scores_gemma":[0.9980979,0.00014999908,0.00021740845,0.0013361077,0.00013994174,0.000058623158],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0010042111,0.00016892451,0.000279869,0.000044194567,0.00044712308,0.00044950176,0.0016247956,0.00022764166,0.006716935],"category_scores_gemma":[0.00022827732,0.00008944605,0.000052450643,0.00024197207,0.00033073727,0.0007111586,0.0004747285,0.0004491379,0.0043101846],"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":[0.00001786431,0.000006571717,0.0022691393,0.000016998612,0.000022476488,3.6692728e-7,0.00034931334,0.00003783475,0.0000040840696,0.0000018985997,0.99152905,0.0057444233],"study_design_scores_gemma":[0.00008792367,0.00003573372,0.012195128,0.000037712995,0.000037095404,0.0000015640342,0.00050920225,0.014449097,0.000027200833,0.00020042638,0.9722807,0.00013821904],"about_ca_topic_score_codex":0.004570453,"about_ca_topic_score_gemma":0.009213779,"teacher_disagreement_score":0.7532358,"about_ca_system_score_codex":0.0000063639823,"about_ca_system_score_gemma":0.000094402705,"threshold_uncertainty_score":0.9964651},"labels":[],"label_agreement":null},{"id":"W2909942535","doi":"10.1038/s41597-024-04278-w","title":"The International Bathymetric Chart of the Arctic Ocean Version 5.0","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Methane Hydrates and Related Phenomena","field":"Environmental Science","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":"Canadian Hydrographic Service; Geological Survey of Canada","funders":"Executive Agency for Small and Medium-sized Enterprises; Jet Propulsion Laboratory; European Climate, Infrastructure and Environment Executive Agency; Stockholms Universitet; Universitat de Barcelona; Vetenskapsrådet; Polarforskningssekretariatet; Agencia Estatal de Investigación; California Institute of Technology; National Aeronautics and Space Administration","keywords":"Bathymetry; Arctic; Bathymetric chart; Oceanography; Sea ice; Seafloor spreading; Submarine pipeline; Arctic ice pack; The arctic; Marine geology; Seabed; Geology; Environmental science","score_opus":0.020803981717288794,"score_gpt":0.24122598158175676,"score_spread":0.22042199986446798,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2909942535","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":[0.83693,0.0040483586,0.00014483936,0.015060659,0.05537821,0.00073724106,0.0023048585,0.00010970015,0.08528616],"genre_scores_gemma":[0.96828026,0.00006214082,0.00005870241,0.000037727055,0.00004244407,6.3649344e-7,0.00017475919,0.000005575145,0.031337764],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988565,0.000033672197,0.00013004556,0.00033546123,0.00051376305,0.00013056006],"domain_scores_gemma":[0.9987942,0.000093729286,0.000038221886,0.0010342776,0.0000072250436,0.000032352422],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0013662593,0.00005159088,0.000037897815,0.000037054,0.0002966929,0.00023085967,0.0020905046,0.000019567791,0.0020166845],"category_scores_gemma":[0.00013099419,0.00002420213,0.000032405707,0.00088366703,0.00040712956,0.00021234894,0.0018003939,0.00011550078,0.0011014516],"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":[0.000007950636,0.000052494066,0.0040852004,0.000018556895,0.00004720453,0.0000032291732,0.0004074487,0.00029442905,0.010662764,0.0011048975,0.9592481,0.024067683],"study_design_scores_gemma":[0.000052282114,0.000006416276,0.0029227983,0.000029943243,0.000015858179,0.0000039183137,0.000084463434,0.023616288,0.0011018958,0.0012185924,0.97089744,0.00005008384],"about_ca_topic_score_codex":0.000052253738,"about_ca_topic_score_gemma":0.000015856973,"teacher_disagreement_score":0.13135028,"about_ca_system_score_codex":0.000048928545,"about_ca_system_score_gemma":0.000018813154,"threshold_uncertainty_score":0.9996763},"labels":[],"label_agreement":null},{"id":"W2910750340","doi":"10.1038/sdata.2018.280","title":"A global dataset of CO2 emissions and ancillary data related to emissions for 343 cities","year":2019,"lang":"en","type":"article","venue":"Scientific Data","topic":"Air Quality and Health Impacts","field":"Environmental Science","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":"Environment and Climate Change Canada","funders":"Centre National de la Recherche Scientifique; Fondation BNP Paribas; BNP Paribas Cardif","keywords":"Greenhouse gas; Environmental science; China; Sample (material); Data set; Data quality; Geography; Business; Statistics; Mathematics; Ecology","score_opus":0.11633315598266655,"score_gpt":0.38402478668171347,"score_spread":0.2676916306990469,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2910750340","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22633265,0.00026410373,0.0010410402,0.006035536,0.0010518609,0.0012642846,0.7618173,0.000047700094,0.0021455688],"genre_scores_gemma":[0.24638642,0.0001615992,0.085275285,0.0068181567,0.00010342088,0.000029853929,0.63927144,0.000060561382,0.021893257],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978836,0.00005516591,0.00036707975,0.00091121666,0.00040772074,0.0003752184],"domain_scores_gemma":[0.99548346,0.00012247247,0.00011572924,0.003819561,0.000013417124,0.00044535805],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002413608,0.0001104467,0.00018167417,0.000033102937,0.00036878773,0.000090507005,0.0019998548,0.00006822538,0.0014371907],"category_scores_gemma":[0.0008698803,0.00009320877,0.00001142207,0.00048220946,0.00037467544,0.0008385719,0.0049773897,0.000069187954,0.0003101488],"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":[0.00002107056,0.000044884782,0.007163166,0.000066924265,0.0000053162407,6.515696e-7,0.00018416665,0.000026440162,0.0005798851,0.0001380262,0.98820525,0.0035642295],"study_design_scores_gemma":[0.00028751028,0.00005319576,0.0132435085,0.000078279736,0.000018571118,0.00000662715,0.00041554845,0.0072181965,0.000049203125,0.0007328411,0.97775584,0.00014067597],"about_ca_topic_score_codex":0.00025138774,"about_ca_topic_score_gemma":0.00032110728,"teacher_disagreement_score":0.12254581,"about_ca_system_score_codex":0.000049884417,"about_ca_system_score_gemma":0.0001352192,"threshold_uncertainty_score":0.99947566},"labels":[],"label_agreement":null},{"id":"W2911105719","doi":"10.1038/sdata.2018.299","title":"A long-term, temporally consistent, gridded daily meteorological dataset for northwestern North America","year":2019,"lang":"en","type":"article","venue":"Scientific Data","topic":"Cryospheric studies and observations","field":"Earth and Planetary Sciences","cited_by":104,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Environment and Climate Change Canada; Pacific Institute for Climate Solutions; University of Victoria","funders":"","keywords":"Term (time); Climatology; Environmental science; Geography; Geology","score_opus":0.07526351363347097,"score_gpt":0.2719372194882594,"score_spread":0.1966737058547884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2911105719","genre_codex":"empirical","genre_gemma":"dataset","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":[0.7588573,0.0004846842,0.0005047938,0.0002950186,0.0020254774,0.00067367,0.23698582,0.000045721983,0.00012752232],"genre_scores_gemma":[0.34037694,0.000052432297,0.004165068,0.00093063735,0.00013450322,0.000007621815,0.6526713,0.0000069059606,0.001654586],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9977972,0.00004315442,0.00033071922,0.0010172828,0.00035727955,0.00045438152],"domain_scores_gemma":[0.9974541,0.00023852423,0.00015820538,0.0019102881,0.0000850373,0.00015385376],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0004685199,0.00017782465,0.00026633198,0.000039905517,0.00047580735,0.00029840952,0.0015385994,0.000040431267,0.0027049575],"category_scores_gemma":[0.000101535756,0.00013356192,0.00005896204,0.0004805424,0.00033846108,0.0005613167,0.0003080062,0.00009397682,0.0013511516],"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":[0.000034275276,0.000031883534,0.83511466,0.000022620536,0.000037922768,0.000006910248,0.000044555087,0.000094309624,0.000007656924,0.0000035278845,0.15539117,0.009210532],"study_design_scores_gemma":[0.00026129576,0.000079689074,0.5914247,0.000004800215,0.00003040783,0.0000030074657,0.000076139266,0.0024905049,6.8071415e-7,0.000013048382,0.40547454,0.00014116534],"about_ca_topic_score_codex":0.0005620012,"about_ca_topic_score_gemma":0.023953594,"teacher_disagreement_score":0.41848034,"about_ca_system_score_codex":0.0000038736353,"about_ca_system_score_gemma":0.000096470205,"threshold_uncertainty_score":0.9994264},"labels":[],"label_agreement":null},{"id":"W2911747435","doi":"10.1038/s41597-018-0006-1","title":"Publisher Correction: GloPL, a global data base on pollen limitation of plant reproduction","year":2019,"lang":"en","type":"erratum","venue":"Scientific Data","topic":"Invertebrate Taxonomy and Ecology","field":"Agricultural and Biological Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Pollen; Reproduction; Plant reproduction; Base (topology); Computer science; Information retrieval; Statistics; Biology; Mathematics; Botany; Ecology; Pollination","score_opus":0.10894450563427192,"score_gpt":0.2556106430272448,"score_spread":0.14666613739297285,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2911747435","genre_codex":"editorial","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004393901,0.00079363846,0.000011589865,0.007304388,0.7509832,0.0016421891,0.13401958,0.00021838317,0.10063317],"genre_scores_gemma":[0.0029259326,0.00007833324,0.00008770101,0.00021902869,0.0026718061,0.000010123847,0.63273907,0.0000023432049,0.36126563],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99622864,0.00017167734,0.00044847757,0.0022556349,0.0005183312,0.00037721815],"domain_scores_gemma":[0.99679357,0.00009696692,0.00048171234,0.0023550529,0.00018459295,0.00008809302],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0020121504,0.00024589733,0.00036445135,0.00004671345,0.00035820855,0.00046593204,0.003421921,0.00040910422,0.0011805783],"category_scores_gemma":[0.0008818845,0.00011104247,0.000055117176,0.0009067373,0.00022896887,0.0012222093,0.0017209972,0.00038335772,0.0008293449],"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":[0.000044185876,0.0001405863,0.00018623142,0.000026628733,0.000027054657,0.0000026116518,0.00000936316,0.0000023869216,0.0000609329,0.000041756884,0.9779823,0.021476004],"study_design_scores_gemma":[0.00009287422,0.00015241223,0.0027518936,0.00007565557,0.000044584278,0.00001580097,0.00020859185,0.0016141783,0.000009251134,0.00012930123,0.994676,0.00022947992],"about_ca_topic_score_codex":0.00058450643,"about_ca_topic_score_gemma":0.007334316,"teacher_disagreement_score":0.74831134,"about_ca_system_score_codex":0.000089152745,"about_ca_system_score_gemma":0.00021375106,"threshold_uncertainty_score":0.9999486},"labels":[],"label_agreement":null},{"id":"W2912425033","doi":"10.1038/sdata.2018.310","title":"PEPCONF, a diverse data set of peptide conformational energies","year":2019,"lang":"en","type":"article","venue":"Scientific Data","topic":"Chemical Synthesis and Analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Okanagan University College; University of British Columbia, Okanagan Campus; University of British Columbia","funders":"British Columbia Knowledge Development Fund; Natural Sciences and Engineering Research Council of Canada; Western Canada Research Grid; Compute Canada","keywords":"Conformational isomerism; Peptide; Chemistry; Tripeptide; Set (abstract data type); Conformational ensembles; Data set; Computational chemistry; Crystallography; Database; Molecule; Computer science; Molecular dynamics; Artificial intelligence; Biochemistry","score_opus":0.05172673562870435,"score_gpt":0.29104771952590347,"score_spread":0.23932098389719914,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2912425033","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":[0.9779275,0.0001704427,0.00014774677,0.000114683564,0.00024064748,0.00006891336,0.018564384,0.0000059580098,0.0027597318],"genre_scores_gemma":[0.92651325,0.000022795572,0.0005776795,0.000036030142,0.00007128393,7.1664306e-7,0.06798556,0.0000044266744,0.004788253],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99900883,0.000015405962,0.00017232791,0.00047005358,0.00021233235,0.000121044395],"domain_scores_gemma":[0.99722356,0.000013866541,0.000087098226,0.0025702633,0.00006320763,0.00004200941],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047134623,0.00006796072,0.000105292,0.00003149453,0.000050658728,0.000064816944,0.0016119924,0.000040008625,0.00046586222],"category_scores_gemma":[0.00015120544,0.000057319296,0.000034619774,0.00010499625,0.00015068478,0.000025739379,0.0021772273,0.00002828128,0.00013224661],"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":[0.000012411802,0.000024747664,0.0014029847,0.000023734186,0.00006376902,2.5566072e-7,0.000020879515,0.000020263942,0.79505956,0.00008012841,0.20097078,0.002320456],"study_design_scores_gemma":[0.00019934618,0.000011447063,0.00042776088,0.000013424276,0.000038198817,0.0000018272908,0.00029021184,0.0030896391,0.18178946,0.000028263925,0.81398493,0.00012552187],"about_ca_topic_score_codex":0.000034220477,"about_ca_topic_score_gemma":0.000033229535,"teacher_disagreement_score":0.61327016,"about_ca_system_score_codex":0.0000027068756,"about_ca_system_score_gemma":0.00006718278,"threshold_uncertainty_score":0.5100865},"labels":[],"label_agreement":null},{"id":"W2913467375","doi":"10.1038/sdata.2019.13","title":"MicroRNA expression profiles across blood and different tissues in cattle","year":2019,"lang":"en","type":"article","venue":"Scientific Data","topic":"MicroRNA in disease regulation","field":"Biochemistry, Genetics and Molecular Biology","cited_by":43,"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 Alberta","funders":"Alberta Agriculture and Forestry","keywords":"microRNA; Biology; Microvesicles; Gene expression profiling; Computational biology; Gene expression; Transcriptome; Regulation of gene expression; Gene; Bioinformatics; Genetics","score_opus":0.01752199827010926,"score_gpt":0.2868957112692079,"score_spread":0.2693737129990986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2913467375","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":[0.9970036,0.0012877524,0.000020798218,0.00003617513,0.00028763118,0.00021225243,0.0010919778,0.0000063126104,0.000053498537],"genre_scores_gemma":[0.9923944,0.000021868731,0.0002711078,0.000008503602,0.00004155162,0.0000053413846,0.005434954,0.000008975656,0.001813281],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989663,0.000030227444,0.000118399315,0.00060428254,0.000104175444,0.00017662268],"domain_scores_gemma":[0.99878854,0.000004688812,0.0000445306,0.0010904864,0.000022764338,0.000049001123],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022386755,0.00008479886,0.000077269695,0.000027064598,0.000060277634,0.000113525304,0.00038930893,0.00005834055,0.000044720604],"category_scores_gemma":[0.00003787491,0.000072098635,0.000012253733,0.00006317174,0.00010523252,0.000012274535,0.00087433826,0.00003581569,0.00002921742],"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":[0.0000115344965,0.00005553072,0.019798735,0.000031941316,0.000004752652,6.0626974e-7,0.000057938505,0.0000017661041,0.9737889,0.0000029837345,0.00553691,0.0007083782],"study_design_scores_gemma":[0.00038374853,0.00001798726,0.05269426,0.000044316967,0.0000055860874,0.0000037274135,0.00007210415,0.00005052153,0.92314684,0.000021105938,0.023449654,0.00011013786],"about_ca_topic_score_codex":0.0000092450455,"about_ca_topic_score_gemma":0.00005472874,"teacher_disagreement_score":0.050642073,"about_ca_system_score_codex":0.0000045619126,"about_ca_system_score_gemma":0.000023301143,"threshold_uncertainty_score":0.2940097},"labels":[],"label_agreement":null},{"id":"W2914831628","doi":"10.1038/sdata.2018.301","title":"A collection of rumen bacteriome data from 334 mid-lactation dairy cows","year":2019,"lang":"en","type":"article","venue":"Scientific Data","topic":"Ruminant Nutrition and Digestive Physiology","field":"Agricultural and Biological Sciences","cited_by":19,"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":"Biology; Rumen; Milking; Breed; Population; Dairy cattle; 16S ribosomal RNA; Lactation; Pyrosequencing; Animal science; Biotechnology; Food science; Bacteria; Genetics; Gene; Fermentation","score_opus":0.07573706693013013,"score_gpt":0.2746505349462183,"score_spread":0.1989134680160882,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2914831628","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":[0.9780951,0.00005942267,0.0000056497925,0.0005848527,0.0010576644,0.00021412078,0.01919234,0.000028513978,0.0007623324],"genre_scores_gemma":[0.91057897,0.0000147641895,0.00015715104,0.000043942277,0.00008775836,0.000002574928,0.08722779,6.9650673e-7,0.0018863407],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9985934,0.0000911842,0.00021197177,0.00072706945,0.00021027075,0.00016611649],"domain_scores_gemma":[0.99891627,0.00015503334,0.00013836949,0.0006567138,0.00007804052,0.000055551183],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00045399356,0.0000840144,0.00015597898,0.000025947274,0.00015170936,0.00011093462,0.001361188,0.000053451808,0.0024205856],"category_scores_gemma":[0.000099824516,0.00003741409,0.00002118771,0.00054337946,0.00014086875,0.00067630096,0.0008062536,0.00005414889,0.0005200047],"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":[0.000053914548,0.00013003188,0.0040002596,0.000006348281,0.000007871235,3.9070952e-7,0.00002641472,2.7532818e-7,0.90763366,0.000023130287,0.083408915,0.0047088093],"study_design_scores_gemma":[0.00048425604,0.00018248225,0.6445628,0.000056055185,0.000019495455,0.0000021457172,0.00045528435,0.001959143,0.018969486,0.0011075021,0.3319726,0.00022875587],"about_ca_topic_score_codex":0.00039391496,"about_ca_topic_score_gemma":0.0004980842,"teacher_disagreement_score":0.8886641,"about_ca_system_score_codex":0.000011874219,"about_ca_system_score_gemma":0.000021530232,"threshold_uncertainty_score":0.99849135},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"observational","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W2915100187","doi":"10.1038/sdata.2019.32","title":"A 1980–2018 global fire danger re-analysis dataset for the Canadian Fire Weather Indices","year":2019,"lang":"en","type":"article","venue":"Scientific Data","topic":"Fire effects on ecosystems","field":"Environmental Science","cited_by":88,"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":"Horizon 2020 Framework Programme","keywords":"Environmental science; Climatology; Meteorology; Geography; Geology","score_opus":0.024263497241997518,"score_gpt":0.2643931061104489,"score_spread":0.2401296088684514,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2915100187","genre_codex":"dataset","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":[0.37081003,0.00054553687,0.00015869776,0.0039656754,0.006091255,0.003221692,0.60879433,0.000080395796,0.006332397],"genre_scores_gemma":[0.9438323,0.000002269365,0.00035388974,0.00046062528,0.00007886199,0.000047178288,0.04882098,0.00001736419,0.0063865627],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971653,0.00008790657,0.00024692685,0.0012269131,0.0006739936,0.0005989421],"domain_scores_gemma":[0.9946381,0.0001564758,0.00014028294,0.0048038852,0.000011358918,0.00024989355],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0026051665,0.00018748091,0.00022496618,0.000054482272,0.00082436437,0.00074206793,0.0037544563,0.000087769215,0.0053873393],"category_scores_gemma":[0.00016610508,0.00012929973,0.00008464704,0.0015538908,0.00038126085,0.00073769386,0.0010857445,0.000101005964,0.007354461],"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":[0.000005687884,0.000024589845,0.031691138,0.000013814651,0.00016853001,0.000003337907,0.00014567585,0.00011281219,0.000042518797,0.000011447106,0.95539546,0.0123850135],"study_design_scores_gemma":[0.00013922788,0.000016638764,0.021436196,0.000008596853,0.00025887482,0.0000022072584,0.00008733803,0.11988664,0.000009424506,0.00002291751,0.85795254,0.00017940233],"about_ca_topic_score_codex":0.3868903,"about_ca_topic_score_gemma":0.8977815,"teacher_disagreement_score":0.57302225,"about_ca_system_score_codex":0.00038789018,"about_ca_system_score_gemma":0.000097182085,"threshold_uncertainty_score":0.99552184},"labels":[],"label_agreement":null},{"id":"W2915913218","doi":"10.1038/sdata.2019.25","title":"Map of physical interactions between extracellular domains of Arabidopsis leucine-rich repeat receptor kinases","year":2019,"lang":"en","type":"article","venue":"Scientific Data","topic":"Plant-Microbe Interactions and Immunity","field":"Agricultural and Biological Sciences","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":"The Scarborough Hospital; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Austrian Science Fund; National Science Foundation","keywords":"Arabidopsis; Leucine-rich repeat; Kinase; Signalling; Biology; Receptor; Computational biology; Extracellular; Cell biology; Gene; Genetics","score_opus":0.04508187148470579,"score_gpt":0.26960323848637335,"score_spread":0.22452136700166755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2915913218","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":[0.9898928,0.00006914606,0.00000608077,0.00027898655,0.00080799643,0.00014868761,0.008208516,0.000020505213,0.00056728884],"genre_scores_gemma":[0.9869848,0.000004452121,0.00015460089,0.0000048890524,0.00011677769,0.0000019429156,0.006082662,0.0000010103411,0.006648898],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987489,0.00008513043,0.00031123686,0.00043929694,0.00022718146,0.00018822662],"domain_scores_gemma":[0.99864364,0.00036162382,0.00022129984,0.0005912143,0.0001279773,0.000054271874],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00044111544,0.00010858098,0.00024147065,0.000039802308,0.00016338445,0.0000778898,0.001007185,0.000036431746,0.0019305707],"category_scores_gemma":[0.0000855328,0.00004758528,0.00008750216,0.0003638443,0.0001725903,0.0005013743,0.00046607386,0.0001502545,0.00049808214],"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":[0.000013198693,0.00022046102,0.004970294,0.000016005259,0.0000237245,3.561074e-7,0.00006726501,0.000001892136,0.9606461,0.000041028467,0.026189892,0.0078098034],"study_design_scores_gemma":[0.00016102278,0.00021694007,0.035308596,0.0001473367,0.000059035414,0.0000053219023,0.0010723387,0.00023289901,0.36194894,0.00011015209,0.6005037,0.00023374849],"about_ca_topic_score_codex":0.00040488498,"about_ca_topic_score_gemma":0.00021083374,"teacher_disagreement_score":0.5986971,"about_ca_system_score_codex":0.000016989716,"about_ca_system_score_gemma":0.000015229665,"threshold_uncertainty_score":0.9989818},"labels":[],"label_agreement":null},{"id":"W2929357616","doi":"10.1038/s41597-019-0038-1","title":"Statistically downscaled climate dataset for East Africa","year":2019,"lang":"en","type":"article","venue":"Scientific Data","topic":"Climate variability and models","field":"Environmental Science","cited_by":111,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Downscaling; Climate change; Climatology; Precipitation; Climate model; Environmental science; Scale (ratio); Representative Concentration Pathways; Projection (relational algebra); Tanzania; Geography; Environmental resource management; Physical geography; Meteorology; Cartography; Environmental planning; Computer science","score_opus":0.06660062009485934,"score_gpt":0.2906167723772865,"score_spread":0.22401615228242716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2929357616","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.051183194,0.000022669541,0.015587817,0.00090846396,0.0023340676,0.0017545167,0.9141075,0.00009565048,0.014006145],"genre_scores_gemma":[0.57162964,0.000011230641,0.063401625,0.00041689578,0.00009194143,0.0000831091,0.35703233,0.000052082472,0.0072811646],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99777424,0.0000368791,0.0002525959,0.0010706602,0.00037163988,0.00049399247],"domain_scores_gemma":[0.99692065,0.00010972574,0.00006239497,0.0027540273,0.000010806848,0.0001423817],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0021249806,0.00011542441,0.00014618921,0.000027038073,0.00025243816,0.0002691058,0.0015330834,0.000041667183,0.007825331],"category_scores_gemma":[0.00020770266,0.00009966756,0.000024376313,0.00022310273,0.0003552291,0.00063618895,0.0021456971,0.00006751803,0.007621373],"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":[0.000059127597,0.00022136096,0.0016563631,0.000074218806,0.000008152926,0.0000016924871,0.0001848517,0.00028757806,0.012557432,0.0018369589,0.9798534,0.0032588618],"study_design_scores_gemma":[0.0004390589,0.00003732716,0.0009015489,0.000012985534,0.000024950386,0.00000208687,0.000060702125,0.08078212,0.000054429045,0.0031228235,0.91435444,0.00020751993],"about_ca_topic_score_codex":0.0000360559,"about_ca_topic_score_gemma":0.00014507175,"teacher_disagreement_score":0.55707514,"about_ca_system_score_codex":0.000044053835,"about_ca_system_score_gemma":0.000021972099,"threshold_uncertainty_score":0.9931513},"labels":[],"label_agreement":null},{"id":"W2930808060","doi":"10.1038/s41597-019-0024-7","title":"Geo-referenced population-specific microsatellite data across American continents, the MacroPopGen Database","year":2019,"lang":"en","type":"article","venue":"Scientific Data","topic":"Genetic diversity and population structure","field":"Biochemistry, Genetics and Molecular Biology","cited_by":47,"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 Winnipeg; Golder Associates (Canada); BGC Engineering (Canada); Concordia University","funders":"Concordia University; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Biology; Fish migration; Microsatellite; Biodiversity; Genetic diversity; Population; Ecology; Intraspecific competition; Zoology; Allele; Demography; Genetics","score_opus":0.05393613729136078,"score_gpt":0.3173182112775451,"score_spread":0.26338207398618435,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2930808060","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":[0.9550625,0.00059179147,0.000365865,0.0003045053,0.0016508303,0.00033509874,0.041417688,0.000017064194,0.0002546723],"genre_scores_gemma":[0.78035855,0.00010916833,0.0013716278,0.00019123947,0.00014452863,0.0000012622975,0.21225196,0.000013000829,0.005558687],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99770653,0.00008823336,0.00024449333,0.0012549394,0.0003431015,0.0003626735],"domain_scores_gemma":[0.9928875,0.000015443607,0.0001741291,0.0067362366,0.000096290474,0.000090389636],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008022444,0.00016966408,0.00014939807,0.00003054705,0.00044603125,0.00046276886,0.0038255681,0.000063428204,0.00032805983],"category_scores_gemma":[0.0000620583,0.00013130672,0.000033390894,0.000308073,0.00038437557,0.000041193365,0.0042581107,0.00012027237,0.000405379],"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":[0.00015712183,0.00008350872,0.13996243,0.000036204972,0.00012978878,0.0000036565184,0.00029788117,0.00008590946,0.30085897,0.00024096805,0.5165897,0.041553874],"study_design_scores_gemma":[0.00031374552,0.000016936361,0.079736054,0.000007696442,0.000015396337,0.0000060468797,0.00035664524,0.00020859615,0.0026933397,0.00002959776,0.9164139,0.00020202459],"about_ca_topic_score_codex":0.00035669905,"about_ca_topic_score_gemma":0.000520827,"teacher_disagreement_score":0.39982423,"about_ca_system_score_codex":0.0000069879275,"about_ca_system_score_gemma":0.00004664205,"threshold_uncertainty_score":0.7108921},"labels":[],"label_agreement":null},{"id":"W2936362429","doi":"10.1038/s41597-019-0016-7","title":"Physical activity, sleep and cardiovascular health data for 50,000 individuals from the MyHeart Counts Study","year":2019,"lang":"en","type":"article","venue":"Scientific Data","topic":"Physical Activity and Health","field":"Medicine","cited_by":82,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ted Rogers Centre for Heart Research","funders":"U.S. National Library of Medicine","keywords":"Cardiovascular health; Physical activity; Scale (ratio); Gerontology; Data collection; Physical fitness; Sleep (system call); Medicine; Cardiovascular fitness; Health data; Psychology; Physical therapy; Health care; Disease; Computer science","score_opus":0.16373391544128407,"score_gpt":0.3929367127110389,"score_spread":0.22920279726975484,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2936362429","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":[0.96631026,0.00035754414,0.00017200183,0.002427167,0.000775542,0.0018571854,0.027774973,0.00003366482,0.00029165173],"genre_scores_gemma":[0.9940557,0.00001296622,0.00015464211,0.00026018347,0.00039793007,0.000010102259,0.0047011985,0.00001303197,0.00039426374],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980741,0.00011481918,0.000102373415,0.000881601,0.0005684886,0.00025859918],"domain_scores_gemma":[0.9952191,0.00026111884,0.000050317703,0.0043085013,0.000030059029,0.00013087502],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001997219,0.0001004437,0.00040182073,0.000026233523,0.0002677434,0.00014014436,0.0007916998,0.000025554962,0.00004911213],"category_scores_gemma":[0.00011714993,0.000067130066,0.00004345261,0.00016276828,0.00013447211,0.00039363833,0.001174604,0.0001929642,0.00020396578],"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":[0.00012824887,0.0053389687,0.019890506,0.00028015763,0.0010741245,0.000002977809,0.0018032291,0.0000017592131,0.000583413,0.00021632205,0.76435536,0.20632493],"study_design_scores_gemma":[0.0016103102,0.00035405273,0.10255821,0.000063088264,0.00029189535,0.0000030837798,0.00043496498,0.0053048516,0.00004481339,0.0004535994,0.8887283,0.00015282033],"about_ca_topic_score_codex":0.00063019665,"about_ca_topic_score_gemma":0.00007007371,"teacher_disagreement_score":0.20617211,"about_ca_system_score_codex":0.000019595012,"about_ca_system_score_gemma":0.00020202543,"threshold_uncertainty_score":0.27374846},"labels":[],"label_agreement":null},{"id":"W2937999720","doi":"10.1038/s41597-019-0034-5","title":"A statistical atlas of cerebral arteries generated using multi-center MRA datasets from healthy subjects","year":2019,"lang":"en","type":"article","venue":"Scientific Data","topic":"Cerebrovascular and Carotid Artery Diseases","field":"Medicine","cited_by":75,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Brain Institute; University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Government of Canada","keywords":"Magnetic resonance imaging; Neuroimaging; Magnetic resonance angiography; Cerebral arteries; Atlas (anatomy); Medicine; Radiology; Computer science; Anatomy","score_opus":0.06136679331602411,"score_gpt":0.3246087648774315,"score_spread":0.2632419715614074,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2937999720","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":[0.86072713,0.00010985882,0.00097597326,0.000052706517,0.0010598255,0.0003884987,0.13662231,0.000029628774,0.00003404383],"genre_scores_gemma":[0.80128044,0.0000049584814,0.005177098,0.000170315,0.00008475073,0.0000022541483,0.19311006,0.000018902832,0.000151199],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9979368,0.00009034661,0.0003401748,0.0008233412,0.0004833329,0.00032601063],"domain_scores_gemma":[0.9971669,0.000041768675,0.0001174894,0.0023409687,0.00008689358,0.00024599192],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003046507,0.00015543969,0.00033822985,0.00010515509,0.0001034896,0.00013143984,0.00042916794,0.000044860975,0.0015486868],"category_scores_gemma":[0.00013413485,0.00013273048,0.00005877173,0.00023602862,0.00028560933,0.00034371874,0.0004625301,0.00010327794,0.00029929396],"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":[0.0007427537,0.0037641884,0.689714,0.0007611788,0.00049654226,0.000057007637,0.00057812536,0.000013475357,0.06904531,0.00013552066,0.23058565,0.004106232],"study_design_scores_gemma":[0.027674409,0.00066103594,0.68864995,0.00095810986,0.0012019947,0.00018184728,0.0018165199,0.09034378,0.015020056,0.00008829739,0.17214087,0.0012631037],"about_ca_topic_score_codex":0.0003500865,"about_ca_topic_score_gemma":0.00018444708,"teacher_disagreement_score":0.09033031,"about_ca_system_score_codex":0.00003079747,"about_ca_system_score_gemma":0.00033276773,"threshold_uncertainty_score":0.999364},"labels":[],"label_agreement":null},{"id":"W2942802270","doi":"10.1038/s41597-019-0040-7","title":"A long-term dataset of lake surface water temperature over the Tibetan Plateau derived from AVHRR 1981–2015","year":2019,"lang":"en","type":"article","venue":"Scientific Data","topic":"Urban Heat Island Mitigation","field":"Environmental Science","cited_by":51,"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 Oceanic and Atmospheric Administration; National Natural Science Foundation of China; Canada Excellence Research Chairs, Government of Canada; University of Reading","keywords":"Plateau (mathematics); Term (time); Environmental science; Surface water; Remote sensing; Climatology; Physical geography; Geography; Geology; Mathematics; Physics","score_opus":0.01800691870223713,"score_gpt":0.244610230621266,"score_spread":0.22660331191902885,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2942802270","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":[0.93501174,0.00003883341,0.000010264175,0.00018883245,0.00087745604,0.00033917182,0.06330508,0.000017851513,0.00021079107],"genre_scores_gemma":[0.869842,0.0000034436482,0.00019083804,0.000097888886,0.000030967345,0.000001838921,0.12656868,0.000012385414,0.003251984],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99800736,0.00008266481,0.00025120645,0.0007884055,0.000558981,0.00031140668],"domain_scores_gemma":[0.99676216,0.00005093083,0.00007549902,0.0030216933,0.000010771938,0.000078960205],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0008140562,0.00014689555,0.00015027197,0.000020897824,0.00017323524,0.00021906002,0.0017167618,0.000073247764,0.012935014],"category_scores_gemma":[0.000022128237,0.000083668616,0.000026505637,0.00019841167,0.00041334043,0.0008317147,0.0015320439,0.00015356757,0.004311084],"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":[0.000013490625,0.00004431984,0.17335768,0.000007970403,0.000016495704,0.000003819092,0.00043087098,0.000060386275,0.45841575,0.000001927033,0.36748102,0.00016626189],"study_design_scores_gemma":[0.00074674765,0.000030294737,0.7224203,0.000050588045,0.00006528963,0.000005985416,0.000088732326,0.0011453931,0.10551035,0.00011442174,0.16947018,0.0003517792],"about_ca_topic_score_codex":0.00039841718,"about_ca_topic_score_gemma":0.0051986845,"teacher_disagreement_score":0.54906255,"about_ca_system_score_codex":0.000032713662,"about_ca_system_score_gemma":0.000020978832,"threshold_uncertainty_score":0.9964642},"labels":[],"label_agreement":null},{"id":"W2944268392","doi":"10.1038/s41597-019-0069-7","title":"Worldwide measurements of bioturbation intensity, ventilation rate, and the mixing depth of marine sediments","year":2019,"lang":"en","type":"article","venue":"Scientific Data","topic":"Marine Biology and Ecology Research","field":"Earth and Planetary Sciences","cited_by":94,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"Natural Environment Research Council; Research Councils UK; Sight Research UK","keywords":"Bioturbation; Biogeochemical cycle; Environmental science; Ecology; Ecosystem engineer; Ecosystem; Burrow; Oceanography; Sediment; Paleolimnology; Intertidal zone; Marine ecosystem; Climate change; Geology; Biology; Geomorphology","score_opus":0.0681339636167772,"score_gpt":0.2746749684645114,"score_spread":0.2065410048477342,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2944268392","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":[0.9951148,0.000083889114,0.0000072860275,0.00013173831,0.0008243407,0.00022938108,0.00009621991,0.0000039065967,0.0035084116],"genre_scores_gemma":[0.996058,0.0000069376656,0.00013469295,0.000020088864,0.00001095909,2.444258e-7,0.0022536463,7.7836415e-7,0.0015146696],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99914014,0.00012622778,0.00017639418,0.00025009867,0.00018229193,0.00012484685],"domain_scores_gemma":[0.99917626,0.000120261975,0.00011159859,0.0004794062,0.00008737156,0.000025112062],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003679111,0.000047092362,0.00012036636,0.00008768746,0.00010095739,0.000029600724,0.00042681664,0.000031612017,0.0010961479],"category_scores_gemma":[0.00019561472,0.000029985033,0.0000133526955,0.00022416636,0.00039658116,0.00019884782,0.0002741738,0.00006568115,0.00006262749],"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":[0.00018588977,0.00000892685,0.98974067,0.000021481204,0.000021404381,1.5365201e-7,0.00003676825,0.00001750288,0.0006112706,0.00001099516,0.0009805438,0.008364378],"study_design_scores_gemma":[0.00042523953,0.000024715073,0.9919106,0.0000095278965,0.000011461848,0.0000012234366,0.000028645389,0.005276349,0.0014470394,0.00030936982,0.0005248999,0.000030949486],"about_ca_topic_score_codex":0.0005887915,"about_ca_topic_score_gemma":0.002846103,"teacher_disagreement_score":0.008333428,"about_ca_system_score_codex":0.0000015714555,"about_ca_system_score_gemma":0.0000333344,"threshold_uncertainty_score":0.999817},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"observational","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W2950886245","doi":"10.1038/sdata.2018.142","title":"A multi-omic atlas of the human frontal cortex for aging and Alzheimer’s disease research","year":2018,"lang":"en","type":"article","venue":"Scientific Data","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":688,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Institute of Environmental Health Sciences; National Institute on Aging; National Institutes of Health; National Center for Research Resources; Broad Institute","keywords":"Dementia; Biology; Dorsolateral prefrontal cortex; Histone; Cognitive decline; Neuroscience; Alzheimer's disease; Biomarker; Disease; Prefrontal cortex; Computational biology; Genetics; Bioinformatics; Cognition; Medicine; Gene; Internal medicine","score_opus":0.10791270952260082,"score_gpt":0.3747868602896041,"score_spread":0.26687415076700327,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950886245","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":[0.9877251,0.002101774,0.0023598531,0.00037460378,0.001262376,0.0008799248,0.0048993872,0.000006586793,0.0003904025],"genre_scores_gemma":[0.9954665,0.000007783878,0.0014019007,0.000042435164,0.00019039895,0.000006620783,0.0016543868,0.000007988578,0.001221999],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991477,0.000028859755,0.00014633614,0.0003436797,0.00012598556,0.00020743698],"domain_scores_gemma":[0.9984988,0.0000099288545,0.000057238714,0.001252909,0.00010876343,0.000072378425],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010261046,0.00006129961,0.000061679144,0.000027810705,0.00046143794,0.00009089709,0.00078590185,0.00003843705,0.000009352568],"category_scores_gemma":[0.000061754225,0.000044687204,0.000027584088,0.00007593916,0.00088125956,0.0000072965513,0.0012978015,0.000055187484,0.0000051550583],"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":[0.00007261429,0.00010469685,0.0029615154,0.00005924756,0.00009962804,3.9574934e-7,0.00034237886,0.0000024780163,0.5035619,0.00040727208,0.48194242,0.01044546],"study_design_scores_gemma":[0.002458186,0.00026396866,0.049171247,0.00013759667,0.0001807132,0.0000072553094,0.00065558724,0.05764876,0.06385111,0.0018887781,0.82321805,0.0005187515],"about_ca_topic_score_codex":0.000020735604,"about_ca_topic_score_gemma":0.00022436182,"teacher_disagreement_score":0.43971077,"about_ca_system_score_codex":0.0000035652047,"about_ca_system_score_gemma":0.00008989121,"threshold_uncertainty_score":0.35490543},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W2951103577","doi":"10.1038/sdata.2016.44","title":"The brain imaging data structure, a format for organizing and describing outputs of neuroimaging experiments","year":2016,"lang":"en","type":"article","venue":"Scientific Data","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":1910,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Montreal Neurological Institute and Hospital","funders":"National Institute on Alcohol Abuse and Alcoholism; European Regional Development Fund; National Institute of General Medical Sciences; National Institute of Mental Health; Medical Research Council; Center for Behavioral Brain Sciences; National Institute of Biomedical Imaging and Bioengineering; Wellcome Trust; National Institutes of Health; Laura and John Arnold Foundation; National Science Foundation","keywords":"Computer science; Neuroimaging; Metadata; Data sharing; Software; Field (mathematics); File format; Functional magnetic resonance imaging; Information retrieval; Artificial intelligence; Data mining; Data science; Database; World Wide Web; Programming language","score_opus":0.37461250903114907,"score_gpt":0.4171929214087385,"score_spread":0.042580412377589416,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2951103577","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":[0.1827933,0.0026368755,0.74034476,0.018455517,0.020638185,0.0018395642,0.032485183,0.00023015436,0.00057643215],"genre_scores_gemma":[0.985862,0.0000069601315,0.010874346,0.00019367212,0.000104779225,0.0000030328451,0.0008861596,0.000022367582,0.0020466417],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99506176,0.00014856181,0.0007867189,0.0020828154,0.001399791,0.000520381],"domain_scores_gemma":[0.98633856,0.0026163019,0.000419711,0.0102031715,0.00029619527,0.00012606243],"candidate_categories":["metaresearch","sts","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.017306263,0.00016628459,0.00020925132,0.00029078423,0.0014014457,0.003643148,0.009571965,0.000017078406,0.00003227778],"category_scores_gemma":[0.014607319,0.000086613945,0.000029053721,0.000900101,0.00071784924,0.002864442,0.014208091,0.00006040803,0.000024227711],"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":[0.000011937823,0.000012855448,0.0014541924,0.0000067083242,0.000010423734,0.0000012400394,0.0002939908,0.000001043953,0.019208327,0.0008636277,0.49670374,0.4814319],"study_design_scores_gemma":[0.0010515761,0.000016321825,0.0016796009,0.0001538734,0.000034128567,0.000021757374,0.0031345377,0.10516362,0.0054458445,0.011782772,0.87116826,0.00034771915],"about_ca_topic_score_codex":0.000020156958,"about_ca_topic_score_gemma":0.0000519922,"teacher_disagreement_score":0.80306876,"about_ca_system_score_codex":0.000020802197,"about_ca_system_score_gemma":0.00009439235,"threshold_uncertainty_score":0.9998986},"labels":[],"label_agreement":null},{"id":"W2952906091","doi":"10.1038/sdata.2014.54","title":"A high resolution 7-Tesla resting-state fMRI test-retest dataset with cognitive and physiological measures","year":2015,"lang":"en","type":"article","venue":"Scientific Data","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":61,"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":"Max-Planck-Gesellschaft","keywords":"Resting state fMRI; Functional magnetic resonance imaging; Cognition; Prefrontal cortex; Session (web analytics); Psychology; Audiology; Computer science; Neuroscience; Cognitive psychology; Medicine","score_opus":0.2342273660817456,"score_gpt":0.3202344923102148,"score_spread":0.08600712622846918,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2952906091","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":[0.80894136,0.00033465726,0.0012118445,0.0067063957,0.0019369995,0.00118637,0.17839709,0.00043527075,0.00085000606],"genre_scores_gemma":[0.9921173,0.000007802725,0.00084066734,0.0008131124,0.00009169286,0.000023608396,0.0054830085,0.000014787425,0.000608054],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99692464,0.00022898502,0.00017136206,0.0015930168,0.0007229544,0.00035903556],"domain_scores_gemma":[0.9944163,0.0039610635,0.0001220162,0.0011215732,0.00020492627,0.00017411949],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0016291029,0.00018164447,0.00018539367,0.00010004562,0.00064319867,0.0003677974,0.0006562638,0.000032864296,0.000008722717],"category_scores_gemma":[0.07220954,0.00013241054,0.000009913118,0.0006431662,0.0016959673,0.0008109835,0.0014460323,0.00018879659,0.00013305989],"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":[0.00025507994,0.00021272493,0.0013402425,0.000017141316,0.000013559004,0.00006930448,0.00019005347,0.000065059285,0.04591766,0.0002078512,0.9499412,0.0017701103],"study_design_scores_gemma":[0.014536306,0.0064280047,0.15458886,0.0011614186,0.00051681773,0.0010372514,0.003082663,0.040010728,0.11696991,0.03130136,0.62586796,0.004498714],"about_ca_topic_score_codex":0.0000916127,"about_ca_topic_score_gemma":0.0001880598,"teacher_disagreement_score":0.32407326,"about_ca_system_score_codex":0.000032850246,"about_ca_system_score_gemma":0.00014777233,"threshold_uncertainty_score":0.93560565},"labels":[],"label_agreement":null},{"id":"W2953143431","doi":"10.1038/sdata.2017.147","title":"Linking FANTOM5 CAGE peaks to annotations with CAGEscan","year":2017,"lang":"en","type":"article","venue":"Scientific Data","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":21,"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":"RIKEN; Australian Research Council; Ministry of Education, Culture, Sports, Science and Technology; Conquer Cancer Foundation","keywords":"Cage; Computer science; Biology; Combinatorics; Mathematics","score_opus":0.046579806632690866,"score_gpt":0.3092296791531692,"score_spread":0.26264987252047833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2953143431","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":[0.943608,0.00026527434,0.035099097,0.0018837919,0.0019550438,0.00073742575,0.0039971224,0.000043406522,0.01241085],"genre_scores_gemma":[0.9779345,0.0000060370994,0.009378566,0.00012358328,0.00017830727,0.000016103986,0.0021858392,0.000017077,0.010159978],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99882466,0.000026235359,0.0000971991,0.0006475511,0.00018528067,0.0002190884],"domain_scores_gemma":[0.99625194,0.000004862222,0.00007995617,0.003483932,0.00007302196,0.000106289575],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00060564827,0.000095020034,0.000076389224,0.000041495026,0.0009276009,0.00065208,0.0017337081,0.00004878726,0.000035174096],"category_scores_gemma":[0.00019790605,0.000078911115,0.000018156645,0.00005848272,0.00013537129,0.000019038613,0.00080007827,0.000041037176,0.00007513193],"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":[0.00002115682,0.000021909838,0.0006201565,0.000009379509,0.000018499692,0.000007497963,0.000113190785,0.000007249954,0.95520407,0.00013152594,0.02039577,0.023449589],"study_design_scores_gemma":[0.0001917779,0.00008703984,0.0025328435,0.00005048973,0.00001936969,0.000009707312,0.00011313551,0.000060469905,0.4219514,0.00011301799,0.57463455,0.00023617665],"about_ca_topic_score_codex":0.0000680999,"about_ca_topic_score_gemma":0.00092321954,"teacher_disagreement_score":0.5542388,"about_ca_system_score_codex":0.0000044235658,"about_ca_system_score_gemma":0.00009517183,"threshold_uncertainty_score":0.713445},"labels":[],"label_agreement":null},{"id":"W2954654581","doi":"10.1038/s41597-019-0105-7","title":"iEEG-BIDS, extending the Brain Imaging Data Structure specification to human intracranial electrophysiology","year":2019,"lang":"en","type":"article","venue":"Scientific Data","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":181,"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":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek; National Institute of Neurological Disorders and Stroke; National Institute of Mental Health; Whitehall Foundation; Gordon and Betty Moore Foundation; Horizon 2020 Framework Programme; Alfred P. Sloan Foundation; European Commission; Alan Turing Institute; National Institutes of Health; National Science Foundation","keywords":"Computer science; Metadata; Data sharing; Neuroinformatics; Human brain; Neuroscience; Artificial intelligence; Data science; Psychology; World Wide Web","score_opus":0.07157132679559527,"score_gpt":0.3255467582382028,"score_spread":0.2539754314426075,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2954654581","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":[0.92996377,0.00010824153,0.0015722488,0.046156872,0.009952971,0.0013071343,0.009639444,0.00022244162,0.0010768794],"genre_scores_gemma":[0.9922671,0.0000027914352,0.00037286695,0.0030505839,0.000535458,0.000005755731,0.0018995738,0.000023066441,0.0018428053],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9963106,0.00022816827,0.00023639691,0.0022265362,0.0005383971,0.00045989014],"domain_scores_gemma":[0.9923549,0.0015303222,0.00011607243,0.005874605,0.000059605867,0.00006443864],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012989439,0.00017492175,0.00016740721,0.00015442651,0.0011418482,0.0005606381,0.0048529697,0.000030672036,0.00037552166],"category_scores_gemma":[0.0067085032,0.00013166951,0.000021836757,0.0008612495,0.00039299525,0.001014495,0.0037509347,0.00028535712,0.0007068347],"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":[0.000014331012,0.000017577253,0.00014384875,0.0000050224053,0.0000039034853,0.0000025746165,0.00007366703,0.000016077227,0.7453235,0.0026228272,0.24695922,0.0048174695],"study_design_scores_gemma":[0.0004708203,0.000082311,0.021666976,0.00002937226,0.00002549151,0.00007621145,0.0003175306,0.012588127,0.046403486,0.00835125,0.9094416,0.0005468467],"about_ca_topic_score_codex":0.000030554133,"about_ca_topic_score_gemma":0.00013652847,"teacher_disagreement_score":0.69892,"about_ca_system_score_codex":0.000060737504,"about_ca_system_score_gemma":0.00007491979,"threshold_uncertainty_score":0.90851665},"labels":[],"label_agreement":null},{"id":"W2955660171","doi":"10.1038/s41597-019-0122-6","title":"A high-resolution gridded dataset to assess electrification in sub-Saharan Africa","year":2019,"lang":"en","type":"article","venue":"Scientific Data","topic":"Impact of Light on Environment and Health","field":"Environmental Science","cited_by":121,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"Ministero dell’Istruzione, dell’Università e della Ricerca; International Institute for Applied Systems Analysis; Università degli Studi di Milano","keywords":"Electrification; Electricity; Rural electrification; Consistency (knowledge bases); Benchmarking; Data quality; Sustainability; Environmental economics; Consumption (sociology); Quality (philosophy); Computer science; Database; Geography; Business; Service (business); Economics","score_opus":0.06913132960950415,"score_gpt":0.2948649510468915,"score_spread":0.22573362143738734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2955660171","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":[0.9850448,0.000117483425,0.0007337351,0.001699407,0.0011755155,0.0011568413,0.008466328,0.00005018894,0.0015557345],"genre_scores_gemma":[0.97174245,0.000032599066,0.0013543017,0.00020697244,0.000042591477,0.000017040504,0.025351755,0.000014792675,0.0012374943],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99734783,0.00009613021,0.0003016069,0.0009721272,0.00064593425,0.0006363991],"domain_scores_gemma":[0.9974288,0.000028443432,0.000093503695,0.0022268025,0.0000034827488,0.0002190134],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0025120936,0.00013742226,0.00015788856,0.00014672194,0.00017303052,0.00017155355,0.0014095416,0.000057965164,0.0021155959],"category_scores_gemma":[0.000079991296,0.00012981899,0.000014318305,0.00082293263,0.000107484586,0.0010491244,0.0005103659,0.0001469197,0.017663654],"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":[0.000042115807,0.00022612163,0.012389218,0.000011469371,0.00000290416,0.0000024773938,0.00013092635,0.00023456773,0.20912142,0.000047665562,0.7744526,0.0033385186],"study_design_scores_gemma":[0.00044136884,0.000069027374,0.30662265,0.000021508255,0.00000769289,0.0000015708057,0.000021647635,0.0017041832,0.005956655,0.00014979906,0.6847483,0.00025559682],"about_ca_topic_score_codex":0.0003438136,"about_ca_topic_score_gemma":0.00048742877,"teacher_disagreement_score":0.29423344,"about_ca_system_score_codex":0.00031639915,"about_ca_system_score_gemma":0.000041324216,"threshold_uncertainty_score":0.9987966},"labels":[],"label_agreement":null},{"id":"W2957869398","doi":"10.1038/s41597-019-0129-z","title":"A macaque connectome for large-scale network simulations in TheVirtualBrain","year":2019,"lang":"en","type":"article","venue":"Scientific Data","topic":"Advanced Neuroimaging Techniques and Applications","field":"Medicine","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; Western University; McGill University; Montreal Neurological Institute and Hospital; Baycrest Hospital","funders":"Deutsche Forschungsgemeinschaft; European Commission","keywords":"Connectome; Macaque; Connectomics; Tractography; Computer science; Human Connectome Project; Diffusion MRI; Resting state fMRI; Neuroscience; Scale (ratio); Tracing; Functional connectivity; Biology; Cartography; Magnetic resonance imaging; Geography; Medicine","score_opus":0.11977953947096279,"score_gpt":0.40320857664028026,"score_spread":0.28342903716931744,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2957869398","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":[0.46374643,0.00029813894,0.47080383,0.01952008,0.001873104,0.010949339,0.026295828,0.0009458935,0.0055673723],"genre_scores_gemma":[0.92846876,0.0000042135844,0.05539212,0.00075448223,0.00010824061,0.00006688171,0.007914145,0.000026034872,0.0072651347],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988854,0.000013232086,0.00017277809,0.00055447133,0.00011659417,0.00025750176],"domain_scores_gemma":[0.9979852,0.00015764807,0.00004584052,0.0017121789,0.00004497892,0.000054146603],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042749848,0.00007236912,0.00013795464,0.00008157236,0.00011068147,0.000045565932,0.00038176423,0.000029833594,0.0001442161],"category_scores_gemma":[0.00012699228,0.00006555736,0.000025604335,0.00049575715,0.000047843638,0.00016051457,0.00025849932,0.000100921534,0.000071224305],"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":[0.00024326751,0.0013109051,0.089604825,0.000327893,0.000042292224,0.000011787442,0.00080626237,0.004495553,0.056058254,0.07724255,0.75785035,0.012006036],"study_design_scores_gemma":[0.0008664419,0.000034438955,0.0027927777,0.00007383483,0.000015779326,0.0000050971344,0.00005266476,0.1877115,0.0003119431,0.009766649,0.7982579,0.000110987035],"about_ca_topic_score_codex":0.0000031804746,"about_ca_topic_score_gemma":0.000044106502,"teacher_disagreement_score":0.4647223,"about_ca_system_score_codex":0.000019462834,"about_ca_system_score_gemma":0.00004922492,"threshold_uncertainty_score":0.26733515},"labels":[],"label_agreement":null},{"id":"W2962754235","doi":"10.1038/s41597-019-0217-0","title":"An accurate registration of the BigBrain dataset with the MNI PD25 and ICBM152 atlases","year":2019,"lang":"en","type":"article","venue":"Scientific Data","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":81,"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; Western University","funders":"Canadian Institutes of Health Research","keywords":"Computer science; Segmentation; Brain atlas; Atlas (anatomy); Image registration; Magnetic resonance imaging; Artificial intelligence; Brain mapping; Pattern recognition (psychology); Neuroscience; Medicine; Biology; Anatomy; Radiology; Image (mathematics)","score_opus":0.037542854995450604,"score_gpt":0.3138715182451634,"score_spread":0.2763286632497128,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2962754235","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":[0.07382153,0.000105369145,0.89685076,0.012455628,0.0012045024,0.0015638696,0.013087067,0.00020482074,0.00070645986],"genre_scores_gemma":[0.89339906,0.000016856418,0.086347416,0.002268535,0.000071417395,0.000024465538,0.01469193,0.000017670065,0.0031626746],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99853754,0.0001449842,0.0001583458,0.0005235331,0.00051186926,0.00012372503],"domain_scores_gemma":[0.99555665,0.00009059513,0.00016941999,0.0040797247,0.000053561704,0.000050057417],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001782886,0.000070996124,0.0000710275,0.00003947717,0.00017994136,0.0006238033,0.003547199,0.000018178976,0.000033259148],"category_scores_gemma":[0.00012670452,0.000034397854,0.0000073998,0.00047835233,0.0004596743,0.0017339688,0.00093976076,0.00007960734,0.000017426135],"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":[0.0000073805722,0.00007026123,0.0003187941,0.000032716394,0.000010426809,0.0000020475343,0.0004408503,0.000005993551,0.044903427,0.0025474823,0.906198,0.0454626],"study_design_scores_gemma":[0.0017137737,0.0006572783,0.024563378,0.0003814541,0.00009130696,0.00009864792,0.0020621563,0.16350037,0.44190848,0.0035847246,0.36045286,0.0009855803],"about_ca_topic_score_codex":0.000058230682,"about_ca_topic_score_gemma":0.00011857165,"teacher_disagreement_score":0.8195775,"about_ca_system_score_codex":0.0000058733913,"about_ca_system_score_gemma":0.00011059917,"threshold_uncertainty_score":0.6591637},"labels":[],"label_agreement":null},{"id":"W2968251458","doi":"10.1038/s41597-019-0150-2","title":"MOD-LSP, MODIS-based parameters for hydrologic modeling of North American land cover change","year":2019,"lang":"en","type":"article","venue":"Scientific Data","topic":"Remote Sensing in Agriculture","field":"Environmental Science","cited_by":21,"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 Science Foundation","keywords":"Land cover; Environmental science; Cover (algebra); Remote sensing; Physical geography; Geography; Hydrology (agriculture); Land use; Ecology; Geology; Biology","score_opus":0.06376587501712246,"score_gpt":0.25469549726520796,"score_spread":0.19092962224808552,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2968251458","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":[0.9934837,0.000009137473,0.003463372,0.0001612733,0.00045747185,0.0006120417,0.001409336,0.000031631702,0.00037201346],"genre_scores_gemma":[0.9856497,0.0000016487371,0.011885616,0.00017770442,0.000019408479,0.0000034178142,0.0018579928,0.0000108359545,0.00039367782],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99823576,0.000034958663,0.00019295282,0.00079586793,0.00041467135,0.00032577544],"domain_scores_gemma":[0.9982125,0.000055001907,0.00014720738,0.0014875224,0.000017797267,0.00007997964],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046333243,0.00013561881,0.0001987715,0.000043373093,0.00010511106,0.000076655226,0.0010190099,0.000030851363,0.00006834448],"category_scores_gemma":[0.0000646207,0.000098950964,0.000050751773,0.0005073392,0.0003766924,0.00033585797,0.00044492533,0.0000793428,0.00032782258],"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":[0.000055626853,0.00012431864,0.12750053,0.000036079033,0.000016469894,0.0000015936905,0.00017803178,0.845246,0.0034891814,0.0000023112552,0.013160376,0.010189472],"study_design_scores_gemma":[0.00021275383,0.000057761623,0.015468169,0.0000095086425,0.000016399063,8.826218e-7,0.00001146077,0.9798406,0.00020842845,0.00003568371,0.0039913515,0.00014700841],"about_ca_topic_score_codex":0.00068973924,"about_ca_topic_score_gemma":0.0006841045,"teacher_disagreement_score":0.13459459,"about_ca_system_score_codex":0.00005162795,"about_ca_system_score_gemma":0.000012870435,"threshold_uncertainty_score":0.42136052},"labels":[],"label_agreement":null},{"id":"W2971384141","doi":"10.1038/s41597-019-0174-7","title":"Creating reproducible pharmacogenomic analysis pipelines","year":2019,"lang":"en","type":"article","venue":"Scientific Data","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; Institute of Cancer Research; Ontario Institute for Cancer Research; University Health Network; University of Toronto; Princess Margaret Cancer Centre","funders":"","keywords":"Workflow; Computer science; Pipeline (software); Scalability; Identifier; Pharmacogenomics; Data science; Process (computing); Pipeline transport; Metadata; Data access; Data mining; Database; Bioinformatics; World Wide Web; Engineering; Biology; Programming language","score_opus":0.2945933816599378,"score_gpt":0.45496221309025664,"score_spread":0.16036883143031883,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2971384141","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":[0.8906768,0.00048018564,0.025003215,0.0014948403,0.021608312,0.00081476977,0.005012644,0.00035784664,0.054551374],"genre_scores_gemma":[0.82314986,0.0000026375494,0.0057053054,0.00014468454,0.00022501263,0.0000029092796,0.003326207,0.000012442164,0.16743092],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9909285,0.00022801236,0.0009934818,0.0047883485,0.0025412233,0.0005204833],"domain_scores_gemma":[0.97978014,0.00067302864,0.0004183377,0.018531516,0.00041407245,0.00018293234],"candidate_categories":["metaresearch","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.03717489,0.00018590002,0.00040094176,0.0015176622,0.00063994847,0.004636749,0.008942363,0.000032821456,0.0061775814],"category_scores_gemma":[0.005176694,0.00014162085,0.00016381437,0.009607575,0.00021587062,0.0013385954,0.006229327,0.00012687134,0.0149624],"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":[0.000012638025,0.000097427765,0.038173098,0.0000075144903,0.0001767453,0.0000060320667,0.00031777692,0.0033939057,0.0033419926,0.000305841,0.8785423,0.07562474],"study_design_scores_gemma":[0.00022706458,0.000008281445,0.006707884,0.000007983482,0.00020324043,0.0000021861936,0.00070400717,0.29381862,0.00050275866,0.0011270375,0.69645077,0.00024015708],"about_ca_topic_score_codex":0.00012058969,"about_ca_topic_score_gemma":0.00008136827,"teacher_disagreement_score":0.2904247,"about_ca_system_score_codex":0.000033165634,"about_ca_system_score_gemma":0.00012316398,"threshold_uncertainty_score":0.9964197},"labels":[],"label_agreement":null},{"id":"W2980534007","doi":"10.1038/s41597-019-0213-4","title":"The FluPRINT dataset, a multidimensional analysis of the influenza vaccine imprint on the immune system","year":2019,"lang":"en","type":"article","venue":"Scientific Data","topic":"Influenza Virus Research Studies","field":"Medicine","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Infection and Immunity","funders":"National Center for Advancing Translational Sciences; National Center for Research Resources; National Institutes of Health; National Institute of Allergy and Infectious Diseases; European Commission; Georgia Clinical and Translational Science Alliance; Howard Hughes Medical Institute","keywords":"Immunogenicity; Influenza vaccine; Immune system; Immunology; Biology; Computational biology; Immunity; Vaccination; Virology","score_opus":0.10350322837359491,"score_gpt":0.38000786687867,"score_spread":0.2765046385050751,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2980534007","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":[0.9655462,0.001996944,0.000016447344,0.004644925,0.0017037103,0.002391923,0.022660105,0.00004829859,0.0009914652],"genre_scores_gemma":[0.9956956,0.00002193766,0.00009138255,0.0003993163,0.000048343303,0.000036195474,0.002180299,0.000017049593,0.0015098779],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9965963,0.00025319762,0.0005670564,0.00069137214,0.0014714487,0.00042063984],"domain_scores_gemma":[0.98967886,0.00080815365,0.0002469012,0.008851115,0.00033892682,0.00007607273],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0056968345,0.00017631326,0.0003936313,0.00020370753,0.0008986854,0.00013015102,0.0024257058,0.000040621315,0.00018156038],"category_scores_gemma":[0.0015957423,0.000067346125,0.00016946039,0.0018002936,0.0004901632,0.0001123314,0.004713741,0.0003768232,0.00048774216],"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":[0.0031011286,0.0012757428,0.09291472,0.0009618826,0.021298472,0.00003500992,0.00206606,0.0027869178,0.35015896,0.061975624,0.45043457,0.01299093],"study_design_scores_gemma":[0.0015579817,0.00009105025,0.38269427,0.00034045166,0.0013065332,0.000007912724,0.0018060817,0.041870438,0.020307483,0.000017239212,0.5497927,0.00020785508],"about_ca_topic_score_codex":0.00033756928,"about_ca_topic_score_gemma":0.00016417648,"teacher_disagreement_score":0.32985148,"about_ca_system_score_codex":0.000111949164,"about_ca_system_score_gemma":0.00022403065,"threshold_uncertainty_score":0.69120526},"labels":[],"label_agreement":null},{"id":"W2981232846","doi":"10.1038/s41597-019-0181-8","title":"Bile acids targeted metabolomics and medication classification data in the ADNI1 and ADNIGO/2 cohorts","year":2019,"lang":"en","type":"article","venue":"Scientific Data","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":28,"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; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; Northern California Institute for Research and Education; University of California, San Diego; Pfizer; Biogen; BioClinica; F. Hoffmann-La Roche; University of Southern California; Novartis Pharmaceuticals Corporation; U.S. Department of Defense; Eli Lilly and Company; Bristol-Myers Squibb; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; Alzheimer's Association; National Institutes of Health; U.S. Department of Health and Human Services; Foundation for the National Institutes of Health","keywords":"Metabolomics; Disease; Dementia; Mechanism (biology); Alzheimer's Disease Neuroimaging Initiative; Neuroimaging; Cohort; Bioinformatics; Medicine; Computational biology; Biology; Internal medicine; Neuroscience","score_opus":0.03761647439491405,"score_gpt":0.2914497505758763,"score_spread":0.25383327618096224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2981232846","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":[0.98797315,0.006960973,0.00029602557,0.0010986313,0.00065634504,0.00041718967,0.002066227,0.0000071053014,0.00052433356],"genre_scores_gemma":[0.9790679,0.0017987171,0.0012016626,0.00013749914,0.0000684031,0.000010218976,0.017250443,0.000007958906,0.0004572007],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.998474,0.00008569851,0.00019175537,0.00087828125,0.00019641194,0.00017387394],"domain_scores_gemma":[0.99711734,0.000028000755,0.000088859415,0.002687967,0.000037698806,0.00004012663],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022782993,0.00010249846,0.00013833541,0.0000771736,0.00012842704,0.00014519508,0.0010727514,0.0000659002,0.000019673647],"category_scores_gemma":[0.00032235132,0.00007331387,0.000009191386,0.00023456373,0.00023693721,0.000031559757,0.001312486,0.000082811086,0.000009264643],"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":[0.000041462386,0.00014709537,0.08011285,0.00006120235,0.000117619704,0.00000118288,0.00030325094,0.0000010606282,0.79815626,0.0029631637,0.101435356,0.016659472],"study_design_scores_gemma":[0.0005399677,0.000046821133,0.20356849,0.000008407089,0.000061628736,0.000010948103,0.0008279532,0.0033478816,0.0032071318,0.00034353562,0.78783,0.0002072622],"about_ca_topic_score_codex":0.00001993063,"about_ca_topic_score_gemma":0.0001491363,"teacher_disagreement_score":0.7949492,"about_ca_system_score_codex":0.0000038085448,"about_ca_system_score_gemma":0.00005558661,"threshold_uncertainty_score":0.2989653},"labels":[],"label_agreement":null},{"id":"W2981521947","doi":"10.1038/s41597-019-0206-3","title":"A database for using machine learning and data mining techniques for coronary artery disease diagnosis","year":2019,"lang":"en","type":"article","venue":"Scientific Data","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":107,"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; Université du Québec à Montréal","funders":"","keywords":"Coronary artery disease; Computer science; Disease; Database; Artificial intelligence; Information retrieval; Medicine; Internal medicine","score_opus":0.40365149775140063,"score_gpt":0.5364813959138394,"score_spread":0.13282989816243873,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2981521947","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":[0.69629884,0.0032706158,0.031830437,0.0027796198,0.007028046,0.013058207,0.24512906,0.0005078241,0.00009734498],"genre_scores_gemma":[0.5500695,0.00028230844,0.21563633,0.0012491754,0.001274886,0.0015392019,0.22449192,0.00022514349,0.0052315486],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964747,0.00026547848,0.00064173527,0.0016175887,0.0002905144,0.0007100034],"domain_scores_gemma":[0.9933002,0.0023269346,0.0002912816,0.0035328728,0.00024035088,0.00030836117],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.004692767,0.00019522787,0.0002842179,0.00018293418,0.002117623,0.0001248294,0.0016265695,0.00010483782,0.00027230664],"category_scores_gemma":[0.0035809581,0.00018538306,0.00002833365,0.0002529756,0.00021366701,0.0012970023,0.0036162364,0.0003354548,0.000058944443],"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":[0.00047736656,0.0001482584,0.84522504,0.003245081,0.00004387523,0.000012852307,0.0012479171,0.000004759785,0.0016886013,0.0005162642,0.08299373,0.06439628],"study_design_scores_gemma":[0.00026655858,0.00007926959,0.00063597906,0.0011223195,0.00010477151,0.0000029933926,0.0039033536,0.5562635,0.00020431742,0.00048991526,0.43658122,0.00034576468],"about_ca_topic_score_codex":0.0003372086,"about_ca_topic_score_gemma":0.0013295279,"teacher_disagreement_score":0.84458905,"about_ca_system_score_codex":0.00007307647,"about_ca_system_score_gemma":0.00059531175,"threshold_uncertainty_score":0.9991815},"labels":[],"label_agreement":null},{"id":"W2981564286","doi":"10.1038/s41597-019-0242-z","title":"Integrated open-source software for multiscale electrophysiology","year":2019,"lang":"en","type":"article","venue":"Scientific Data","topic":"Neural dynamics and brain function","field":"Neuroscience","cited_by":26,"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; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Molson Foundation","keywords":"Open source software; Open source; Computer science; Software; Data science; Programming language","score_opus":0.06402038037987169,"score_gpt":0.300269165734127,"score_spread":0.2362487853542553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2981564286","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":[0.9549492,0.000018973999,0.025779247,0.0006519223,0.008396887,0.0022004144,0.007033133,0.00026420518,0.0007060388],"genre_scores_gemma":[0.8463944,0.000005900314,0.006616676,0.0015854983,0.0001203115,0.00006189802,0.009174987,0.000060756844,0.13597955],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981248,0.000064082305,0.00015566272,0.001169811,0.00015587643,0.00032980798],"domain_scores_gemma":[0.9980257,0.00021874692,0.000077090146,0.0015507817,0.00006953948,0.000058108035],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038268144,0.000107845066,0.00014122945,0.000071117516,0.00030567698,0.00052856025,0.0024165905,0.000043905573,0.0002068297],"category_scores_gemma":[0.0010746369,0.000085560016,0.000025750745,0.000544816,0.00014892309,0.00059784116,0.0012686778,0.000114103284,0.0005852551],"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":[0.000052945237,0.00005240702,0.000040081035,0.000010229645,0.0000017042114,7.1473056e-7,0.000011548424,0.000029805959,0.91249484,0.0005647473,0.06707923,0.019661773],"study_design_scores_gemma":[0.0006596618,0.00018569884,0.00020897892,0.00001498832,0.0000073054453,0.0000092478585,0.000022354949,0.11698557,0.070696525,0.0015836868,0.80940735,0.00021861067],"about_ca_topic_score_codex":0.000028567341,"about_ca_topic_score_gemma":0.00003306874,"teacher_disagreement_score":0.8417983,"about_ca_system_score_codex":0.000022132695,"about_ca_system_score_gemma":0.00007879742,"threshold_uncertainty_score":0.7522465},"labels":[],"label_agreement":null},{"id":"W2981959691","doi":"10.1038/s41597-019-0241-0","title":"Distributed radiomics as a signature validation study using the Personal Health Train infrastructure","year":2019,"lang":"en","type":"article","venue":"Scientific Data","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":67,"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","funders":"","keywords":"Radiomics; Computer science; Signature (topology); Data mining; Artificial intelligence; Mathematics","score_opus":0.03081040018237908,"score_gpt":0.3496671711163765,"score_spread":0.31885677093399745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2981959691","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":[0.9862325,0.00021105795,0.0037925413,0.005996808,0.0016996618,0.001002716,0.00093225844,0.000049958307,0.00008249212],"genre_scores_gemma":[0.9894462,0.0000039557663,0.0016186654,0.00085547246,0.0002062373,0.000002129399,0.0071744337,0.00001997035,0.0006729092],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979259,0.0001654135,0.00025952494,0.0006559868,0.0006765973,0.00031661478],"domain_scores_gemma":[0.9982662,0.000066275345,0.00014803166,0.0012777119,0.00007077002,0.00017097099],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025835575,0.00014012464,0.00024673477,0.00010022425,0.00041751724,0.00030229113,0.00067791773,0.000053575983,0.0002974921],"category_scores_gemma":[0.00047828618,0.000090742826,0.00004430022,0.00057515537,0.00019419493,0.00020277454,0.0002972491,0.00066376553,0.000030922503],"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":[0.0004658319,0.0015624494,0.15839916,0.00057591853,0.0007796686,0.00015964732,0.03421872,0.0035055531,0.05066663,0.0007462182,0.599594,0.14932624],"study_design_scores_gemma":[0.0038830764,0.00036800976,0.04885384,0.00023380465,0.00023396582,0.0004283161,0.011524812,0.7690376,0.000105439,0.00034853895,0.16461317,0.0003694101],"about_ca_topic_score_codex":0.00009771962,"about_ca_topic_score_gemma":0.0000063772018,"teacher_disagreement_score":0.7655321,"about_ca_system_score_codex":0.00012111847,"about_ca_system_score_gemma":0.0005761002,"threshold_uncertainty_score":0.3700385},"labels":[],"label_agreement":null},{"id":"W2982168029","doi":"10.1038/s41597-019-0214-3","title":"Global humid tropics forest structural condition and forest structural integrity maps","year":2019,"lang":"en","type":"article","venue":"Scientific Data","topic":"Remote Sensing in Agriculture","field":"Environmental Science","cited_by":85,"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 Northern British Columbia","funders":"Nuclear Safety and Security Commission; National Aeronautics and Space Administration","keywords":"Canopy; Biodiversity; Forest ecology; Tropics; Tree canopy; Ecosystem services; Agroforestry; Disturbance (geology); Secondary forest; Environmental science; Ecosystem; Environmental resource management; Geography; Ecology; Biology","score_opus":0.01630188727024519,"score_gpt":0.2600394197173262,"score_spread":0.24373753244708102,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2982168029","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":[0.9923285,0.000028293209,0.000053255888,0.00022684738,0.0023924878,0.00032908554,0.0023846403,0.0000561275,0.0022007446],"genre_scores_gemma":[0.9898514,0.0000016582785,0.0030309774,0.00006118599,0.000083166036,3.3899948e-7,0.005607888,0.000007581524,0.0013557842],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9978001,0.000055477212,0.00021879819,0.0009794282,0.0005620896,0.00038408194],"domain_scores_gemma":[0.99834186,0.000023355868,0.00011244195,0.0013547221,0.000021771026,0.00014582941],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029819302,0.00019808437,0.00016596215,0.000023485403,0.00034133455,0.000522255,0.0010129937,0.00010907688,0.000560094],"category_scores_gemma":[0.00009250581,0.00014114803,0.0000321462,0.0003878496,0.00074168295,0.0010093376,0.0013763397,0.00021318751,0.00049497635],"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":[0.000017881524,0.000011438983,0.85863066,0.00002634925,0.000014182896,0.000009509316,0.0001498958,0.0006062022,0.0036244055,0.0011614052,0.12811233,0.007635722],"study_design_scores_gemma":[0.00029976823,0.000028532344,0.9567909,0.000017453356,0.00001653613,0.00008760564,0.0001327058,0.015754899,0.00008080448,0.008786949,0.017769251,0.0002345601],"about_ca_topic_score_codex":0.0005332871,"about_ca_topic_score_gemma":0.006779952,"teacher_disagreement_score":0.11034308,"about_ca_system_score_codex":0.00017780543,"about_ca_system_score_gemma":0.000019589377,"threshold_uncertainty_score":0.6362085},"labels":[],"label_agreement":null},{"id":"W2982600860","doi":"10.1038/s41597-019-0262-8","title":"Structural and functional multi-platform MRI series of a single human volunteer over more than fifteen years","year":2019,"lang":"en","type":"article","venue":"Scientific Data","topic":"Advanced MRI Techniques and Applications","field":"Medicine","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université de Sherbrooke; University of Alberta; Institut Universitaire de Gériatrie de Montréal; Université Laval; Institut Universitaire en Santé Mentale de Québec","funders":"Canadian Institutes of Health Research; Canada Research Chairs; University of Electronic Science and Technology of China; Government of Canada; Government of Ontario; Alzheimer's Society; Fonds de Recherche du Québec - Santé; Pfizer Canada; Pfizer; Ontario Brain Institute; Courtois Foundation; Consortium canadien en neurodégénérescence associée au vieillissement","keywords":"Volunteer; Series (stratigraphy); Computer science; Computational biology; Biology; Ecology; Paleontology","score_opus":0.0722936045505076,"score_gpt":0.3349037215651771,"score_spread":0.2626101170146695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2982600860","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":[0.9956528,0.00006125469,0.001627584,0.00014887666,0.00016475511,0.0003322293,0.0016900516,0.00004779115,0.00027469185],"genre_scores_gemma":[0.96119684,0.0000028739482,0.021362556,0.00003251312,0.000039280298,0.0000060590414,0.0037824367,0.00001159768,0.013565848],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99923116,0.000002293271,0.0001307818,0.00033773633,0.00018401672,0.000113985036],"domain_scores_gemma":[0.99895614,0.000007956238,0.000059805574,0.0008743334,0.000052896612,0.00004885894],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011246131,0.0000665353,0.00011301121,0.000058913563,0.00008155977,0.000033497996,0.00015670755,0.00003382033,0.00031061567],"category_scores_gemma":[0.000013663537,0.00005614497,0.000019183517,0.00014101903,0.00025209776,0.000337171,0.00027825663,0.00006681756,0.0000130010985],"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":[0.00015373908,0.00031263725,0.094675176,0.00022693822,0.00006108379,0.000007451998,0.001120351,0.000039564035,0.7605497,0.009374769,0.1240123,0.009466288],"study_design_scores_gemma":[0.0015101006,0.00018644317,0.7841845,0.00013935384,0.00007753624,0.00006201202,0.00060591707,0.0046138894,0.013112563,0.001762951,0.19346356,0.00028115447],"about_ca_topic_score_codex":0.000028429991,"about_ca_topic_score_gemma":0.000043524888,"teacher_disagreement_score":0.7474371,"about_ca_system_score_codex":0.000014941369,"about_ca_system_score_gemma":0.000025699026,"threshold_uncertainty_score":0.34010237},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W2990212745","doi":"10.1038/s41597-019-0310-4","title":"Benefits and barriers in the design of harmonized access agreements for international data sharing","year":2019,"lang":"en","type":"article","venue":"Scientific Data","topic":"Ethics in Clinical Research","field":"Medicine","cited_by":33,"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; McGill University and Génome Québec Innovation Centre; McGill University; McGill University Health Centre","funders":"Canadian Institutes of Health Research; University College London Hospitals NHS Foundation Trust; National Institute for Health and Care Research; Horizon 2020 Framework Programme; McGill University","keywords":"Data sharing; Context (archaeology); Corporate governance; Core (optical fiber); Data access; Set (abstract data type); Computer science; Business; Data science; Database; Telecommunications; Medicine","score_opus":0.8224288789402373,"score_gpt":0.60965478037303,"score_spread":0.2127740985672073,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2990212745","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":[0.9288825,0.0010178925,0.009781369,0.020516451,0.007021836,0.006910535,0.02325457,0.00003489558,0.002579972],"genre_scores_gemma":[0.97566164,0.00027581418,0.01148115,0.0005309291,0.000113483075,0.000025324858,0.00868291,0.000017907727,0.0032108293],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99779713,0.000046032674,0.00029995895,0.00078266393,0.00090120424,0.00017298777],"domain_scores_gemma":[0.9927127,0.0029076473,0.00008750726,0.0039015114,0.00030807502,0.000082571394],"candidate_categories":["metaresearch","open_science"],"consensus_categories":[],"category_scores_codex":[0.019647093,0.000054175143,0.00012741332,0.00011691674,0.00006664999,0.00026923086,0.0059752157,0.00005792253,0.00022076756],"category_scores_gemma":[0.025972089,0.00003727475,0.000011220656,0.00024470242,0.00024544727,0.00052074663,0.005148733,0.00030601304,0.000012880189],"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":[0.0024485793,0.0008000429,0.6493539,0.0018535461,0.0005029706,0.000018240471,0.0033680552,0.00019881627,0.013281745,0.01460241,0.22729123,0.08628044],"study_design_scores_gemma":[0.021749176,0.0005627227,0.23245429,0.0037016112,0.00029090524,0.000017685827,0.0038055521,0.6107401,0.0053435783,0.052137863,0.068515375,0.0006811069],"about_ca_topic_score_codex":0.000043183714,"about_ca_topic_score_gemma":0.000116666895,"teacher_disagreement_score":0.61054134,"about_ca_system_score_codex":0.000015375068,"about_ca_system_score_gemma":0.00025868797,"threshold_uncertainty_score":0.99940294},"labels":[],"label_agreement":null},{"id":"W2991126022","doi":"10.1038/s41597-019-0312-2","title":"A global wildfire dataset for the analysis of fire regimes and fire behaviour","year":2019,"lang":"en","type":"article","venue":"Scientific Data","topic":"Fire effects on ecosystems","field":"Environmental Science","cited_by":366,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Nutrition International","funders":"","keywords":"Environmental science; Work (physics); Product (mathematics); Computer science; Remote sensing; Meteorology; Geography; Engineering; Mathematics","score_opus":0.017380249280836636,"score_gpt":0.26873818777623465,"score_spread":0.251357938495398,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2991126022","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":[0.88719875,0.0002553989,0.00004862342,0.00026679353,0.0005906475,0.0006257305,0.11089925,0.000013287966,0.000101516016],"genre_scores_gemma":[0.97868377,0.0000059885106,0.00027128175,0.000040944476,0.000012037768,0.00001319977,0.01991089,0.0000062376926,0.0010556408],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99827653,0.00004904518,0.00021635971,0.0008035307,0.00041179353,0.00024275214],"domain_scores_gemma":[0.99658626,0.00017535719,0.00014593746,0.0030157783,0.0000066291595,0.00007004285],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014700079,0.000116850744,0.00021882159,0.000028021863,0.00022505228,0.00017076831,0.0016673092,0.000042734202,0.0004554468],"category_scores_gemma":[0.00012471995,0.000080169586,0.000052105483,0.0011094245,0.0003933559,0.00048420933,0.0013309767,0.000041063617,0.00013934166],"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":[0.000015292044,0.000059514943,0.340115,0.000025749936,0.00015933166,0.0000012426646,0.00008650283,0.000119256605,0.0001299163,0.000012668729,0.6315981,0.027677402],"study_design_scores_gemma":[0.00028849268,0.00004011199,0.48337108,0.000021817168,0.00076767616,0.0000045287024,0.00016343196,0.35646078,0.000035683017,0.000026015441,0.15863934,0.00018104652],"about_ca_topic_score_codex":0.0025944368,"about_ca_topic_score_gemma":0.0015221209,"teacher_disagreement_score":0.47295877,"about_ca_system_score_codex":0.00004404216,"about_ca_system_score_gemma":0.000016982855,"threshold_uncertainty_score":0.49868232},"labels":[],"label_agreement":null},{"id":"W2993872008","doi":"10.1038/s41597-019-0300-6","title":"Global hydro-environmental sub-basin and river reach characteristics at high spatial resolution","year":2019,"lang":"en","type":"article","venue":"Scientific Data","topic":"Hydrology and Watershed Management Studies","field":"Environmental Science","cited_by":660,"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":"Australian Research Council; Department of Education and Training; Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Compendium; Structural basin; Drainage basin; Land cover; Hydrology (agriculture); Environmental science; Spatial analysis; Computer science; Environmental resource management; Land use; Database; Remote sensing; Geography; Cartography; Geology; Ecology","score_opus":0.01102404109151187,"score_gpt":0.20506397169694648,"score_spread":0.19403993060543462,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2993872008","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":[0.99469185,0.000024673369,0.0001293454,0.0003809076,0.001019086,0.00023926233,0.001703411,0.00003132131,0.0017801593],"genre_scores_gemma":[0.9929016,0.000024554876,0.00018695655,0.00012230487,0.00003345637,0.0000033002566,0.0026109242,0.000006324856,0.0041105542],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99821454,0.000059628463,0.00016725823,0.0008893519,0.00033636787,0.00033282914],"domain_scores_gemma":[0.9988104,0.000014798808,0.00007627899,0.0010212893,0.0000015916504,0.0000756555],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00059194304,0.00014030165,0.00014124166,0.000024931853,0.0004418435,0.00006735733,0.00055386405,0.000058088037,0.0012554163],"category_scores_gemma":[0.000018733024,0.00012767714,0.000017274444,0.00011542126,0.0010869189,0.00041981234,0.003891431,0.000062670995,0.004231803],"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":[0.00005984955,0.000089992514,0.9120167,0.000009799681,0.000024955287,0.00001322123,0.00015484093,0.000038903407,0.0035692854,0.00005657278,0.07825549,0.0057103946],"study_design_scores_gemma":[0.0003449432,0.000036258956,0.89428043,0.0000051735824,0.000033485358,0.000005865954,0.000018312347,0.002990055,0.00014497041,0.00029387252,0.10167443,0.0001721975],"about_ca_topic_score_codex":0.00042613348,"about_ca_topic_score_gemma":0.0003161995,"teacher_disagreement_score":0.023418946,"about_ca_system_score_codex":0.00019096295,"about_ca_system_score_gemma":0.0000033777308,"threshold_uncertainty_score":0.9996576},"labels":[],"label_agreement":null},{"id":"W2994025393","doi":"10.1038/s41597-019-0316-y","title":"CE-QUAL-W2 model of dam outflow elevation impact on temperature, dissolved oxygen and nutrients in a reservoir","year":2019,"lang":"en","type":"article","venue":"Scientific Data","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Global Institute for Water Security; University of Saskatchewan","funders":"Global Institute for Water Security, University of Saskatchewan; Global Water Futures; University of Saskatchewan","keywords":"Outflow; Nutrient; Environmental science; Elevation (ballistics); Hydrology (agriculture); Oxygen; Oceanography; Ecology; Geology; Chemistry; Biology; Geotechnical engineering; Mathematics","score_opus":0.04989829200182872,"score_gpt":0.29832687360129106,"score_spread":0.24842858159946235,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2994025393","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":[0.99753773,0.0000081793005,0.000020010357,0.000108112734,0.00019242948,0.00030171146,0.000906745,0.000020568481,0.0009045306],"genre_scores_gemma":[0.9969222,0.0000020199636,0.00083077606,0.000040931576,0.000007674166,0.0000028585378,0.00074657047,0.0000097758075,0.0014371799],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99799544,0.000066761335,0.00025875328,0.00083055126,0.0005328903,0.00031562382],"domain_scores_gemma":[0.99833435,0.00005859878,0.00010247305,0.0013933604,0.000012214665,0.00009899902],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015074783,0.00013733016,0.00017994232,0.000095101364,0.00010031303,0.00011833621,0.00086391304,0.00008245741,0.0003325281],"category_scores_gemma":[0.0003218631,0.000100618905,0.00002509151,0.0005974489,0.00026855702,0.0004926268,0.00094469305,0.00016514574,0.00021622216],"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":[0.00029892658,0.00072914927,0.2701327,0.000053429267,0.00001701332,0.0000050143312,0.0011372797,0.2951022,0.40163428,0.00010019777,0.02865498,0.002134827],"study_design_scores_gemma":[0.00062826497,0.00014651421,0.12522513,0.00008635339,0.0000072752036,0.000001169336,0.00002688338,0.86924475,0.0021348845,0.0017155393,0.000569833,0.00021338047],"about_ca_topic_score_codex":0.00018893697,"about_ca_topic_score_gemma":0.00008907907,"teacher_disagreement_score":0.5741426,"about_ca_system_score_codex":0.00009474179,"about_ca_system_score_gemma":0.0000246595,"threshold_uncertainty_score":0.41031197},"labels":[],"label_agreement":null},{"id":"W3000434011","doi":"10.1038/s41597-019-0344-7","title":"A global database for metacommunity ecology, integrating species, traits, environment and space","year":2020,"lang":"en","type":"article","venue":"Scientific Data","topic":"Species Distribution and Climate Change","field":"Environmental Science","cited_by":64,"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; Université de Montréal","funders":"Conselho Nacional de Desenvolvimento Científico e Tecnológico; Deutsche Forschungsgemeinschaft; Deutsches Zentrum für integrative Biodiversitätsforschung Halle-Jena-Leipzig; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Metacommunity; Ecology; Trait; Biodiversity; Ecosystem; Taxon; Community; Database; Biology; Macroecology; Spatial ecology; Geography; Computer science; Biological dispersal","score_opus":0.11391963621065433,"score_gpt":0.28919924332291835,"score_spread":0.17527960711226404,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3000434011","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":[0.5949129,0.0006749031,0.021288931,0.031094706,0.0014233249,0.0024325075,0.30721,0.00029630918,0.04066643],"genre_scores_gemma":[0.9243233,0.00017327782,0.020728208,0.0026561,0.0001462078,0.00007336623,0.04930291,0.0000310604,0.0025655224],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99849313,0.00006057711,0.00017704944,0.00070651725,0.00025544333,0.00030727967],"domain_scores_gemma":[0.99881476,0.000055238146,0.00007275612,0.00081738434,0.000005634023,0.00023425282],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00074923306,0.00013591017,0.00014519645,0.000010245081,0.00048624713,0.00023696797,0.0010795343,0.00003843669,0.022218524],"category_scores_gemma":[0.00031380416,0.00012188532,0.000029130044,0.00026162717,0.0007319011,0.00042764118,0.002795381,0.00009102262,0.00046903663],"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":[0.000025332994,0.00015207953,0.01373773,0.000030395264,0.000020113672,0.0000033465988,0.0003542662,0.000007260284,0.009940681,0.0045061875,0.965452,0.005770617],"study_design_scores_gemma":[0.00037532364,0.000046762703,0.061677266,0.000003665247,0.00003357759,0.0000043863133,0.002800479,0.0026264011,0.00021201996,0.00010282992,0.9319468,0.00017046479],"about_ca_topic_score_codex":0.00011731726,"about_ca_topic_score_gemma":0.001623876,"teacher_disagreement_score":0.32941046,"about_ca_system_score_codex":0.00020573122,"about_ca_system_score_gemma":0.000015054174,"threshold_uncertainty_score":0.9786753},"labels":[],"label_agreement":null},{"id":"W3005230983","doi":"10.1038/s41597-020-0375-0","title":"Nexus of grazing management with plant and soil properties in northern China grasslands","year":2020,"lang":"en","type":"article","venue":"Scientific Data","topic":"Soil Carbon and Nitrogen Dynamics","field":"Agricultural and Biological Sciences","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Agriculture and Agri-Food Canada","funders":"Agriculture and Agri-Food Canada; Gansu Agricultural University","keywords":"Grazing; Environmental science; Grassland; Biomass (ecology); Ecosystem; Agroforestry; Vegetation (pathology); Agronomy; Plant community; Ecology; Biology; Species richness","score_opus":0.039439262392051616,"score_gpt":0.19525176392634327,"score_spread":0.15581250153429166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3005230983","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":[0.9983609,0.00011479697,0.00000130023,0.0004288219,0.0000517857,0.000102852675,0.00037767217,0.000017533426,0.0005443523],"genre_scores_gemma":[0.99922156,0.000009390835,0.000038447128,0.000033129938,0.000016993694,0.000002358263,0.0006255746,5.825909e-7,0.000051933104],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99921125,0.000018522273,0.000110401794,0.00034060015,0.00018480862,0.00013442221],"domain_scores_gemma":[0.9997655,0.000008182953,0.000039715193,0.00011816208,0.000013330259,0.0000551184],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002131924,0.00006860866,0.000095950905,0.000011753938,0.000074926276,0.00008783311,0.00039830987,0.00001671708,0.0000062305303],"category_scores_gemma":[0.000011400692,0.000023199249,0.000009808617,0.00033747533,0.00011751093,0.00011135114,0.00033337655,0.000046608064,0.0000028327074],"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":[0.00028742323,0.0002481768,0.84246325,0.00019882694,0.00006433505,0.000081768005,0.0016951318,0.00009326508,0.06088745,0.0003770108,0.0014592665,0.092144094],"study_design_scores_gemma":[0.0007104443,0.00042355014,0.92943096,0.0001688354,0.000045919885,0.000015577094,0.0035030239,0.056818385,0.002600719,0.00030391582,0.0055425456,0.00043613167],"about_ca_topic_score_codex":0.00025828084,"about_ca_topic_score_gemma":0.022543447,"teacher_disagreement_score":0.09170797,"about_ca_system_score_codex":0.0000041377148,"about_ca_system_score_gemma":0.000005179422,"threshold_uncertainty_score":0.9952926},"labels":[],"label_agreement":null},{"id":"W3006404851","doi":"10.1038/s41597-020-0379-9","title":"High-resolution T2-FLAIR and non-contrast CT brain atlas of the elderly","year":2020,"lang":"en","type":"article","venue":"Scientific Data","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Foothills Medical Centre; University of Calgary","funders":"Canadian Open Neuroscience Platform; University of Calgary; Canada Research Chairs; Heart and Stroke Foundation of Canada","keywords":"Fluid-attenuated inversion recovery; Spatial normalization; Neuroimaging; Contrast (vision); Computer science; Modalities; Normalization (sociology); Artificial intelligence; Modality (human–computer interaction); Voxel; Brain atlas; Brain mapping; Pattern recognition (psychology); Medicine; Neuroscience; Magnetic resonance imaging; Radiology; Psychology","score_opus":0.030584969278722597,"score_gpt":0.27253003643218593,"score_spread":0.24194506715346334,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3006404851","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":[0.009204991,0.00005483042,0.97654015,0.012598374,0.0007309949,0.00028037603,0.00030604991,0.00010535172,0.00017889871],"genre_scores_gemma":[0.80559033,0.000006821452,0.19138823,0.0018388965,0.00010268433,0.000009556886,0.00030634043,0.00001024426,0.00074687967],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9984125,0.00008606046,0.00023561077,0.0006029156,0.0004917115,0.0001712173],"domain_scores_gemma":[0.99812025,0.000083718514,0.00012091287,0.0014956864,0.000057968216,0.00012145238],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008843914,0.000080423015,0.000113404516,0.00004310068,0.00017492483,0.00031258358,0.0028125695,0.000019011373,0.00003884719],"category_scores_gemma":[0.00048554802,0.000057483896,0.000021463848,0.00061798625,0.00042832296,0.00083658437,0.0018123601,0.0001068999,0.000028762097],"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":[0.0000030080857,0.000035580884,0.000075040254,0.000039361348,0.000009673962,0.0000053195654,0.0004950963,0.000002419373,0.11966547,0.0013920398,0.7030622,0.1752148],"study_design_scores_gemma":[0.0013966036,0.00031683804,0.008115712,0.00018388477,0.000035944406,0.000023789793,0.00019292453,0.14125842,0.79354167,0.0040245135,0.050408404,0.00050127634],"about_ca_topic_score_codex":0.0000611925,"about_ca_topic_score_gemma":0.000022549762,"teacher_disagreement_score":0.79638535,"about_ca_system_score_codex":0.00001035934,"about_ca_system_score_gemma":0.00009661008,"threshold_uncertainty_score":0.52265006},"labels":[],"label_agreement":null},{"id":"W3006538489","doi":"10.1038/s41597-020-0388-8","title":"The Rural Household Multiple Indicator Survey, data from 13,310 farm households in 21 countries","year":2020,"lang":"en","type":"article","venue":"Scientific Data","topic":"Food Security and Health in Diverse Populations","field":"Health Professions","cited_by":44,"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":"Consortium of International Agricultural Research Centers; United States Agency for International Development","keywords":"Food security; Household income; Survey data collection; Livestock; Agriculture; Welfare; Productivity; Poverty; Index (typography); Agricultural economics; Geography; Production (economics); Scale (ratio); Agricultural productivity; Business; Socioeconomics; Economics; Economic growth; Statistics","score_opus":0.48539061247049725,"score_gpt":0.4517201502234974,"score_spread":0.03367046224699988,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3006538489","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":[0.59057397,0.0013437571,0.00010302772,0.014436792,0.006937495,0.0015680526,0.38442314,0.00028672017,0.00032708776],"genre_scores_gemma":[0.9202614,0.000237465,0.00023415008,0.0023876543,0.00043638836,0.000032796666,0.07595224,0.00003745639,0.00042049258],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9952676,0.0010290883,0.00093393156,0.001136465,0.00075529335,0.00087758614],"domain_scores_gemma":[0.99176776,0.0023228836,0.00036706636,0.005068697,0.00009505063,0.00037856222],"candidate_categories":["sts","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00579384,0.00020811257,0.00032485076,0.00009172516,0.0038333943,0.00031384287,0.0057832845,0.00022751099,0.0004074923],"category_scores_gemma":[0.00373804,0.00016549752,0.000024642952,0.00087563414,0.00058477547,0.0008223931,0.005753801,0.0010694212,0.00167984],"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":[0.00010267327,0.00005398707,0.45357943,0.00006095239,0.000017442178,0.0000041847647,0.0040708636,0.0000089103105,0.000011841091,0.00021935564,0.5415649,0.00030551004],"study_design_scores_gemma":[0.0008289047,0.000014122847,0.37653702,0.000073429794,0.000017032871,1.4963454e-7,0.0042656884,0.0069206688,0.000002954227,0.00015450215,0.6110037,0.00018179488],"about_ca_topic_score_codex":0.018902456,"about_ca_topic_score_gemma":0.22651123,"teacher_disagreement_score":0.32968742,"about_ca_system_score_codex":0.000090513306,"about_ca_system_score_gemma":0.0010477043,"threshold_uncertainty_score":0.9995959},"labels":[],"label_agreement":null},{"id":"W3007040014","doi":"10.1038/s41597-019-0346-5","title":"Global karst springs hydrograph dataset for research and management of the world’s fastest-flowing groundwater","year":2020,"lang":"en","type":"article","venue":"Scientific Data","topic":"Karst Systems and Hydrogeology","field":"Earth and Planetary Sciences","cited_by":103,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"Natural Environment Research Council; Sight Research UK","keywords":"Karst; Aquifer; Groundwater; Hydrograph; Hydrology (agriculture); Spring (device); Water resource management; Environmental science; Groundwater flow; Environmental resource management; Geography; Geology; Cartography; Drainage basin; Engineering","score_opus":0.16147000265261754,"score_gpt":0.3372273776496487,"score_spread":0.17575737499703117,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3007040014","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":[0.8983841,0.0009971749,0.00018087708,0.004841154,0.0021094265,0.0015795662,0.08811755,0.00003328583,0.003756849],"genre_scores_gemma":[0.9878716,0.000009802272,0.0010210405,0.00013098528,0.00007051109,0.0000026874934,0.010271542,0.0000027729584,0.0006190441],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982566,0.0000680815,0.00022155812,0.00066421536,0.00041668612,0.0003728149],"domain_scores_gemma":[0.9986988,0.000068119305,0.00003990981,0.0010363463,0.000034706616,0.0001221538],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017851114,0.0000856608,0.00013224749,0.000064900305,0.0004541523,0.0002705136,0.0015973495,0.00002459574,0.00019722333],"category_scores_gemma":[0.000028588385,0.0000567713,0.000025327832,0.0009158539,0.0006119848,0.00031817032,0.0006895072,0.00007143418,0.00006087677],"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":[0.0000715672,0.00004992798,0.5524816,0.00056074053,0.00010212711,0.000018704768,0.000223839,0.0001033449,0.00008500633,0.0023696516,0.43316007,0.010773401],"study_design_scores_gemma":[0.00034950537,0.00007855119,0.10305073,0.000068021516,0.00003023474,0.000007082619,0.0002534308,0.008910502,0.000059226513,0.0009159555,0.8861503,0.00012644315],"about_ca_topic_score_codex":0.0008948004,"about_ca_topic_score_gemma":0.008848043,"teacher_disagreement_score":0.45299023,"about_ca_system_score_codex":0.0000026103528,"about_ca_system_score_gemma":0.000023568333,"threshold_uncertainty_score":0.49374157},"labels":[],"label_agreement":null},{"id":"W3007951719","doi":"10.1038/s41597-020-0415-9","title":"A NWB-based dataset and processing pipeline of human single-neuron activity during a declarative memory task","year":2020,"lang":"en","type":"article","venue":"Scientific Data","topic":"Neural dynamics and brain function","field":"Neuroscience","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; Toronto Western Hospital","funders":"National Institute of Neurological Disorders and Stroke; National Institute of Mental Health; McKnight Foundation; Kavli Foundation; National Alliance for Research on Schizophrenia and Depression; Howard Hughes Medical Institute; National Science Foundation","keywords":"Task (project management); Pipeline (software); Computer science; Programming language","score_opus":0.1313626909694292,"score_gpt":0.30981835983481254,"score_spread":0.17845566886538333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3007951719","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":[0.98299676,0.000015254083,0.00074794417,0.0009719592,0.00021018708,0.00023656398,0.014702184,0.000050249717,0.00006889601],"genre_scores_gemma":[0.99708766,9.1668176e-7,0.000105169376,0.0002840413,0.00003942374,0.0000025035874,0.0023793748,0.000012089444,0.00008884029],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99803764,0.000112096364,0.00020072439,0.001078025,0.00036273678,0.00020880668],"domain_scores_gemma":[0.9987989,0.0000719936,0.00018607105,0.00079084706,0.00003540743,0.00011678982],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003171507,0.00013185239,0.00016060415,0.000087565444,0.0004505548,0.0002966523,0.0006482256,0.0000287931,0.000020596202],"category_scores_gemma":[0.0006123455,0.000119016986,0.000017082788,0.0005629269,0.0003673388,0.0008340693,0.00069812563,0.00015212563,0.000007664759],"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":[0.00005367466,0.00009567184,0.000021620017,0.00011861166,8.4411465e-7,0.0000135369155,0.00009727281,0.000031566036,0.99280643,0.0000064965925,0.0038139431,0.0029403053],"study_design_scores_gemma":[0.0005218739,0.00010910431,0.00041086433,0.000042516236,0.000018601266,0.000006717375,0.000037323993,0.15832068,0.83766,0.000035195764,0.0026712676,0.00016587035],"about_ca_topic_score_codex":0.000011333371,"about_ca_topic_score_gemma":0.00003500223,"teacher_disagreement_score":0.1582891,"about_ca_system_score_codex":0.000013270454,"about_ca_system_score_gemma":0.000060240225,"threshold_uncertainty_score":0.48533717},"labels":[],"label_agreement":null},{"id":"W3008267920","doi":"10.1038/s41597-020-00781-y","title":"Multimodal pathophysiological dataset of gradual cerebral ischemia in a cohort of juvenile pigs","year":2021,"lang":"en","type":"article","venue":"Scientific Data","topic":"Neurological Disease Mechanisms and Treatments","field":"Neuroscience","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital","funders":"","keywords":"Juvenile; Pathophysiology; Ischemia; Cohort; Medicine; Biology; Internal medicine; Ecology","score_opus":0.07800368628217957,"score_gpt":0.31025987053816684,"score_spread":0.23225618425598726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3008267920","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":[0.9177932,0.000015360776,0.000026200938,0.00004170688,0.00030032705,0.00015911259,0.08151303,0.000013488227,0.00013752955],"genre_scores_gemma":[0.9841203,0.0000059969875,0.0008543531,0.00010592076,0.0000097539005,0.000008606485,0.014783186,0.0000058908904,0.00010598146],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99762714,0.00017289704,0.0003931438,0.0011129751,0.00042397942,0.00026986786],"domain_scores_gemma":[0.997961,0.00013350332,0.00013809557,0.0016306893,0.000036117992,0.00010063865],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032939579,0.0001256351,0.00028871864,0.00004883733,0.000071885304,0.00004364868,0.00097298337,0.000051903604,0.00055267866],"category_scores_gemma":[0.0009927741,0.00009707653,0.000048838254,0.00056895317,0.00037238575,0.0002465526,0.0014699643,0.00011549047,0.00007139441],"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":[0.000056575846,0.0012469703,0.007837456,0.00003186972,0.000005389114,0.000336506,0.000016040221,0.0000070312312,0.9803805,0.0008665781,0.008430768,0.00078434794],"study_design_scores_gemma":[0.0012710398,0.0001128859,0.045975808,0.00003198653,0.00004146149,0.0000207106,0.000030764935,0.0027724332,0.9427624,0.0039812275,0.0027847388,0.00021456178],"about_ca_topic_score_codex":0.000028713488,"about_ca_topic_score_gemma":0.000011884677,"teacher_disagreement_score":0.06672984,"about_ca_system_score_codex":0.00000856903,"about_ca_system_score_gemma":0.00010570005,"threshold_uncertainty_score":0.6051444},"labels":[],"label_agreement":null},{"id":"W3008978453","doi":"10.1038/s41597-020-0397-7","title":"Tesco Grocery 1.0, a large-scale dataset of grocery purchases in London","year":2020,"lang":"en","type":"article","venue":"Scientific Data","topic":"Nutritional Studies and Diet","field":"Medicine","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bell (Canada)","funders":"","keywords":"Representativeness heuristic; Census; Scale (ratio); Grocery store; Geography; Business; Population; Marketing; Statistics; Environmental health; Medicine; Cartography; Mathematics","score_opus":0.0809298758706811,"score_gpt":0.32031605464777646,"score_spread":0.23938617877709537,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3008978453","genre_codex":"dataset","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":[0.3601759,0.008981965,0.00057444687,0.022757778,0.0013274421,0.0012362107,0.60241723,0.00012042475,0.0024086242],"genre_scores_gemma":[0.63956386,0.00041134912,0.0045588943,0.0041477196,0.00054630043,0.000021428177,0.35014457,0.000036101337,0.0005697592],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984279,0.000016521237,0.000307498,0.00059349247,0.0004032712,0.00025130113],"domain_scores_gemma":[0.9988139,0.000051247112,0.000067729285,0.00085349916,0.000066796005,0.00014682024],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004810493,0.000097291835,0.00026014872,0.00008680221,0.0000933685,0.000035531102,0.00046017815,0.00003228165,0.00030417528],"category_scores_gemma":[0.00041428913,0.000083328094,0.00003062791,0.0006606969,0.00020023844,0.0002416051,0.00095690624,0.00011143521,0.00010792469],"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":[0.00014936308,0.0004415186,0.00857562,0.00030114639,0.000016902313,0.000045860488,0.00010346251,8.2425873e-7,0.0027576783,0.000058869507,0.98697525,0.0005734788],"study_design_scores_gemma":[0.0019126983,0.00012853742,0.009280523,0.00016754442,0.00005089214,0.000011313126,0.0008275154,0.0009725525,0.0013278751,0.00016508359,0.9850287,0.00012679178],"about_ca_topic_score_codex":0.00005827017,"about_ca_topic_score_gemma":0.00015823217,"teacher_disagreement_score":0.27938798,"about_ca_system_score_codex":0.000014684631,"about_ca_system_score_gemma":0.00008034464,"threshold_uncertainty_score":0.3398021},"labels":[],"label_agreement":null},{"id":"W3009357978","doi":"10.1038/s41597-019-0320-2","title":"A reference library for Canadian invertebrates with 1.5 million barcodes, voucher specimens, and DNA samples","year":2019,"lang":"en","type":"article","venue":"Scientific Data","topic":"Environmental DNA in Biodiversity Studies","field":"Environmental Science","cited_by":110,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Dalhousie University; Public Health Agency of Canada; University of Guelph","funders":"Nature Conservancy of Canada; Canada First Research Excellence Fund; Ontario Genomics; Ontario Ministry of Research, Innovation and Science; Government of Canada; Churchill Northern Studies Centre; University of Guelph; Ministry of Environment; Canada Foundation for Innovation; Parks Canada; Genome Canada; Gordon and Betty Moore Foundation; Natural Sciences and Engineering Research Council of Canada; Smithsonian Institution","keywords":"GenBank; Biodiversity; Barcode; Biology; DNA barcoding; Taxonomic rank; Global biodiversity; Taxonomy (biology); Environmental DNA; DNA sequencing; Zoology; Ecology; Geography; Taxon; DNA; Genetics; Computer science","score_opus":0.03989836595563699,"score_gpt":0.2084597603429137,"score_spread":0.1685613943872767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3009357978","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":[0.98208547,0.00017856694,0.000016714419,0.00077310024,0.000232578,0.0006388479,0.009826171,0.000040983487,0.0062075984],"genre_scores_gemma":[0.9210315,0.00012827598,0.04378881,0.00088474323,0.000035438065,0.000019679832,0.00905841,0.00003936656,0.025013788],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984357,0.000021003334,0.000099904006,0.0008556594,0.00024364633,0.00034413507],"domain_scores_gemma":[0.99880224,0.00004108894,0.000041444328,0.00091864687,0.0000030620693,0.00019349033],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00023528704,0.00013939278,0.00011812789,0.00005603751,0.0004224607,0.00020704417,0.00079681096,0.000042479107,0.0041074883],"category_scores_gemma":[0.000018027347,0.00011304267,0.000010979452,0.00020266398,0.00068299874,0.0010525929,0.001201188,0.00006477034,0.001326457],"study_design_candidate":"not_applicable","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":[0.00001532881,0.000022669949,0.61593115,0.000016654769,0.000016099943,0.0000026368043,0.00019183395,0.000005291706,0.0051019387,0.000077760786,0.3773867,0.0012319324],"study_design_scores_gemma":[0.00030791646,0.000064671745,0.341422,0.000023442833,0.000019786925,0.0000030889314,0.00047888706,0.0003625504,0.0023143773,0.00024024016,0.6545052,0.00025785866],"about_ca_topic_score_codex":0.0071956087,"about_ca_topic_score_gemma":0.032420676,"teacher_disagreement_score":0.27711847,"about_ca_system_score_codex":0.00007874436,"about_ca_system_score_gemma":0.000019694218,"threshold_uncertainty_score":0.9994511},"labels":[],"label_agreement":null},{"id":"W3009988161","doi":"10.1038/s41597-020-0422-x","title":"A survey of invasive plants on grassland soil microbial communities and ecosystem services","year":2020,"lang":"en","type":"article","venue":"Scientific Data","topic":"Plant and fungal interactions","field":"Agricultural and Biological Sciences","cited_by":38,"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 Saskatchewan","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Ecosystem; Ecosystem services; Bromus inermis; Environmental science; Ecology; Ecosystem health; Grassland; Agroforestry; Forage; Biology","score_opus":0.13996465667780603,"score_gpt":0.24953217304742834,"score_spread":0.10956751636962231,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3009988161","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":[0.93757135,0.000056250134,1.4433361e-7,0.00027884546,0.0002517393,0.00006440855,0.0614792,0.000014382854,0.00028369238],"genre_scores_gemma":[0.98397547,0.000021341602,0.0000036423876,0.00008732542,0.000039303,7.6800654e-7,0.015796112,3.5485277e-7,0.00007565573],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9993286,0.00010933678,0.00013098553,0.00021280412,0.000111052315,0.00010719784],"domain_scores_gemma":[0.999255,0.00043579546,0.00007444113,0.0001272082,0.000043939777,0.00006361939],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034706094,0.00006725656,0.00011669251,0.000010243188,0.00022955195,0.0001893874,0.00065234053,0.000028600933,0.00008054849],"category_scores_gemma":[0.000041889587,0.000027049235,0.0000120709165,0.0001515954,0.00006523729,0.00019716733,0.0003717102,0.000071281705,0.00004855339],"study_design_candidate":"observational","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":[0.0002639682,0.00029814264,0.08280229,0.00017078411,0.00007508601,0.00000960579,0.0019518427,0.000003826618,0.75365514,0.00003663789,0.15202147,0.008711227],"study_design_scores_gemma":[0.0007930279,0.0006053983,0.82001615,0.0006085107,0.00004366914,0.00003518091,0.009241863,0.003916041,0.0502881,0.00006803943,0.11372608,0.00065795385],"about_ca_topic_score_codex":0.0028529754,"about_ca_topic_score_gemma":0.21866454,"teacher_disagreement_score":0.73721385,"about_ca_system_score_codex":0.000002680555,"about_ca_system_score_gemma":0.000008900046,"threshold_uncertainty_score":0.7955928},"labels":[],"label_agreement":null},{"id":"W3010123800","doi":"10.1038/s41597-020-0420-z","title":"Author Correction: A global database for metacommunity ecology, integrating species, traits, environment and space","year":2020,"lang":"en","type":"erratum","venue":"Scientific Data","topic":"Species Distribution and Climate Change","field":"Environmental Science","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":"Western University; Université de Montréal","funders":"","keywords":"Metacommunity; Ecology; Space (punctuation); Geography; Computer science; Biology; Sociology; Demography","score_opus":0.09680895019397591,"score_gpt":0.30215380738792247,"score_spread":0.20534485719394657,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3010123800","genre_codex":"dataset","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00082933693,0.0022909853,0.00685396,0.019452007,0.1599444,0.0037798674,0.6054987,0.0004457852,0.20090498],"genre_scores_gemma":[0.00081743347,0.0004790034,0.0044829794,0.00066253234,0.00085007655,0.00014542871,0.36888656,0.000063244566,0.6236127],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9965091,0.00016753434,0.0004198493,0.0016873897,0.0006378841,0.0005782881],"domain_scores_gemma":[0.9971685,0.000106907806,0.00030514438,0.0020358237,0.000017787352,0.0003658277],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0014448971,0.0004243295,0.0004599381,0.000040957453,0.001113415,0.00066064927,0.0022556297,0.00029354828,0.039984982],"category_scores_gemma":[0.00074954494,0.00040055613,0.00009548197,0.00048020112,0.0014107033,0.0005054598,0.005629086,0.0007411514,0.0009997898],"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":[0.0000135348355,0.00010202692,0.0002449874,0.00005020217,0.000030743846,0.0000043505215,0.00009395222,8.007014e-7,0.00013868067,0.00032550926,0.99623954,0.0027556606],"study_design_scores_gemma":[0.00025625268,0.000065046836,0.008071772,0.0000343351,0.00014529112,0.00001918271,0.0022307655,0.0022388715,0.00001584373,0.0000643261,0.98646814,0.0003901597],"about_ca_topic_score_codex":0.0003578841,"about_ca_topic_score_gemma":0.008032908,"teacher_disagreement_score":0.42270777,"about_ca_system_score_codex":0.0010537906,"about_ca_system_score_gemma":0.00010595606,"threshold_uncertainty_score":0.9998446},"labels":[],"label_agreement":null},{"id":"W3010707172","doi":"10.1038/s41597-020-0435-5","title":"Multidisciplinary database of permeability of fault zones and surrounding protolith rocks at world-wide sites","year":2020,"lang":"en","type":"article","venue":"Scientific Data","topic":"Hydrocarbon exploration and reservoir analysis","field":"Engineering","cited_by":75,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Hydrogeology; Geology; Geothermal gradient; Permeability (electromagnetism); Protolith; Groundwater; Petrology; Aquifer; Crust; Petroleum engineering; Geotechnical engineering; Geochemistry; Metamorphic rock; Geophysics","score_opus":0.06308179900604846,"score_gpt":0.2855893111818437,"score_spread":0.22250751217579526,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3010707172","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":[0.99226636,0.0005015341,0.002757222,0.00025827304,0.00012910488,0.000399015,0.0018665476,0.00011519276,0.0017067587],"genre_scores_gemma":[0.9961611,0.000016376389,0.000994607,0.0000027622082,0.00001852125,0.000006030559,0.0016890432,0.000016602904,0.0010949712],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99891996,0.000034179815,0.00027832913,0.0003930482,0.00024182467,0.00013267374],"domain_scores_gemma":[0.9988231,0.00005273812,0.000058267964,0.00090934633,0.000038669532,0.00011789099],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004034273,0.0000963395,0.00020025467,0.00013300369,0.00009329312,0.000042896656,0.00044089582,0.000021101469,0.00021401444],"category_scores_gemma":[0.00018495209,0.00008279533,0.000029888644,0.0006573449,0.00020567856,0.00036040958,0.0008102615,0.00006204005,0.000018399594],"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":[0.00019966978,0.00052937644,0.35640064,0.007775678,0.0005517586,0.000056363686,0.013327214,0.055122405,0.4938436,0.00021516552,0.068642154,0.003335996],"study_design_scores_gemma":[0.00036211876,0.000017398781,0.0016401898,0.00008686073,0.000059296766,0.0000018031699,0.00075066247,0.9526759,0.033615954,0.0000358567,0.010550104,0.00020389547],"about_ca_topic_score_codex":0.000021418091,"about_ca_topic_score_gemma":0.00044933826,"teacher_disagreement_score":0.89755344,"about_ca_system_score_codex":0.000013219033,"about_ca_system_score_gemma":0.000015303596,"threshold_uncertainty_score":0.33762956},"labels":[],"label_agreement":null},{"id":"W3011355476","doi":"10.1038/s41597-020-0428-4","title":"Genome assembly of six polyploid potato genomes","year":2020,"lang":"en","type":"article","venue":"Scientific Data","topic":"Plant Pathogens and Resistance","field":"Agricultural and Biological Sciences","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":"Agriculture and Agri-Food Canada; McGill University","funders":"Agriculture and Agri-Food Canada; Consortium of International Agricultural Research Centers; Compute Canada; Natural Sciences and Engineering Research Council of Canada; Centre Sève; McGill University","keywords":"Polyploid; Genome; Biology; Genetics; Genome size; DNA sequencing; Evolutionary biology; Gene","score_opus":0.057538862461047204,"score_gpt":0.2333634025700783,"score_spread":0.1758245401090311,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3011355476","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":[0.9799265,0.0011644679,0.0000070738415,0.0015793955,0.00023118858,0.000106563595,0.015554232,0.000039567014,0.0013909996],"genre_scores_gemma":[0.99413717,0.00004305929,0.00022304247,0.00011289049,0.00014828914,0.0000010902872,0.0038298015,6.9055534e-7,0.0015039716],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987534,0.00003109849,0.00018775505,0.0005353837,0.00027095556,0.00022134987],"domain_scores_gemma":[0.9994432,0.000045236848,0.000088094166,0.00023900918,0.000044091947,0.00014039887],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032311416,0.000085596905,0.00014367502,0.000008532273,0.00018102415,0.000118373326,0.001346602,0.000034441953,0.0004622385],"category_scores_gemma":[0.0000587721,0.000031487085,0.000040091247,0.00051862275,0.00012603708,0.00017427748,0.00048661424,0.000053508065,0.00014456667],"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":[0.000008301553,0.000023475379,0.00036510828,0.000008323821,0.000005835637,0.0000041929156,0.000026166474,0.0000012550867,0.9874581,0.000050668186,0.00751368,0.0045348816],"study_design_scores_gemma":[0.00007622641,0.00006619026,0.086167015,0.000010905265,0.000014489395,0.0000044057583,0.00024340508,0.00028331345,0.015120242,0.000031021307,0.89779115,0.00019163123],"about_ca_topic_score_codex":0.000018018787,"about_ca_topic_score_gemma":0.00015870249,"teacher_disagreement_score":0.97233784,"about_ca_system_score_codex":0.0000042846677,"about_ca_system_score_gemma":0.000015945305,"threshold_uncertainty_score":0.5061187},"labels":[],"label_agreement":null},{"id":"W3011735246","doi":"10.1038/s41597-020-00655-3","title":"TILES-2018, a longitudinal physiologic and behavioral data set of hospital workers","year":2020,"lang":"en","type":"article","venue":"Scientific Data","topic":"Heart Rate Variability and Autonomic Control","field":"Medicine","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":"Institut National de la Recherche Scientifique; Université du Québec à Montréal","funders":"Intelligence Advanced Research Projects Activity; NIH Office of the Director; Office of the Director of National Intelligence","keywords":"Set (abstract data type); Longitudinal data; Data set; Gerontology; Medicine; Psychology; Computer science; Data mining; Artificial intelligence","score_opus":0.21975587364632193,"score_gpt":0.36081602114383465,"score_spread":0.14106014749751272,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3011735246","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":[0.9828217,0.00016652631,0.00011933747,0.0051965234,0.00057750737,0.00037965144,0.0106330095,0.000041466137,0.00006428205],"genre_scores_gemma":[0.99112886,0.0000044740045,0.0008885767,0.000080660415,0.00014241388,0.0000018758617,0.007585216,0.0000066462667,0.00016128563],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99838215,0.000038772785,0.00025559144,0.0009284297,0.00018859694,0.00020644387],"domain_scores_gemma":[0.99735385,0.00004650726,0.00007050318,0.0023006832,0.000042546777,0.00018588964],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00076833647,0.00010490233,0.0002847821,0.000035109053,0.00008985108,0.00007491937,0.00078723364,0.000050242845,0.00023739193],"category_scores_gemma":[0.0003040899,0.000084705796,0.000025178857,0.00024448556,0.00049356965,0.00035272082,0.0015673501,0.00014494709,0.00006554864],"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":[0.00034019336,0.0013483706,0.17487115,0.00062636414,0.00027455983,0.00012653181,0.0027423666,0.00000908821,0.14436086,0.00011670974,0.5763081,0.09887575],"study_design_scores_gemma":[0.004119399,0.0016770521,0.35935068,0.00026847795,0.0007855925,0.0000219103,0.0021058095,0.06223166,0.001389718,0.00014751259,0.56722873,0.00067348947],"about_ca_topic_score_codex":0.00008084012,"about_ca_topic_score_gemma":0.000014823659,"teacher_disagreement_score":0.18447952,"about_ca_system_score_codex":0.000011214555,"about_ca_system_score_gemma":0.00023247328,"threshold_uncertainty_score":0.3454202},"labels":[],"label_agreement":null},{"id":"W3013353379","doi":"10.1038/s41597-020-0446-2","title":"A global ensemble of ocean wave climate projections from CMIP5-driven models","year":2020,"lang":"en","type":"article","venue":"Scientific Data","topic":"Ocean Waves and Remote Sensing","field":"Earth and Planetary Sciences","cited_by":96,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Environment and Climate Change Canada","funders":"Lawrence Berkeley National Laboratory; Biological and Environmental Research; Japan Society for the Promotion of Science; Office of Science; Ministry of Education, Culture, Sports, Science and Technology; U.S. Department of Energy; Commonwealth Scientific and Industrial Research Organisation; National Energy Research Scientific Computing Center","keywords":"Downscaling; Climatology; Environmental science; Coupled model intercomparison project; Metadata; Climate model; Climate change; Significant wave height; Wind wave model; Wave model; Scale (ratio); Meteorology; Wind wave; Wind speed; Computer science; Geography; Geology; Cartography; Precipitation","score_opus":0.10439511858755074,"score_gpt":0.2496939400140287,"score_spread":0.14529882142647796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3013353379","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":[0.90243435,0.00039840947,0.0020817341,0.001065485,0.002503736,0.00039695343,0.07179835,0.00013464487,0.019186333],"genre_scores_gemma":[0.9817755,0.000021777392,0.010240166,0.00010661219,0.00013558262,2.3408997e-9,0.007624902,0.0000031430848,0.00009229064],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984007,0.00004680826,0.00024635842,0.000661475,0.00034075443,0.0003039113],"domain_scores_gemma":[0.9988583,0.000032704138,0.00010094503,0.0007797139,0.00005151429,0.0001768448],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025032548,0.000109188404,0.00017448395,0.00003760029,0.0002792023,0.00021473318,0.000600413,0.0000443113,0.00026088321],"category_scores_gemma":[0.000047964437,0.00008787058,0.000046458405,0.0005996716,0.00021553013,0.0005160299,0.00019880595,0.000075521806,0.00013205493],"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":[0.00043047834,0.00028385175,0.07232711,0.00041875461,0.0004074468,0.00026090647,0.009281403,0.14443809,0.0022909143,0.0011876823,0.44863176,0.3200416],"study_design_scores_gemma":[0.00015323874,0.000034368695,0.0047648377,0.00002743764,0.00003111795,0.000006580375,0.0005418506,0.9872496,0.00007007858,0.0014623883,0.0055318396,0.00012662119],"about_ca_topic_score_codex":0.001400181,"about_ca_topic_score_gemma":0.0013613998,"teacher_disagreement_score":0.8428116,"about_ca_system_score_codex":0.0000033341892,"about_ca_system_score_gemma":0.000100291254,"threshold_uncertainty_score":0.35832584},"labels":[],"label_agreement":null},{"id":"W3013517662","doi":"10.1038/s41597-020-0445-3","title":"A global database of Holocene paleotemperature records","year":2020,"lang":"en","type":"article","venue":"Scientific Data","topic":"Geology and Paleoclimatology Research","field":"Earth and Planetary Sciences","cited_by":300,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Okanagan University College; University of British Columbia, Okanagan Campus; Bishop's University; Okanagan College; Geological Survey of Canada; University of Ottawa; University of New Brunswick; Center for Northern Studies; Concordia University; Université du Québec à Montréal; University of British Columbia; Fisheries and Oceans Canada; Mount Royal University; Université Laval; Natural Resources Canada","funders":"National Oceanic and Atmospheric Administration; Sight Research UK; Climate Program Office; Heising-Simons Foundation; Past Global Changes; Natural Environment Research Council; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Holocene; Paleoclimatology; Proxy (statistics); Peat; Database; Geology; Context (archaeology); Physical geography; Climate change; Northern Hemisphere; Climatology; Oceanography; Geography; Archaeology; Paleontology","score_opus":0.06975029518787,"score_gpt":0.29128594666734886,"score_spread":0.22153565147947885,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3013517662","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":[0.95152587,0.0017537514,0.0000755804,0.003299765,0.0011857993,0.00017048886,0.03174489,0.000037875496,0.010205984],"genre_scores_gemma":[0.9739671,0.00003054247,0.0013434364,0.00025447822,0.00005814564,2.241818e-7,0.02417461,9.89076e-7,0.00017050725],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9984072,0.00013523895,0.00018941214,0.0006613941,0.00028978847,0.0003169554],"domain_scores_gemma":[0.99848956,0.0000763773,0.000056576137,0.0011078645,0.00006123266,0.00020841972],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008592359,0.000091017915,0.00016602069,0.000038922113,0.000195972,0.00006820965,0.0016598357,0.00008297205,0.00538217],"category_scores_gemma":[0.00044785763,0.00007335242,0.000024222429,0.00083912275,0.0006370526,0.00034086328,0.00023215011,0.00016370042,0.00071310025],"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":[0.000046363766,0.000010364796,0.91686237,0.00003652572,0.000010721294,0.00003619702,0.000044331227,0.000021643098,0.00001303701,0.000040026578,0.08189814,0.0009803061],"study_design_scores_gemma":[0.00047279708,0.00013076949,0.95062864,0.000027473241,0.000028667298,0.00006713653,0.00019913014,0.013787998,0.00014150246,0.0003799875,0.03391569,0.00022020604],"about_ca_topic_score_codex":0.000111148474,"about_ca_topic_score_gemma":0.001970656,"teacher_disagreement_score":0.047982447,"about_ca_system_score_codex":3.2873237e-7,"about_ca_system_score_gemma":0.00016036106,"threshold_uncertainty_score":0.995527},"labels":[],"label_agreement":null},{"id":"W3017300021","doi":"10.1038/s41597-020-0465-z","title":"FiCli, the Fish and Climate Change Database, informs climate adaptation and management for freshwater fishes","year":2020,"lang":"en","type":"article","venue":"Scientific Data","topic":"Fish Ecology and Management Studies","field":"Environmental Science","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ministry of Natural Resources and Forestry","funders":"","keywords":"Climate change; Adaptation (eye); Environmental resource management; Geography; Climate change adaptation; Fish <Actinopterygii>; Effects of global warming; Database; Freshwater fish; Ecology; Global warming; Fishery; Environmental science; Biology; Computer science","score_opus":0.0835278061003806,"score_gpt":0.25542169910849427,"score_spread":0.17189389300811367,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3017300021","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":[0.52314055,0.00060118677,0.0045189993,0.3131646,0.0057008606,0.017610643,0.093125686,0.00073173095,0.04140576],"genre_scores_gemma":[0.7706281,0.017508974,0.044100046,0.11824585,0.0006558733,0.0022503946,0.042217545,0.0001098352,0.0042834026],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988231,0.00001622425,0.00014558322,0.0005574941,0.00015507282,0.0003025001],"domain_scores_gemma":[0.9993121,0.00004331119,0.000059484137,0.0005252444,0.000004827267,0.000055042998],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00077991036,0.0001026674,0.00008898325,0.00002076372,0.00080462755,0.00021420897,0.00050593837,0.000020332836,0.00021403645],"category_scores_gemma":[0.000043235203,0.00006932089,0.000010640535,0.00014416494,0.0004419627,0.0009852882,0.004087463,0.000045364646,0.00008373364],"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":[0.000034506797,0.0000200714,0.020597382,0.00019089306,0.000026058398,0.0000031509303,0.0013921211,0.000007771709,0.000012586175,0.0005662006,0.9620616,0.015087704],"study_design_scores_gemma":[0.00039207801,0.000040648498,0.10885558,0.000015510097,0.00006711105,8.174536e-7,0.001336561,0.021368006,0.000012447655,0.00016140849,0.86760527,0.00014452952],"about_ca_topic_score_codex":0.000020122348,"about_ca_topic_score_gemma":0.0072972584,"teacher_disagreement_score":0.24748755,"about_ca_system_score_codex":0.000008037446,"about_ca_system_score_gemma":9.91449e-7,"threshold_uncertainty_score":0.61886257},"labels":[],"label_agreement":null},{"id":"W3018678682","doi":"10.1038/s41597-020-0467-x","title":"Simultaneous human intracerebral stimulation and HD-EEG, ground-truth for source localization methods","year":2020,"lang":"en","type":"article","venue":"Scientific Data","topic":"Advanced MRI Techniques and Applications","field":"Medicine","cited_by":74,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Sleep & Circadian Network; Université de Montréal; Hôpital du Sacré-Cœur de Montréal","funders":"Horizon 2020 Framework Programme; European Commission; Ministero della Salute; Università degli Studi di Milano","keywords":"Electroencephalography; Ground truth; Computer science; Epilepsy; Artificial intelligence; Clinical Practice; Ranging; Range (aeronautics); Sensitivity (control systems); Human brain; Pattern recognition (psychology); Neuroscience; Medicine; Psychology; Materials science","score_opus":0.10995956128060774,"score_gpt":0.43888664130918353,"score_spread":0.3289270800285758,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3018678682","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":[0.003626371,0.00006844311,0.99390775,0.0009161783,0.000080482794,0.00071337377,0.00042014386,0.0001780654,0.00008919502],"genre_scores_gemma":[0.48859164,0.000005543648,0.5013641,0.000375066,0.00014732644,0.000028997023,0.008683087,0.000024871133,0.000779342],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99886495,0.000023348028,0.00021471223,0.0005986271,0.00014573723,0.00015261238],"domain_scores_gemma":[0.9988223,0.00015394845,0.000085660664,0.00069578516,0.000106958716,0.0001353585],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043350068,0.000093660536,0.0001489479,0.00004788856,0.00035249034,0.00011740042,0.0002234393,0.00005199871,0.00003865657],"category_scores_gemma":[0.0006090576,0.00008654237,0.000020275576,0.00030255155,0.00015974022,0.00020904993,0.00021999794,0.00007933566,0.000006289254],"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":[0.00018938229,0.00030725414,0.0004286743,0.00045348023,0.00004103967,0.0000054396014,0.0016714509,0.012265337,0.11510152,0.02349286,0.055851467,0.79019207],"study_design_scores_gemma":[0.00042659315,0.00008789991,0.00007861183,0.000020490475,0.00007235783,0.0000057661864,0.00015579729,0.73972213,0.0022574223,0.003928774,0.25313962,0.00010456646],"about_ca_topic_score_codex":0.0000080496475,"about_ca_topic_score_gemma":0.000004929698,"teacher_disagreement_score":0.7900875,"about_ca_system_score_codex":0.000021560974,"about_ca_system_score_gemma":0.000028889066,"threshold_uncertainty_score":0.35290954},"labels":[],"label_agreement":null},{"id":"W3021219695","doi":"10.1038/s41597-020-0477-8","title":"COVID-19 Disease Map, building a computational repository of SARS-CoV-2 virus-host interaction mechanisms","year":2020,"lang":"en","type":"article","venue":"Scientific Data","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":153,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Institute for Cancer Research","funders":"National Institute of General Medical Sciences; Agence Nationale de la Recherche","keywords":"Pandemic; Coronavirus disease 2019 (COVID-19); Host (biology); Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Virology; 2019-20 coronavirus outbreak; Virus; Biology; Disease; Computational biology; Outbreak; Infectious disease (medical specialty); Medicine; Genetics","score_opus":0.14070240531308462,"score_gpt":0.3903484463825193,"score_spread":0.2496460410694347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3021219695","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":[0.007119818,0.000063796615,0.9834698,0.0051925913,0.0024892222,0.00022470945,0.0012020249,0.00015820663,0.00007986965],"genre_scores_gemma":[0.46295246,9.1386556e-7,0.53267086,0.0028173116,0.00013357124,0.000010650427,0.0013293313,0.000018397328,0.00006650958],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967549,0.00031815562,0.00048179302,0.0012855047,0.0009301557,0.0002295321],"domain_scores_gemma":[0.99719405,0.00046039294,0.00030205175,0.001480494,0.00017298214,0.00039004977],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013343093,0.00016338722,0.00019227473,0.00020630093,0.0003778652,0.00069207593,0.0031509274,0.000030741183,0.000018955328],"category_scores_gemma":[0.0012828243,0.00017296965,0.00007717561,0.00094958715,0.00020605298,0.0019860326,0.0027018462,0.00014454823,0.000063595624],"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":[0.0002083813,0.00045493015,0.00008449609,0.00049766136,0.00011625222,0.00018348494,0.0027811404,0.23827156,0.33630258,0.23552887,0.17995809,0.0056125657],"study_design_scores_gemma":[0.00023965292,0.000024591614,0.0002102571,0.000029407287,0.000016544487,0.000010857586,0.00003723004,0.92427874,0.016748706,0.030047396,0.028166784,0.00018981645],"about_ca_topic_score_codex":0.00005472239,"about_ca_topic_score_gemma":0.0000054478996,"teacher_disagreement_score":0.6860072,"about_ca_system_score_codex":0.00011426846,"about_ca_system_score_gemma":0.001153222,"threshold_uncertainty_score":0.7053498},"labels":[],"label_agreement":null},{"id":"W3024722698","doi":"10.1038/s41597-020-0486-7","title":"The TRUST Principles for digital repositories","year":2020,"lang":"en","type":"article","venue":"Scientific Data","topic":"Research Data Management Practices","field":"Computer Science","cited_by":390,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ocean Networks Canada Society; University of Victoria","funders":"National Institute of Biomedical Imaging and Bioengineering; National Institute of Diabetes and Digestive and Kidney Diseases; Economic and Social Research Council","keywords":"World Wide Web; Computer science; Metadata; Scholarly communication; Data science; Internet privacy; Knowledge management; Publishing; Political science","score_opus":0.2872569636919766,"score_gpt":0.3757555810503705,"score_spread":0.08849861735839387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3024722698","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":[0.00055632455,0.00043943457,0.9210995,0.06060238,0.0037909069,0.00096588593,0.0029899115,0.0003062158,0.009249465],"genre_scores_gemma":[0.33624765,0.000683527,0.33517107,0.0023227911,0.004216848,0.0004623708,0.020623216,0.00013046096,0.30014205],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978414,0.00003923405,0.00020628878,0.00096672383,0.0006246713,0.00032163932],"domain_scores_gemma":[0.9943673,0.0004363721,0.000115271345,0.0048468993,0.00010484731,0.00012933313],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":["scholarly_communication","open_science"],"category_scores_codex":[0.0021477712,0.00007645638,0.00006558477,0.000031548683,0.0009497717,0.038372423,0.015265726,0.000013048014,0.0000019674528],"category_scores_gemma":[0.006170863,0.000050607465,0.000023469138,0.0006003391,0.0002592145,0.040000178,0.01025894,0.00008066493,0.00007849642],"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":[0.0000182429,0.000029928793,0.00019681067,0.000037075853,0.000034816898,0.000010054145,0.00024888478,0.0000073826836,0.00018879249,0.42583832,0.51791066,0.055479016],"study_design_scores_gemma":[0.00007565916,0.000024418883,0.0001751642,0.0000030989454,0.000003187548,0.0000011731538,0.000079109515,0.046195887,0.00023601766,0.00058139116,0.9525578,0.00006707858],"about_ca_topic_score_codex":0.0000036391814,"about_ca_topic_score_gemma":0.000009160065,"teacher_disagreement_score":0.5859284,"about_ca_system_score_codex":0.000011219001,"about_ca_system_score_gemma":0.00012214547,"threshold_uncertainty_score":0.9977459},"labels":[{"model":"gemma","categories":["metaresearch","open_science"],"domain":"reproducibility","study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":["scholarly_communication","open_science"],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W3026775718","doi":"10.1038/s41597-020-0489-4","title":"The Ontario Climate Data Portal, a user-friendly portal of Ontario-specific climate projections","year":2020,"lang":"en","type":"article","venue":"Scientific Data","topic":"Climate variability and models","field":"Environmental Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada; Ministère de l’Environnement, de la Protection de la nature et des Parcs; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Climate change; User Friendly; Internet portal; Geography; Physical geography; Environmental science; Environmental resource management; Computer science; World Wide Web; Data science; Ecology; Biology; The Internet","score_opus":0.09271490599768245,"score_gpt":0.2789525976296391,"score_spread":0.18623769163195664,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3026775718","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":[0.9057818,0.00010247133,0.0006474297,0.0021526988,0.0034969067,0.0018242561,0.033035252,0.00021865632,0.05274053],"genre_scores_gemma":[0.9080585,0.00032539977,0.02387653,0.000502545,0.00022249272,0.00008535748,0.05478015,0.000127325,0.012021698],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99562067,0.00007397833,0.00077056815,0.001873442,0.0008823748,0.00077898905],"domain_scores_gemma":[0.993137,0.00008688863,0.0003105234,0.0061752214,0.00003089874,0.00025949185],"candidate_categories":["open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0029348037,0.0002496042,0.00028174013,0.000037878126,0.0012995412,0.00055260485,0.0049260426,0.00008078402,0.007599035],"category_scores_gemma":[0.00014021367,0.00019141518,0.000073178744,0.00068395317,0.0011607069,0.001757009,0.009353598,0.00037092302,0.0007527718],"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":[0.00022207694,0.00081656565,0.1124793,0.00008636806,0.00008603453,0.000059071568,0.008704473,0.0006005978,0.0047170217,0.0026179468,0.86683714,0.002773414],"study_design_scores_gemma":[0.00027991302,0.000065777866,0.012189194,0.000018549814,0.000058834732,0.00001714975,0.00052592676,0.0047801593,0.000087290166,0.00010200747,0.9816126,0.00026259312],"about_ca_topic_score_codex":0.06540127,"about_ca_topic_score_gemma":0.8373792,"teacher_disagreement_score":0.77197796,"about_ca_system_score_codex":0.00022785019,"about_ca_system_score_gemma":0.00042062087,"threshold_uncertainty_score":0.9995152},"labels":[],"label_agreement":null},{"id":"W3028338699","doi":"10.1038/s41597-020-0488-5","title":"Global high-resolution emissions of soil NOx, sea salt aerosols, and biogenic volatile organic compounds","year":2020,"lang":"en","type":"article","venue":"Scientific Data","topic":"Atmospheric chemistry and aerosols","field":"Earth and Planetary Sciences","cited_by":186,"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 Natural Science Foundation of China","keywords":"Environmental science; NOx; Pollutant; Air quality index; Methane; Greenhouse gas; Pollution; Air pollution; Sea salt; Atmospheric sciences; Climate change; Environmental chemistry; Carbon cycle; Atmosphere (unit); Aerosol; Meteorology; Oceanography; Ecosystem; Chemistry; Ecology; Geography; Geology","score_opus":0.030461318930859977,"score_gpt":0.22887825537623427,"score_spread":0.19841693644537428,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3028338699","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":[0.9812317,0.0007218271,0.0006525763,0.0007428744,0.00052137097,0.00011250923,0.014957778,0.000059277412,0.0010000819],"genre_scores_gemma":[0.9895688,0.00001817696,0.0015159129,0.0000803412,0.00009535436,1.9160527e-7,0.008426797,0.000002625167,0.00029174855],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9984907,0.000035304696,0.00024937108,0.0006371785,0.0003257917,0.00026167443],"domain_scores_gemma":[0.9988076,0.00004681241,0.00011112422,0.0007009308,0.00004143335,0.00029208622],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002920837,0.00012803652,0.00017653663,0.000004130512,0.00033708857,0.0001660634,0.00082302175,0.00006408383,0.002210029],"category_scores_gemma":[0.00014614576,0.000110185756,0.000026901213,0.00070592714,0.00037863036,0.00035017682,0.0002482316,0.00008322485,0.00011215753],"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":[0.00011488176,0.00009938488,0.52653533,0.00021656623,0.000079757985,0.000018499699,0.0003057123,0.0008433023,0.0822648,0.000053964843,0.38204378,0.007424003],"study_design_scores_gemma":[0.0026261306,0.0003831475,0.4331753,0.00021015208,0.00029273523,0.00009672045,0.0010978428,0.4168523,0.026830463,0.001439293,0.11539002,0.001605903],"about_ca_topic_score_codex":0.00066561514,"about_ca_topic_score_gemma":0.0008482185,"teacher_disagreement_score":0.41600898,"about_ca_system_score_codex":0.000004661628,"about_ca_system_score_gemma":0.00017575291,"threshold_uncertainty_score":0.9987021},"labels":[],"label_agreement":null},{"id":"W3033693292","doi":"10.1038/s41597-020-00712-x","title":"The Building Data Genome Project 2, energy meter data from the ASHRAE Great Energy Predictor III competition","year":2020,"lang":"en","type":"article","venue":"Scientific Data","topic":"Building Energy and Comfort Optimization","field":"Engineering","cited_by":223,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Ministry of Education, India; National Research Foundation","keywords":"ASHRAE 90.1; Benchmarking; Data set; Range (aeronautics); Energy (signal processing); Competition (biology); Metre; Measure (data warehouse)","score_opus":0.07491076497867988,"score_gpt":0.2493241337972274,"score_spread":0.17441336881854752,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3033693292","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":[0.003593938,0.006104938,0.90085304,0.0026512083,0.0072307372,0.00039097367,0.076191366,0.0012013639,0.0017824274],"genre_scores_gemma":[0.5166982,0.0013418271,0.012518435,0.000958526,0.0025132147,0.000046423338,0.46460924,0.0001542944,0.0011598691],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99767476,0.00009723365,0.00033237797,0.0010824184,0.00046409888,0.00034912943],"domain_scores_gemma":[0.9923994,0.00019707231,0.00007999819,0.007195039,0.000040179726,0.0000883004],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0007875249,0.00021173799,0.00016610976,0.00004433107,0.00073829753,0.00096847315,0.0087627685,0.000073897434,0.00011239895],"category_scores_gemma":[0.00013275897,0.00013942904,0.000024144238,0.0006140445,0.00019840403,0.0013418752,0.0050334334,0.00016725689,0.000009308725],"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":[0.00004205512,0.000033153465,0.000046231602,0.000021744852,0.0003536862,0.000008131302,0.00021486722,0.0690918,0.005046068,0.008212982,0.90110266,0.015826596],"study_design_scores_gemma":[0.00011143127,0.000004080705,0.000021559057,0.000012744732,0.000039972485,0.0000012484643,0.000027812137,0.50203854,0.00016404934,0.0001011078,0.49736992,0.00010756299],"about_ca_topic_score_codex":0.00048369213,"about_ca_topic_score_gemma":0.0009921989,"teacher_disagreement_score":0.88833463,"about_ca_system_score_codex":0.00002764338,"about_ca_system_score_gemma":0.000079904596,"threshold_uncertainty_score":0.9966003},"labels":[],"label_agreement":null},{"id":"W3035205089","doi":"10.1038/s41597-020-00611-1","title":"Publisher Correction: A global database of Holocene paleotemperature records","year":2020,"lang":"en","type":"erratum","venue":"Scientific Data","topic":"Geology and Paleoclimatology Research","field":"Earth and Planetary Sciences","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":"Okanagan University College; University of British Columbia, Okanagan Campus; Bishop's University; Okanagan College; Geological Survey of Canada; University of Ottawa; University of New Brunswick; Center for Northern Studies; Concordia University; Université du Québec à Montréal; University of British Columbia; Fisheries and Oceans Canada; Mount Royal University; Université Laval; Natural Resources Canada","funders":"","keywords":"Holocene; Database; Information retrieval; Geology; Computer science; Oceanography","score_opus":0.04864310150019533,"score_gpt":0.282948224771884,"score_spread":0.2343051232716887,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3035205089","genre_codex":"editorial","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010432568,0.012467789,0.00002551728,0.003196693,0.58161736,0.00054859754,0.054315757,0.00011734251,0.3466677],"genre_scores_gemma":[0.011069285,0.0005014917,0.00061258976,0.00028724625,0.0013245574,0.0000021582869,0.63714,0.000008923246,0.34905377],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99573815,0.00038560768,0.0004949851,0.0018306718,0.00086859456,0.00068200484],"domain_scores_gemma":[0.99575114,0.00014874045,0.00028069672,0.0032130212,0.00025965393,0.00034675875],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00179662,0.00033781774,0.00059667224,0.00019461832,0.0004610623,0.0004783559,0.0042837085,0.00082229316,0.012001239],"category_scores_gemma":[0.0013331295,0.0002870743,0.00009252821,0.0018004328,0.0013547379,0.0008775104,0.0006515458,0.0017816728,0.0013047179],"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":[0.00004155437,0.000017864902,0.35206786,0.00012469028,0.00004211314,0.00008157727,0.000017524419,0.0000026877788,1.0130789e-7,0.0000044479234,0.6466642,0.000935358],"study_design_scores_gemma":[0.00020520974,0.00008261947,0.07110734,0.00014108478,0.00007257533,0.00015059917,0.00008592045,0.002289272,8.332159e-7,0.00022589967,0.9253254,0.00031323155],"about_ca_topic_score_codex":0.00053147535,"about_ca_topic_score_gemma":0.0153915025,"teacher_disagreement_score":0.58282423,"about_ca_system_score_codex":0.0000028844372,"about_ca_system_score_gemma":0.00137101,"threshold_uncertainty_score":0.99995816},"labels":[],"label_agreement":null},{"id":"W3036205451","doi":"10.1038/s41597-020-0533-4","title":"Massive online data annotation, crowdsourcing to generate high quality sleep spindle annotations from EEG data","year":2020,"lang":"en","type":"article","venue":"Scientific Data","topic":"Obstructive Sleep Apnea Research","field":"Medicine","cited_by":51,"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; Canadian Sleep & Circadian Network","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Crowdsourcing; Annotation; Computer science; Electroencephalography; Data quality; Quality (philosophy); Metadata; Information retrieval; Data science; World Wide Web; Artificial intelligence; Biology; Neuroscience","score_opus":0.2777290831394593,"score_gpt":0.4268230892464325,"score_spread":0.14909400610697315,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3036205451","genre_codex":"empirical","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.50070006,0.00021928076,0.038955078,0.033231743,0.0015463195,0.0011148959,0.42394227,0.00017311046,0.00011724675],"genre_scores_gemma":[0.39243457,0.000004225814,0.06902944,0.001274928,0.00079354644,0.0000082680335,0.5360643,0.000049080223,0.00034161733],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99342304,0.0002902735,0.0007720943,0.0033321758,0.0015586427,0.00062379637],"domain_scores_gemma":[0.9842131,0.0002541081,0.00023193863,0.013748973,0.00072281563,0.0008290737],"candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.002054015,0.00028063878,0.00046439242,0.00024406638,0.0005636942,0.00071568356,0.006731638,0.00009018746,0.0009845587],"category_scores_gemma":[0.007791804,0.0002696115,0.000030297668,0.0020942283,0.00041009442,0.0019703654,0.012014014,0.00046813916,0.0011207846],"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":[0.00048210047,0.0009458443,0.011491579,0.00022983867,0.0006950647,0.00021732056,0.0025106224,0.00059269695,0.26300737,0.00038451247,0.6289321,0.090510905],"study_design_scores_gemma":[0.00405739,0.00020084245,0.21199605,0.00013176513,0.00055694464,0.000009587124,0.0042022867,0.53731954,0.0068653068,0.00032720316,0.23333214,0.0010009347],"about_ca_topic_score_codex":0.001115075,"about_ca_topic_score_gemma":0.0008414265,"teacher_disagreement_score":0.5367269,"about_ca_system_score_codex":0.00009124074,"about_ca_system_score_gemma":0.00035640204,"threshold_uncertainty_score":0.9999756},"labels":[],"label_agreement":null},{"id":"W3036577737","doi":"10.1038/s41597-020-0529-0","title":"Plant traits and vegetation data from climate warming experiments along an 1100 m elevation gradient in Gongga Mountains, China","year":2020,"lang":"en","type":"article","venue":"Scientific Data","topic":"Species Distribution and Climate Change","field":"Environmental Science","cited_by":27,"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":"Chinese Academy of Sciences; National Natural Science Foundation of China; University of Arizona","keywords":"Elevation (ballistics); China; Vegetation (pathology); Physical geography; Environmental science; Global warming; Climate change; Ecology; Geology; Geography; Biology","score_opus":0.1121294371311376,"score_gpt":0.3025631863235091,"score_spread":0.1904337491923715,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3036577737","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":[0.9830745,0.000120282755,0.00011262913,0.00032214075,0.00029365713,0.0002275104,0.015423929,0.00004336333,0.0003819829],"genre_scores_gemma":[0.9283027,0.000045019027,0.00025610856,0.00016417317,0.000036983954,0.0000065245604,0.07116767,0.000009169672,0.00001162666],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9978317,0.00006169637,0.00027194028,0.0011156854,0.0004080626,0.00031093435],"domain_scores_gemma":[0.9988717,0.000016747164,0.00009496808,0.0008328696,0.0000056271247,0.00017809833],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000636764,0.0001331028,0.0001235167,0.00003597847,0.0002510615,0.0003294607,0.0011606205,0.000039799284,0.0022128173],"category_scores_gemma":[0.000101192636,0.00013080765,0.000008845112,0.000359835,0.00017899224,0.0018294458,0.0016296974,0.00008990381,0.00034566125],"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":[0.00032754824,0.0015560257,0.3268274,0.0001727223,0.000056737365,0.00011713999,0.03723612,0.0002547536,0.44099364,0.0013302213,0.1302183,0.060909405],"study_design_scores_gemma":[0.00069812464,0.000037346308,0.884202,0.000029664672,0.000017025537,0.0000023852,0.00417891,0.08539985,0.0017082627,0.00005850459,0.023388678,0.00027927055],"about_ca_topic_score_codex":0.0006695628,"about_ca_topic_score_gemma":0.003483628,"teacher_disagreement_score":0.55737454,"about_ca_system_score_codex":0.00014822616,"about_ca_system_score_gemma":0.000011232623,"threshold_uncertainty_score":0.9986993},"labels":[],"label_agreement":null},{"id":"W3036636131","doi":"10.1038/s41597-020-0522-7","title":"The Fire and Tree Mortality Database, for empirical modeling of individual tree mortality after fire","year":2020,"lang":"en","type":"article","venue":"Scientific Data","topic":"Fire effects on ecosystems","field":"Environmental Science","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Sport Centre Pacific; Natural Resources Canada; Canadian Forest Service","funders":"U.S. Forest Service; Joint Fire Science Program; Rocky Mountain Research Station; U.S. Department of Agriculture","keywords":"Woodland; Geography; Tree (set theory); Ecology; Fire regime; Range (aeronautics); Database; Environmental resource management; Environmental science; Biology; Computer science; Ecosystem; Mathematics","score_opus":0.11759719441126627,"score_gpt":0.3233541803086803,"score_spread":0.20575698589741404,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3036636131","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":[0.98218125,0.0002729192,0.0009819942,0.0007099421,0.00047463772,0.0006988384,0.014434047,0.00003759683,0.0002087676],"genre_scores_gemma":[0.99710816,0.000009705556,0.0006568662,0.00015151766,0.00006961858,0.000045690616,0.0018464506,0.00001613466,0.00009583829],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997044,0.00012928786,0.00044769628,0.001127858,0.00086245406,0.00038867482],"domain_scores_gemma":[0.9972686,0.00020212487,0.0001361208,0.0021569273,0.000017656848,0.00021856072],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023772179,0.00018406085,0.00024111124,0.000013040117,0.00040578045,0.00030336046,0.0018765985,0.00006300805,0.00011766239],"category_scores_gemma":[0.0005957133,0.00013288633,0.000056970723,0.000381035,0.00065122906,0.0007691503,0.002620211,0.00013694316,0.000050771432],"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":[0.00020122694,0.00035229203,0.4672037,0.0005149388,0.00023267086,0.000024070005,0.0026262444,0.00051395316,0.0025415455,0.000029677281,0.3924203,0.13333938],"study_design_scores_gemma":[0.0003174134,0.000047182828,0.10197793,0.00002495588,0.000089716355,0.0000016756294,0.00014617025,0.8831333,0.00015595807,0.00009295254,0.013818999,0.00019374416],"about_ca_topic_score_codex":0.0004262713,"about_ca_topic_score_gemma":0.0031857283,"teacher_disagreement_score":0.8826193,"about_ca_system_score_codex":0.000030009804,"about_ca_system_score_gemma":0.000039397906,"threshold_uncertainty_score":0.54189473},"labels":[],"label_agreement":null},{"id":"W3037249913","doi":"10.1038/s41597-020-0551-2","title":"The BenBioDen database, a global database for meio-, macro- and megabenthic biomass and densities","year":2020,"lang":"en","type":"article","venue":"Scientific Data","topic":"Marine Biology and Ecology Research","field":"Earth and Planetary Sciences","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bedford Institute of Oceanography; Fisheries and Oceans Canada; Memorial University of Newfoundland; Université Laval; ArcticNet; St. Francis Xavier University; Université du Québec à Chicoutimi","funders":"Executive Agency for Small and Medium-sized Enterprises; Universität Rostock; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; European Commission; ArcticNet","keywords":"Benthic zone; Fauna; Biomass (ecology); Database; Environmental science; Bioturbation; Oceanography; Ecosystem; Benthos; Ecology; Macrobenthos; Abundance (ecology); Biology; Geology; Computer science; Sediment; Paleontology","score_opus":0.08922836685675936,"score_gpt":0.297443035589597,"score_spread":0.20821466873283764,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3037249913","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":[0.84253114,0.008211646,0.00026446287,0.018244186,0.0018084712,0.0009690327,0.12692451,0.00007853642,0.0009680092],"genre_scores_gemma":[0.9474111,0.00037008006,0.0015934396,0.00076001365,0.0002176495,0.000005594343,0.048627805,0.000004096813,0.0010102228],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984482,0.00010461494,0.0001507314,0.0007262433,0.0001721342,0.00039810743],"domain_scores_gemma":[0.9985661,0.00040766576,0.000042345568,0.00072313315,0.000042645483,0.00021811924],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018391185,0.00010615501,0.00012260705,0.000024735959,0.0012640111,0.0004533095,0.000934479,0.00005295577,0.0002513659],"category_scores_gemma":[0.0006504908,0.00006908938,0.000012789119,0.0002193515,0.0012530914,0.00041859434,0.0007779934,0.0001056664,0.00007542834],"study_design_candidate":"observational","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":[0.00026023615,0.0000113151755,0.66474104,0.00011991956,0.00006793273,0.000020994426,0.00010582795,7.8020486e-7,0.00019400293,0.000619585,0.30791909,0.025939284],"study_design_scores_gemma":[0.00074810546,0.00016061493,0.32608658,0.000013794754,0.000065023305,0.0000623609,0.0007627382,0.06931352,0.000116062874,0.0013002664,0.6010686,0.00030230824],"about_ca_topic_score_codex":0.0005256028,"about_ca_topic_score_gemma":0.018100958,"teacher_disagreement_score":0.33865446,"about_ca_system_score_codex":0.0000018294891,"about_ca_system_score_gemma":0.00009852548,"threshold_uncertainty_score":0.9998161},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W3039006806","doi":"10.1038/s41597-020-0554-z","title":"ERA5-based global meteorological wildfire danger maps","year":2020,"lang":"en","type":"article","venue":"Scientific Data","topic":"Fire effects on ecosystems","field":"Environmental Science","cited_by":214,"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":"Horizon 2020 Framework Programme","keywords":"Environmental science; Meteorology; Earth system science; Climate change; Precipitation; Proxy (statistics); Interim; Probabilistic logic; Climatology; Environmental resource management; Computer science; Geography; Geology","score_opus":0.039449350082295526,"score_gpt":0.2532188669693745,"score_spread":0.213769516887079,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3039006806","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":[0.91941994,0.00029406068,0.0041500335,0.019636411,0.006078702,0.0017106358,0.016278988,0.00093299616,0.03149822],"genre_scores_gemma":[0.99257386,3.9612507e-7,0.0029831082,0.001868522,0.00010370747,0.000010993038,0.0021356416,0.000012350571,0.0003114054],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9970889,0.00015875565,0.00023426679,0.0013370946,0.0007364902,0.00044450042],"domain_scores_gemma":[0.9976942,0.000058535436,0.00008052434,0.0018249449,0.0000050037984,0.0003368222],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0011156542,0.00017502111,0.00018866808,0.000014015661,0.00025829693,0.00029985284,0.002509543,0.00007842884,0.0026791622],"category_scores_gemma":[0.00042953913,0.0001434838,0.000048212456,0.0008515135,0.0005065785,0.00052229484,0.0016967944,0.00013102182,0.0110966815],"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":[0.000026612941,0.000085519445,0.023919879,0.000015490334,0.000009207628,0.000050285405,0.00004894143,0.00010269316,0.005422365,0.00003398601,0.9498005,0.020484507],"study_design_scores_gemma":[0.00041800723,0.00009201654,0.019401575,0.000010465595,0.00002285694,0.0000067061806,0.000019355224,0.11013541,0.000531168,0.00012083799,0.8689462,0.00029541636],"about_ca_topic_score_codex":0.00019582354,"about_ca_topic_score_gemma":0.00019989112,"teacher_disagreement_score":0.110032715,"about_ca_system_score_codex":0.00011197679,"about_ca_system_score_gemma":0.00003232018,"threshold_uncertainty_score":0.99823254},"labels":[],"label_agreement":null},{"id":"W3040736388","doi":"10.1038/s41597-020-0563-y","title":"A database of human gait performance on irregular and uneven surfaces collected by wearable sensors","year":2020,"lang":"en","type":"article","venue":"Scientific Data","topic":"Context-Aware Activity Recognition Systems","field":"Computer Science","cited_by":119,"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":"National Institute for Occupational Safety and Health; U.S. Department of Health and Human Services","keywords":"Wearable computer; Gait; Computer science; Database; Gait analysis; Wearable technology; Physical medicine and rehabilitation; Embedded system; Medicine","score_opus":0.07286879744542986,"score_gpt":0.2707043208546184,"score_spread":0.19783552340918853,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3040736388","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":[0.9907391,0.00025485782,0.002746034,0.001005525,0.0004308206,0.0003908121,0.003664893,0.00013620393,0.000631773],"genre_scores_gemma":[0.9965807,0.000010679062,0.0008301018,0.00008392984,0.000019119256,0.000004512389,0.0007164121,0.000008775043,0.0017457434],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978037,0.00013954511,0.00028007684,0.0010023017,0.0005326249,0.00024173968],"domain_scores_gemma":[0.9976483,0.00010619221,0.0001646131,0.0018008997,0.000120813755,0.0001591592],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009209826,0.00013579565,0.00023131233,0.000105726525,0.00033923256,0.00045588578,0.0018078707,0.000035526347,0.000048041216],"category_scores_gemma":[0.00015148844,0.00013142642,0.000019152794,0.0010787094,0.00021753625,0.0014051918,0.0012530204,0.00011734878,0.00009586077],"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":[0.000040850056,0.00026403175,0.0013873013,0.00035728197,0.00007018499,0.000015815738,0.0021145637,0.000036995203,0.3478646,0.00019683145,0.63052124,0.017130328],"study_design_scores_gemma":[0.0022105747,0.0005910294,0.0038869493,0.0007503091,0.000046279987,0.000032717762,0.00057116675,0.5998737,0.2042643,0.0000863312,0.18667817,0.0010084622],"about_ca_topic_score_codex":0.00007786249,"about_ca_topic_score_gemma":0.000035136254,"teacher_disagreement_score":0.5998367,"about_ca_system_score_codex":0.00001555188,"about_ca_system_score_gemma":0.00009864348,"threshold_uncertainty_score":0.53594136},"labels":[],"label_agreement":null},{"id":"W3040739689","doi":"10.1038/s41597-020-0534-3","title":"The FLUXNET2015 dataset and the ONEFlux processing pipeline for eddy covariance data","year":2020,"lang":"en","type":"article","venue":"Scientific Data","topic":"Plant Water Relations and Carbon Dynamics","field":"Environmental Science","cited_by":1766,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; University of Manitoba; Centre de Géomatique du Québec; University of Saskatchewan; Canadian Forest Service; Environment and Climate Change Canada; University of British Columbia; University of Waterloo; Global Institute for Water Security; Université Laval; Natural Resources Canada; Ministère des Ressources naturelles et des Forêts; Ontario Drive & Gear (Canada); McMaster University","funders":"Natural Environment Research Council; Sight Research UK","keywords":"Eddy covariance; Covariance; Pipeline (software); Computer science; Data mining; Statistics; Mathematics; Biology","score_opus":0.06542144998765222,"score_gpt":0.2774303750916456,"score_spread":0.21200892510399338,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3040739689","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0040258416,0.002112384,0.28623128,0.06538685,0.0019710758,0.0030764968,0.6352821,0.00015039158,0.0017635538],"genre_scores_gemma":[0.20011958,0.00032041984,0.041832104,0.0048031947,0.00060041883,0.00008693576,0.7415663,0.00007066006,0.010600405],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99855405,0.000045683493,0.00018817741,0.0007073788,0.00028922324,0.00021547113],"domain_scores_gemma":[0.9975013,0.00013086709,0.00008321764,0.0021961175,0.000008294813,0.000080198035],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021957161,0.000089034234,0.00008708836,0.000006675333,0.00095741637,0.0007717479,0.0031471225,0.000022845203,0.00004409259],"category_scores_gemma":[0.00029436007,0.000047308014,0.000008131192,0.00025063663,0.0009211249,0.00073890964,0.0035744822,0.00009719732,0.00010671296],"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":[0.000051900963,0.000014272685,0.00008432545,0.0000102349495,0.0000064574156,8.960929e-7,0.00016339128,0.0007950507,0.00021093225,0.00030152075,0.96895874,0.029402297],"study_design_scores_gemma":[0.00022506937,0.0000021827977,0.000025028326,0.000002794233,0.000016482178,0.0000022681315,0.000024366469,0.5181462,0.000005463345,0.00026063787,0.4812468,0.00004272599],"about_ca_topic_score_codex":0.000048783026,"about_ca_topic_score_gemma":0.00025673173,"teacher_disagreement_score":0.51735115,"about_ca_system_score_codex":0.000009674654,"about_ca_system_score_gemma":0.000029647526,"threshold_uncertainty_score":0.74419826},"labels":[],"label_agreement":null},{"id":"W3041337723","doi":"10.1038/s41597-020-0520-9","title":"The International Bathymetric Chart of the Arctic Ocean Version 4.0","year":2020,"lang":"en","type":"article","venue":"Scientific Data","topic":"Geological Studies and Exploration","field":"Earth and Planetary Sciences","cited_by":311,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Hydrographic Service; Geological Survey of Canada","funders":"Stockholms Universitet; Natural Environment Research Council; Sight Research UK; Jet Propulsion Laboratory; National Aeronautics and Space Administration","keywords":"Bathymetric chart; Oceanography; Bathymetry; Chart; Arctic; The arctic; Geography; Environmental science; Geology; Mathematics; Statistics","score_opus":0.07080271622274797,"score_gpt":0.22058557326769745,"score_spread":0.14978285704494948,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3041337723","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":[0.8182402,0.0022095456,0.00017090581,0.141781,0.017589856,0.0005570404,0.005183967,0.00006334813,0.014204121],"genre_scores_gemma":[0.99855775,0.000046376957,0.00003737046,0.000239374,0.00006957585,6.3745e-8,0.00070774934,4.4084533e-7,0.00034128374],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99924105,0.000025999607,0.00009972144,0.00020437237,0.00033099556,0.000097878685],"domain_scores_gemma":[0.9994256,0.00008620717,0.00005420417,0.00035749385,0.00004165411,0.000034872948],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004895484,0.000035299865,0.000039494695,0.000012001498,0.0004706651,0.00012377888,0.0013765863,0.000010899988,0.0007107964],"category_scores_gemma":[0.00058437797,0.0000158621,0.000020362186,0.00045115297,0.00018776588,0.00015881285,0.00028468954,0.00005315402,0.0003224221],"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":[0.00003585524,0.0000148263825,0.31781378,0.000009486914,0.000023724215,9.114907e-7,0.00033546626,0.00045401976,0.00007828513,0.00018185186,0.63791525,0.04313654],"study_design_scores_gemma":[0.00008532237,0.00002823596,0.26874593,0.0000043865575,0.000007122652,5.5045973e-7,0.0005291628,0.03049988,0.00006719134,0.00039335218,0.69959724,0.0000416205],"about_ca_topic_score_codex":0.00013246427,"about_ca_topic_score_gemma":0.0002650928,"teacher_disagreement_score":0.18031755,"about_ca_system_score_codex":0.0000014542005,"about_ca_system_score_gemma":0.000015411455,"threshold_uncertainty_score":0.7782722},"labels":[],"label_agreement":null},{"id":"W3043194960","doi":"10.1038/s41597-020-00583-2","title":"A comprehensive, multisource database for hydrometeorological modeling of 14,425 North American watersheds","year":2020,"lang":"en","type":"article","venue":"Scientific Data","topic":"Hydrology and Watershed Management Studies","field":"Environmental Science","cited_by":119,"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; École de Technologie Supérieure","funders":"","keywords":"Hydrometeorology; Environmental science; Watershed; Precipitation; Hydrology (agriculture); Snow; Hydrological modelling; Climatology; Scale (ratio); Rain gauge; Database; Meteorology; Geography; Geology; Cartography; Computer science","score_opus":0.0959559339871537,"score_gpt":0.2779758610765329,"score_spread":0.1820199270893792,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3043194960","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":[0.9676414,0.000023562918,0.026997495,0.0019707805,0.00021319592,0.00045402118,0.0023137226,0.00006530272,0.00032049668],"genre_scores_gemma":[0.9870049,0.00001063976,0.009726641,0.0007257201,0.00002336592,0.000015556274,0.002343059,0.000009665505,0.00014050373],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99804616,0.000057610127,0.0002717092,0.0009602303,0.00028593492,0.0003783718],"domain_scores_gemma":[0.998716,0.00006227508,0.00009823852,0.0009797226,0.00001628173,0.00012750462],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037185775,0.00015079013,0.00026635628,0.00004295614,0.0003221539,0.000038827402,0.0013683415,0.000021697746,0.00015302609],"category_scores_gemma":[0.00013834056,0.000120674405,0.00004504421,0.00049109245,0.0011754804,0.0003421677,0.0031983352,0.00009552746,0.00019573976],"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":[0.00100935,0.0008919278,0.26372066,0.0004575526,0.00047464608,0.000059889862,0.0060956376,0.28647372,0.032547135,0.0000780684,0.3852544,0.022936989],"study_design_scores_gemma":[0.00058527704,0.00018692073,0.006052165,0.000005046363,0.000076987,0.0000010278444,0.0002748437,0.8966775,0.0003277624,0.000056034063,0.09550574,0.00025072313],"about_ca_topic_score_codex":0.00013147909,"about_ca_topic_score_gemma":0.00014278137,"teacher_disagreement_score":0.61020374,"about_ca_system_score_codex":0.000012913939,"about_ca_system_score_gemma":0.0000044987523,"threshold_uncertainty_score":0.49209595},"labels":[],"label_agreement":null},{"id":"W3043520506","doi":"10.1038/s41597-020-00589-w","title":"Author Correction: COVID-19 Disease Map, building a computational repository of SARS-CoV-2 virus-host interaction mechanisms","year":2020,"lang":"en","type":"erratum","venue":"Scientific Data","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Institute for Cancer Research","funders":"","keywords":"Coronavirus disease 2019 (COVID-19); Host (biology); Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); 2019-20 coronavirus outbreak; Computer science; Virology; Virus; Computational biology; Biology; Disease; Medicine; Infectious disease (medical specialty); Ecology; Outbreak","score_opus":0.04901385862372627,"score_gpt":0.3529667561876381,"score_spread":0.30395289756391186,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3043520506","genre_codex":"methods","genre_gemma":"dataset","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":[0.00056845683,0.0010523932,0.61778426,0.003686065,0.34836352,0.0012978148,0.021265823,0.00023412498,0.0057475325],"genre_scores_gemma":[0.01640848,0.00005273284,0.061541468,0.003267802,0.0053132838,0.0000681806,0.5852589,0.00023233815,0.3278568],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973083,0.00016247082,0.0006232425,0.0010425702,0.0006262175,0.00023720539],"domain_scores_gemma":[0.99700296,0.000040196108,0.0007551579,0.0017747902,0.00019869751,0.00022818777],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00075209385,0.00029363495,0.00027925847,0.00017934182,0.0004230351,0.00032242475,0.001437084,0.0002959384,0.00004142986],"category_scores_gemma":[0.0016551043,0.00031058514,0.00012542967,0.00026799805,0.00028580162,0.000032172542,0.0016012368,0.00058221736,0.00004862581],"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":[0.00009862504,0.000049604638,0.000007277197,0.0004333097,0.000074898766,0.000010347117,0.00008390054,0.0007474326,0.050792396,0.00009715984,0.94744927,0.00015579916],"study_design_scores_gemma":[0.00015675231,0.00006969447,0.000022710485,0.00011517767,0.00008719499,0.000027963139,0.000057454134,0.099683374,0.0067922766,0.00015181975,0.8925568,0.00027879604],"about_ca_topic_score_codex":0.00006589258,"about_ca_topic_score_gemma":0.00003271859,"teacher_disagreement_score":0.5639931,"about_ca_system_score_codex":0.000081027945,"about_ca_system_score_gemma":0.0013203003,"threshold_uncertainty_score":0.9999346},"labels":[],"label_agreement":null},{"id":"W3043668475","doi":"10.1038/s41597-020-0557-9","title":"CerebrA, registration and manual label correction of Mindboggle-101 atlas for MNI-ICBM152 template","year":2020,"lang":"en","type":"article","venue":"Scientific Data","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":117,"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":"Fonds de Recherche du Québec - Santé","keywords":"Atlas (anatomy); Computer science; Preprocessor; Brain atlas; Magnetic resonance imaging; Artificial intelligence; Pattern recognition (psychology); Medicine; Radiology; Anatomy","score_opus":0.16964929103160334,"score_gpt":0.3270970872157216,"score_spread":0.15744779618411828,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3043668475","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":[0.89410704,0.000262392,0.016367784,0.04346702,0.017771319,0.002704718,0.019085858,0.00036031543,0.005873567],"genre_scores_gemma":[0.9907138,0.000008997631,0.0012876627,0.0007995025,0.00020667852,0.000023108187,0.0006036182,0.000017705734,0.0063389665],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99820006,0.00005719277,0.00022433705,0.0010023527,0.00033722437,0.0001788287],"domain_scores_gemma":[0.9978961,0.001190884,0.00015616091,0.00060566905,0.00008046207,0.00007075346],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0005897644,0.00010814018,0.00014551256,0.0000688857,0.000419843,0.00016545388,0.00043808034,0.00003868522,0.000022889359],"category_scores_gemma":[0.010160247,0.00010562247,0.000021996855,0.00041469128,0.00034314732,0.00064740574,0.00042494753,0.00008188941,0.00003497084],"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":[0.00012207107,0.00006312756,0.00025762213,0.00007791541,0.000009447632,0.000001638361,0.00034597784,0.000016913498,0.27668568,0.00055093225,0.7133888,0.008479876],"study_design_scores_gemma":[0.0014348474,0.00047091834,0.0016909568,0.000057718065,0.000060502305,0.000025027968,0.0007197038,0.07551749,0.4091229,0.0012372794,0.5092747,0.00038790528],"about_ca_topic_score_codex":0.000021425738,"about_ca_topic_score_gemma":0.00010537359,"teacher_disagreement_score":0.20411405,"about_ca_system_score_codex":0.000015818938,"about_ca_system_score_gemma":0.000064616455,"threshold_uncertainty_score":0.9981776},"labels":[],"label_agreement":null},{"id":"W3045777412","doi":"10.1038/s41597-020-00590-3","title":"Author Correction: Global karst springs hydrograph dataset for research and management of the world’s fastest-flowing groundwater","year":2020,"lang":"en","type":"erratum","venue":"Scientific Data","topic":"Karst Systems and Hydrogeology","field":"Earth and Planetary Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"Natural Environment Research Council; Sight Research UK","keywords":"Karst; Hydrograph; Groundwater; Hydrology (agriculture); Geology; Water resource management; Environmental science; Geography; Paleontology; Archaeology; Geotechnical engineering","score_opus":0.1316815406232029,"score_gpt":0.34645248710723464,"score_spread":0.21477094648403175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3045777412","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005066296,0.0077151894,0.0002057545,0.008306739,0.46779948,0.006157866,0.4549145,0.00013582357,0.049698327],"genre_scores_gemma":[0.017595265,0.00012810457,0.0012649948,0.0001817821,0.0018849109,0.000027273927,0.36777908,0.00002730746,0.6111113],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9962556,0.0001727168,0.00048282015,0.0014921867,0.00094594975,0.00065074855],"domain_scores_gemma":[0.9971049,0.000120962046,0.00015382627,0.0023390553,0.00009517093,0.0001860899],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031654201,0.0002484583,0.00038411704,0.00022264622,0.0009878175,0.0007002973,0.0030646157,0.00016764564,0.00040924185],"category_scores_gemma":[0.000069121474,0.00017463413,0.00007567162,0.0015432275,0.0011039467,0.0003678058,0.001343873,0.0005113409,0.00012688772],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002186248,0.000019139265,0.0069066426,0.00045813966,0.00008039212,0.000012500743,0.00003622501,0.0000067843607,9.101609e-7,0.00011430442,0.9893398,0.0030032774],"study_design_scores_gemma":[0.00015601634,0.000069211004,0.009675817,0.00032462843,0.000077521094,0.000019036152,0.00014398865,0.0049356343,0.0000030589224,0.00034392034,0.98407006,0.00018109025],"about_ca_topic_score_codex":0.00230812,"about_ca_topic_score_gemma":0.035435222,"teacher_disagreement_score":0.56141293,"about_ca_system_score_codex":0.000013532059,"about_ca_system_score_gemma":0.00014345878,"threshold_uncertainty_score":0.9821656},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W3048219094","doi":"10.1038/s41597-020-00603-1","title":"A consistent Great Lakes ice cover digital data set for winters 1973–2019","year":2020,"lang":"en","type":"article","venue":"Scientific Data","topic":"Arctic and Antarctic ice dynamics","field":"Earth and Planetary Sciences","cited_by":21,"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 Oceanic and Atmospheric Administration; U.S. Department of Commerce","keywords":"Cover (algebra); Physical geography; Data set; Geology; Oceanography; Environmental science; Geography; Computer science; Engineering","score_opus":0.08784984032571287,"score_gpt":0.26159169881930355,"score_spread":0.1737418584935907,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3048219094","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06621449,0.00036268664,0.019424357,0.012071707,0.0058999984,0.0011990718,0.8846175,0.00022595361,0.009984262],"genre_scores_gemma":[0.7471811,0.000013865001,0.0022251336,0.0014607735,0.00023926405,6.333817e-7,0.24433845,0.000008137363,0.0045326077],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99792206,0.00002368454,0.00024579384,0.0010491435,0.0003752561,0.00038405013],"domain_scores_gemma":[0.997561,0.00022357269,0.000090949725,0.0018248168,0.000051134946,0.00024852782],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000539611,0.00015512836,0.00018186793,0.000037484595,0.00034397742,0.00085959584,0.0026408199,0.000040351686,0.0012076419],"category_scores_gemma":[0.0004799899,0.00012520456,0.00004293053,0.00025277914,0.0004321809,0.0017361086,0.0005975916,0.000105855666,0.0013463348],"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":[0.000101023266,0.000019114885,0.024295313,0.00007209261,0.00006434905,0.000017393506,0.00042766205,0.00014677261,0.000014001411,0.000049532882,0.948607,0.026185725],"study_design_scores_gemma":[0.00031692995,0.000060026035,0.001563068,0.00001997937,0.00005228693,0.00001602827,0.00065716705,0.24412793,0.0000024615067,0.00010224243,0.7528828,0.00019909385],"about_ca_topic_score_codex":0.00014653782,"about_ca_topic_score_gemma":0.0003350866,"teacher_disagreement_score":0.6809667,"about_ca_system_score_codex":0.0000037134637,"about_ca_system_score_gemma":0.00016273091,"threshold_uncertainty_score":0.9997054},"labels":[],"label_agreement":null},{"id":"W3048924598","doi":"10.1038/s41597-020-00594-z","title":"A comprehensive CHO SWATH-MS spectral library for robust quantitative profiling of 10,000 proteins","year":2020,"lang":"en","type":"article","venue":"Scientific Data","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","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":"Spinal Cord Injury BC","funders":"Biomedical Research Council; Agency for Science, Technology and Research","keywords":"Chinese hamster ovary cell; Computer science; Profiling (computer programming); Proteome; Computational biology; Data acquisition; Downstream (manufacturing); Biological system; Chemistry; Biology; Cell culture; Bioinformatics; Engineering","score_opus":0.1247426534309085,"score_gpt":0.32926990674785844,"score_spread":0.20452725331694993,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3048924598","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":[0.054512773,0.0005096038,0.80770564,0.0037742653,0.00018389642,0.0052368324,0.11746581,0.0009770072,0.009634174],"genre_scores_gemma":[0.015965454,0.000011171886,0.9685361,0.00006313896,0.0001125433,0.00037747383,0.013121412,0.00004144334,0.0017712654],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99857163,0.000008394968,0.00029385558,0.00072963693,0.00016279667,0.00023368464],"domain_scores_gemma":[0.99844784,0.00006614495,0.00019059725,0.0010981644,0.000096501055,0.0001007679],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000099174205,0.00013072224,0.00019095078,0.000033061828,0.00018747988,0.00011238488,0.001172842,0.000057152378,0.00052162283],"category_scores_gemma":[0.00010667997,0.00012651942,0.000054135,0.0003258686,0.0002576235,0.00047062023,0.00058964686,0.00014417325,0.000021758993],"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":[0.00013132418,0.00012277153,0.0000610683,0.0006097682,0.00003338461,0.000001664392,0.00030184977,0.00023027485,0.9332174,0.013308337,0.050413087,0.0015690585],"study_design_scores_gemma":[0.00023316378,0.000032079606,0.0000041978155,0.00004832234,0.000015255964,8.3832805e-7,0.00025315036,0.030640211,0.8099607,0.002650703,0.15600921,0.00015214086],"about_ca_topic_score_codex":0.0000050684503,"about_ca_topic_score_gemma":0.0000012607891,"teacher_disagreement_score":0.16083045,"about_ca_system_score_codex":0.00001108229,"about_ca_system_score_gemma":0.00010272943,"threshold_uncertainty_score":0.5711404},"labels":[],"label_agreement":null},{"id":"W3080864197","doi":"10.1038/s41597-020-00610-2","title":"HIT-COVID, a global database tracking public health interventions to COVID-19","year":2020,"lang":"en","type":"article","venue":"Scientific Data","topic":"COVID-19 epidemiological studies","field":"Mathematics","cited_by":115,"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; McMaster University","funders":"National Institute of General Medical Sciences; Johnson and Johnson Foundation; Johns Hopkins University","keywords":"Coronavirus disease 2019 (COVID-19); 2019-20 coronavirus outbreak; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Pandemic; Public health; Tracking (education); Global health; Geography; Data science; Computer science; Virology; Biology; Medicine; Outbreak; Infectious disease (medical specialty); Psychology; Nursing","score_opus":0.8307176163106647,"score_gpt":0.5738583493022208,"score_spread":0.25685926700844386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3080864197","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":[0.0024536029,0.00062827795,0.5601788,0.3963335,0.0010425571,0.001146302,0.03729148,0.0006479584,0.00027752822],"genre_scores_gemma":[0.5213219,0.00009799656,0.19504806,0.25764158,0.0010371496,0.0002659544,0.022959366,0.00011078786,0.001517194],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9951257,0.00056167785,0.00095957326,0.001847735,0.0006533059,0.00085200486],"domain_scores_gemma":[0.9930891,0.0014342164,0.0003472898,0.0029532441,0.00011886878,0.0020573093],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0088116005,0.00025983888,0.0005871908,0.00010510827,0.0010639431,0.00057378894,0.0031607514,0.0000574359,0.0008363055],"category_scores_gemma":[0.12959275,0.00022089819,0.00017021953,0.0019263095,0.00036554877,0.0006155177,0.0060508098,0.00023395744,0.0006210951],"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":[0.000014004953,0.00022605891,0.0017762473,0.0010424664,0.000041183004,0.000017624268,0.00081845024,0.000011138918,0.000028361896,0.020038523,0.9699677,0.0060182046],"study_design_scores_gemma":[0.0004321888,0.00009706928,0.0006225851,0.000107706604,0.000038698337,0.000006545307,0.0008224284,0.0010768672,0.000002919069,0.018765282,0.9777167,0.00031104113],"about_ca_topic_score_codex":0.00045377546,"about_ca_topic_score_gemma":0.0030335328,"teacher_disagreement_score":0.51886827,"about_ca_system_score_codex":0.0006120004,"about_ca_system_score_gemma":0.00097175175,"threshold_uncertainty_score":0.9156959},"labels":[],"label_agreement":null},{"id":"W3080911893","doi":"10.1038/s41597-020-00578-z","title":"Arctic tidal current atlas","year":2020,"lang":"en","type":"article","venue":"Scientific Data","topic":"Oceanographic and Atmospheric Processes","field":"Earth and Planetary Sciences","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Fisheries and Oceans Canada","funders":"Norges Forskningsråd; Bundesministerium für Bildung und Forschung; National Science Foundation","keywords":"Baroclinity; Current (fluid); Oceanography; Arctic; Tidal power; Environmental science; Ocean current; Submarine pipeline; Tidal range; Climatology; Geology; Estuary; Ecology","score_opus":0.07603865341572055,"score_gpt":0.25238641647405463,"score_spread":0.17634776305833408,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3080911893","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":[0.85815084,0.035797037,0.007884935,0.015656348,0.023281893,0.0011710332,0.02552326,0.001171402,0.031363264],"genre_scores_gemma":[0.99371684,0.00005774321,0.001127974,0.00025131364,0.00024213144,1.7026913e-7,0.0043178843,0.0000024274607,0.00028354515],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985734,0.00002408234,0.00014632684,0.0006319651,0.00035488213,0.00026929556],"domain_scores_gemma":[0.99900764,0.000038183727,0.00004910328,0.0006292787,0.000036395882,0.00023940318],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00030043235,0.00009684283,0.000098321645,0.000012726853,0.00025960192,0.00034076662,0.0013671174,0.000019433946,0.00368502],"category_scores_gemma":[0.00017102051,0.0000750636,0.00002604435,0.00081009377,0.0002533812,0.0005681037,0.00013294988,0.000119814475,0.0021517873],"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":[0.000022958651,0.000033049517,0.37068087,0.00015844007,0.00001659712,0.0000135658765,0.0003086006,0.00012223395,0.000022073877,0.00007461927,0.3298118,0.29873517],"study_design_scores_gemma":[0.00016138237,0.00003590633,0.05024293,0.000021975582,0.000018523384,0.0000036513131,0.00013509442,0.027299134,0.000032430944,0.00055918586,0.92129636,0.00019343896],"about_ca_topic_score_codex":0.00007589391,"about_ca_topic_score_gemma":0.00013255382,"teacher_disagreement_score":0.59148455,"about_ca_system_score_codex":8.260632e-7,"about_ca_system_score_gemma":0.00010307655,"threshold_uncertainty_score":0.99862516},"labels":[],"label_agreement":null},{"id":"W3082836448","doi":"10.1038/s41597-020-00584-1","title":"Author Correction: A global database of Holocene paleotemperature records","year":2020,"lang":"en","type":"erratum","venue":"Scientific Data","topic":"Geology and Paleoclimatology Research","field":"Earth and Planetary Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Okanagan University College; University of British Columbia, Okanagan Campus; Bishop's University; Okanagan College; Geological Survey of Canada; University of Ottawa; University of New Brunswick; Center for Northern Studies; Concordia University; Université du Québec à Montréal; University of British Columbia; Fisheries and Oceans Canada; Mount Royal University; Université Laval; Natural Resources Canada","funders":"","keywords":"Holocene; Database; Geology; Oceanography; Data science; Information retrieval; Computer science","score_opus":0.06046163971018304,"score_gpt":0.30597480834678126,"score_spread":0.24551316863659822,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3082836448","genre_codex":"editorial","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035770074,0.019169964,0.00006913809,0.0063012517,0.5705011,0.00090021273,0.22225197,0.00018589992,0.17704347],"genre_scores_gemma":[0.022197295,0.0003704586,0.0009230998,0.00021103423,0.0015022759,0.000002222797,0.61616355,0.000009087396,0.35862097],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99578464,0.00042044508,0.00050633616,0.0018020158,0.00082049944,0.0006660443],"domain_scores_gemma":[0.9958795,0.00016485761,0.00028800752,0.0031091839,0.0002052891,0.00035318878],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0018379769,0.0003402439,0.00061534083,0.00017858819,0.0005286894,0.00023571444,0.0037856232,0.0008101028,0.011265554],"category_scores_gemma":[0.001198115,0.00029163965,0.00009438123,0.0015837683,0.0013666132,0.00042302726,0.00058839854,0.0017270055,0.0017610813],"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":[0.000054684013,0.000018299417,0.28598487,0.00015651084,0.00004373744,0.000111929105,0.000026457776,0.0000041072994,3.5942952e-7,0.0000060841458,0.7124865,0.0011064457],"study_design_scores_gemma":[0.00018586188,0.000109127956,0.06716971,0.00018933136,0.00009108378,0.00018878528,0.00009969324,0.006331564,0.00000474411,0.00013048251,0.9251653,0.0003342994],"about_ca_topic_score_codex":0.00040702932,"about_ca_topic_score_gemma":0.012287542,"teacher_disagreement_score":0.5689988,"about_ca_system_score_codex":0.0000027747046,"about_ca_system_score_gemma":0.0013290407,"threshold_uncertainty_score":0.99995357},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W3085670454","doi":"10.1038/s41597-020-00652-6","title":"Structural models of human ACE2 variants with SARS-CoV-2 Spike protein for structure-based drug design","year":2020,"lang":"en","type":"article","venue":"Scientific Data","topic":"SARS-CoV-2 and COVID-19 Research","field":"Medicine","cited_by":35,"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","funders":"Bundesministerium für Bildung und Forschung; European Regional Development Fund; Deutsche Forschungsgemeinschaft","keywords":"Coronavirus; Alanine scanning; Angiotensin-converting enzyme 2; Computational biology; Missense mutation; Mutagenesis; Biology; Genome; Mutant; Indel; Genetics; Coronavirus disease 2019 (COVID-19); Mutation; Gene; Medicine; Infectious disease (medical specialty)","score_opus":0.20444825342388231,"score_gpt":0.37951834475289553,"score_spread":0.17507009132901322,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3085670454","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":[0.9582227,0.00006970453,0.033036005,0.0008887898,0.00019319322,0.0033056636,0.0040450175,0.000094270734,0.00014464368],"genre_scores_gemma":[0.97836375,3.338096e-8,0.017057009,0.0034187047,0.00011498976,0.00004127429,0.0008999753,0.000045043478,0.00005924206],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99689656,0.00008803414,0.00037642146,0.0011423171,0.0009839634,0.0005126904],"domain_scores_gemma":[0.99737775,0.000052294745,0.00015873187,0.001983585,0.0003456634,0.000081993356],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00086538546,0.00024361532,0.0004204363,0.00019254157,0.00028030958,0.00020672416,0.0014324309,0.00007873915,0.000022256192],"category_scores_gemma":[0.00027794726,0.0001790614,0.000063684085,0.000770903,0.0005147382,0.0004569684,0.00036742547,0.00023887602,0.0000108269205],"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":[0.000977599,0.00005327974,0.00016565167,0.00046109455,0.00006122672,0.000023580536,0.00038917773,0.00004424435,0.98508555,0.0003403898,0.011513257,0.0008849585],"study_design_scores_gemma":[0.002898482,0.00040401117,0.00008190343,0.00012652879,0.00007934113,0.0000053537674,0.00007554275,0.15575652,0.834271,0.0016343958,0.00445726,0.00020967092],"about_ca_topic_score_codex":0.00010221048,"about_ca_topic_score_gemma":0.00008220494,"teacher_disagreement_score":0.15571228,"about_ca_system_score_codex":0.000047749818,"about_ca_system_score_gemma":0.0009837921,"threshold_uncertainty_score":0.73019123},"labels":[],"label_agreement":null},{"id":"W3087421614","doi":"10.1038/s41597-020-00644-6","title":"A high-resolution in vivo magnetic resonance imaging atlas of the human hypothalamic region","year":2020,"lang":"en","type":"article","venue":"Scientific Data","topic":"Neonatal and fetal brain pathology","field":"Medicine","cited_by":146,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Western Hospital; University of Toronto","funders":"McDonnell Center for Systems Neuroscience; National Institutes of Health; NIH Blueprint for Neuroscience Research; Canada Research Chairs; National Institute of Mental Health; Deutsche Forschungsgemeinschaft","keywords":"Atlas (anatomy); Magnetic resonance imaging; Nuclear magnetic resonance; In vivo; Functional magnetic resonance imaging; Biology; Physics; Medicine; Neuroscience; Anatomy; Radiology","score_opus":0.03990451522155245,"score_gpt":0.26367124791062385,"score_spread":0.2237667326890714,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3087421614","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":[0.9853173,0.0028382484,0.000072742376,0.008823432,0.00070777786,0.00042959192,0.00059058436,0.000036179616,0.00118415],"genre_scores_gemma":[0.99671876,0.0000060880016,0.00028622797,0.0003689904,0.000059242837,0.0000030263216,0.00019693523,0.000007916002,0.0023528084],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9988065,0.000053744643,0.00022115176,0.0005059895,0.00023256194,0.00018010347],"domain_scores_gemma":[0.99875987,0.000022116415,0.00006799498,0.0010685137,0.000032611584,0.000048904792],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003091224,0.00007534506,0.00014896692,0.00006205836,0.00009337125,0.000018778177,0.00061261473,0.000027281265,0.00006285129],"category_scores_gemma":[0.00022797489,0.000054344495,0.000029270512,0.0005569985,0.0004952882,0.00012485405,0.00064462895,0.00014042141,0.000027342357],"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":[0.000105722174,0.0001515726,0.022633338,0.00018248828,0.0000034846453,0.0002461165,0.00085061026,0.0000044456256,0.827541,0.0021037564,0.10801058,0.038166888],"study_design_scores_gemma":[0.004275138,0.00025414783,0.6422662,0.0007067336,0.00009982953,0.0003871542,0.0004503782,0.011240448,0.042840037,0.0037569539,0.29332715,0.00039581335],"about_ca_topic_score_codex":0.00007807775,"about_ca_topic_score_gemma":0.000053027234,"teacher_disagreement_score":0.78470093,"about_ca_system_score_codex":0.000018387054,"about_ca_system_score_gemma":0.00004935764,"threshold_uncertainty_score":0.22161041},"labels":[],"label_agreement":null},{"id":"W3088562264","doi":"10.1038/s41597-020-00648-2","title":"A database of chlorophyll and water chemistry in freshwater lakes","year":2020,"lang":"en","type":"article","venue":"Scientific Data","topic":"Aquatic Ecosystems and Phytoplankton Dynamics","field":"Environmental Science","cited_by":81,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University; York University","funders":"Natural Sciences and Engineering Research Council of Canada; York University; Ministry of Environment; McGill University; Center for Urban Science and Progress; Government of Canada","keywords":"Environmental science; Water quality; Chlorophyll a; Biomass (ecology); Proxy (statistics); Freshwater ecosystem; Watershed; Nutrient; Productivity; Ecosystem; Ecology; Database; Hydrology (agriculture); Biology; Computer science","score_opus":0.02431380870858216,"score_gpt":0.22138061792069283,"score_spread":0.19706680921211067,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3088562264","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":[0.9946987,0.000027373531,0.000097704265,0.000302706,0.00009093074,0.00009181567,0.0035011952,0.000007966914,0.0011816289],"genre_scores_gemma":[0.9966307,0.0000028414258,0.0006703836,0.000049797232,0.000018082279,0.0000018254364,0.0020139897,0.0000052712667,0.00060710555],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.999011,0.000014196843,0.00018042278,0.00045023375,0.00018735486,0.00015680972],"domain_scores_gemma":[0.9991681,0.0000112457265,0.00003252989,0.0007028446,0.000002957133,0.00008229705],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00040508242,0.000068256275,0.00010631219,0.000009221813,0.000042190106,0.000047497262,0.0005587618,0.000023652805,0.0023397717],"category_scores_gemma":[0.000033806748,0.00004802949,0.000008286556,0.000119277036,0.00021602001,0.00026194163,0.0012040214,0.000059752245,0.00019684754],"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":[0.00003128949,0.00009692146,0.06915407,0.00036853182,0.000009467328,0.000035008274,0.0027159962,0.000170651,0.87302727,0.000036505804,0.052556966,0.0017973172],"study_design_scores_gemma":[0.0011505588,0.00004616697,0.00566206,0.00013497764,0.000028034081,0.000016298061,0.00057624996,0.36480418,0.13541037,0.0004154426,0.49115735,0.00059833255],"about_ca_topic_score_codex":0.00015189048,"about_ca_topic_score_gemma":0.0012972872,"teacher_disagreement_score":0.7376169,"about_ca_system_score_codex":0.000008803466,"about_ca_system_score_gemma":0.0000061289356,"threshold_uncertainty_score":0.99857223},"labels":[],"label_agreement":null},{"id":"W3091795721","doi":"10.1038/s41597-020-00690-0","title":"GalliForm, a database of Galliformes occurrence records from the Indo-Malay and Palaearctic, 1800–2008","year":2020,"lang":"en","type":"article","venue":"Scientific Data","topic":"Species Distribution and Climate Change","field":"Environmental Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Fisheries and Oceans Canada","funders":"Zoological museum, Lomonosov Moscow State University; Lomonosov Moscow State University; Leverhulme Trust","keywords":"Macroecology; Database; Biodiversity; Geography; Species distribution; Ecology; Galliformes; Taxon; Biology; Habitat","score_opus":0.09181699789533744,"score_gpt":0.276527385229699,"score_spread":0.18471038733436157,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3091795721","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":[0.8338389,0.0004462417,0.00029702397,0.0058360463,0.00078514335,0.00042566768,0.151989,0.00006188385,0.006320096],"genre_scores_gemma":[0.97739005,0.00037020378,0.00047547655,0.0009693918,0.00006357318,0.000010358483,0.020527292,0.000009228984,0.00018442622],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99831754,0.00004487517,0.00023160897,0.0006517733,0.0004974767,0.00025673115],"domain_scores_gemma":[0.99838644,0.00010116106,0.00011248902,0.0012068237,0.000016525886,0.00017655165],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00058552774,0.000117965654,0.00012873,0.000011876925,0.00026204652,0.00018375488,0.0014232288,0.00003132967,0.048562344],"category_scores_gemma":[0.00042591008,0.000082190025,0.00002452745,0.0004833405,0.0008980227,0.0005530803,0.002260592,0.0001267503,0.0012779278],"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":[0.000028335784,0.00006479109,0.11651279,0.000018736548,0.000011069203,0.000003577563,0.00066091656,0.0000010174803,0.005161937,0.00009248007,0.8711672,0.00627718],"study_design_scores_gemma":[0.00038694835,0.00003811581,0.17061935,0.000030067877,0.00003281587,0.000003393711,0.0024463788,0.0014490437,0.0014264868,0.000061541024,0.82328933,0.00021649798],"about_ca_topic_score_codex":0.0003826947,"about_ca_topic_score_gemma":0.0007047322,"teacher_disagreement_score":0.14355116,"about_ca_system_score_codex":0.000036890604,"about_ca_system_score_gemma":0.000025907755,"threshold_uncertainty_score":0.9994997},"labels":[],"label_agreement":null},{"id":"W3092045521","doi":"10.1038/s41597-020-00642-8","title":"Large eQTL meta-analysis reveals differing patterns between cerebral cortical and cerebellar brain regions","year":2020,"lang":"en","type":"article","venue":"Scientific Data","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":330,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Pacific Centre for Reproductive Medicine; University of British Columbia; Canadian Institute for Advanced Research","funders":"National Institute of Neurological Disorders and Stroke; National Institute on Drug Abuse; National Institute on Aging; National Institutes of Health; Università degli Studi di Trento; National Institute of Mental Health; Arizona Biomedical Research Commission; Translational Genomics Research Institute; Rush University; Michael J. Fox Foundation for Parkinson's Research; Arizona Department of Health Services; CurePSP; University of Pennsylvania; Mayo Foundation for Medical Education and Research; F. Hoffmann-La Roche; Illinois Department of Public Health; University of Pittsburgh; Mayo Clinic","keywords":"Meta-analysis; Neuroscience; Cerebellum; Biology; Medicine; Internal medicine","score_opus":0.09744670688283534,"score_gpt":0.29753978829237937,"score_spread":0.20009308140954402,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3092045521","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":[0.60450906,0.0022407065,0.34660438,0.01253528,0.00038163914,0.00065948133,0.032523625,0.00006063031,0.0004852125],"genre_scores_gemma":[0.98614126,0.000014638157,0.00082974846,0.0010302534,0.00018439919,0.0000038080555,0.01102019,0.000013295385,0.0007624263],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982917,0.000078322875,0.00034157076,0.0007493508,0.00019138971,0.00034769415],"domain_scores_gemma":[0.99814147,0.00003235624,0.0001064942,0.0014199294,0.000035984594,0.0002637648],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000814366,0.00016234996,0.00040290327,0.000048149515,0.00026277264,0.0002505286,0.0007585775,0.00010792601,0.00012929992],"category_scores_gemma":[0.00012343953,0.00013493901,0.00020960641,0.0002876117,0.00012900282,0.000014817196,0.0016210761,0.00014164942,0.000016520531],"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":[0.00006796868,0.00019295914,0.1051665,0.00033417816,0.09285961,0.00002331404,0.0018523305,0.00013055016,0.037920985,0.0022005315,0.7566428,0.0026082632],"study_design_scores_gemma":[0.0023617365,0.0003919054,0.05338264,0.000018772089,0.120771505,0.00002287096,0.0013595808,0.058912035,0.0052104974,0.0014456786,0.7536708,0.0024519581],"about_ca_topic_score_codex":0.0000069464772,"about_ca_topic_score_gemma":0.000079956735,"teacher_disagreement_score":0.38163218,"about_ca_system_score_codex":0.0000029784608,"about_ca_system_score_gemma":0.000026926302,"threshold_uncertainty_score":0.5502653},"labels":[],"label_agreement":null},{"id":"W3092143966","doi":"10.1038/s41597-020-00676-y","title":"A salmon diet database for the North Pacific Ocean","year":2020,"lang":"en","type":"article","venue":"Scientific Data","topic":"Marine and fisheries research","field":"Environmental Science","cited_by":11,"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; Fisheries and Oceans Canada","funders":"Hakai Institute; University of British Columbia; G. Unger Vetlesen Foundation; Ambrose Monell Foundation","keywords":"Pacific ocean; Oceanography; Fishery; Geography; Biology; Geology","score_opus":0.0831538589209788,"score_gpt":0.28426685395865087,"score_spread":0.20111299503767205,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3092143966","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15313129,0.00034138124,0.038698353,0.121241204,0.0076773353,0.011491251,0.15644106,0.0008528625,0.5101253],"genre_scores_gemma":[0.89777386,0.00011392154,0.005756268,0.0022877608,0.0007425214,0.00008350114,0.04286483,0.000085436775,0.050291874],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982789,0.000028182607,0.00013564456,0.0007431847,0.0004821814,0.00033191894],"domain_scores_gemma":[0.9977515,0.000098756616,0.000033999364,0.0019353322,0.000010190549,0.000170254],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00074529205,0.0000884798,0.0000770932,0.000012637824,0.00053601136,0.00036078834,0.002504871,0.000016376425,0.005227324],"category_scores_gemma":[0.00036414538,0.00005813129,0.000027832899,0.0005690437,0.0005408685,0.00052593806,0.0037036133,0.00011971591,0.0006455811],"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":[0.00005594394,0.000026710106,0.029330542,0.000013112725,0.0000059453905,0.0000036662857,0.00019217648,0.0000074413842,0.00016253302,0.000021479847,0.9503835,0.019796936],"study_design_scores_gemma":[0.00011607597,0.000045830075,0.0028240143,8.3131204e-7,0.000008144276,6.091426e-7,0.00021134457,0.027825728,0.000026274705,0.000024805893,0.96883255,0.00008377248],"about_ca_topic_score_codex":0.00012504216,"about_ca_topic_score_gemma":0.00038283068,"teacher_disagreement_score":0.7446426,"about_ca_system_score_codex":0.000016674217,"about_ca_system_score_gemma":0.000023429355,"threshold_uncertainty_score":0.99568206},"labels":[],"label_agreement":null},{"id":"W3092872384","doi":"10.1038/s41597-020-00784-9","title":"COVIDiSTRESS Global Survey dataset on psychological and behavioural consequences of the COVID-19 outbreak","year":2021,"lang":"en","type":"article","venue":"Scientific Data","topic":"COVID-19 and Mental Health","field":"Psychology","cited_by":134,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; University of Toronto","funders":"Vlaamse regering; Fonds Wetenschappelijk Onderzoek; Grantová Agentura České Republiky; Japan Society for the Promotion of Science; National Research University Higher School of Economics; Ministry of Education, Culture, Sports, Science and Technology; Institut Français de Bioinformatique","keywords":"Coronavirus disease 2019 (COVID-19); Outbreak; 2019-20 coronavirus outbreak; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Psychology; Geography; Data science; Virology; Medicine; Computer science; Infectious disease (medical specialty); Pathology; Disease","score_opus":0.42882880990942107,"score_gpt":0.5209819841713665,"score_spread":0.09215317426194547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3092872384","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":[0.5310334,0.00034878877,0.000034470755,0.003292631,0.0033738078,0.00022288888,0.46114823,0.000019451414,0.0005263329],"genre_scores_gemma":[0.94371253,0.000011608373,0.000042210468,0.0038947249,0.0000241122,0.0000061663336,0.051519223,0.0000044381145,0.000784958],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9971732,0.0007410546,0.00030591447,0.0010895593,0.00037485815,0.00031542746],"domain_scores_gemma":[0.996292,0.0003615641,0.00013909441,0.0028864818,0.000047446603,0.0002734388],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0020550801,0.00013095608,0.00019034656,0.00002778585,0.00035882797,0.000122032245,0.0013674546,0.00008197407,0.0009891039],"category_scores_gemma":[0.0008582456,0.00009029064,0.000028657258,0.00051355606,0.001759369,0.00009238752,0.0010271043,0.00014396691,0.00008190343],"study_design_candidate":"observational","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":[0.0001170289,0.0004099984,0.38586086,0.000033289518,0.000013369682,0.000059226863,0.00012258925,4.514862e-7,0.00011823328,0.0018790227,0.60936075,0.0020251558],"study_design_scores_gemma":[0.0008726989,0.00008502996,0.804964,0.000019818004,0.000030686475,0.00013607678,0.00051148003,0.0000049575838,0.00010442178,0.00049788016,0.19261852,0.00015443725],"about_ca_topic_score_codex":0.009908001,"about_ca_topic_score_gemma":0.016148802,"teacher_disagreement_score":0.41910312,"about_ca_system_score_codex":0.00010619788,"about_ca_system_score_gemma":0.0006420534,"threshold_uncertainty_score":0.9999241},"labels":[],"label_agreement":null},{"id":"W3094042624","doi":"10.1038/s41597-020-00701-0","title":"Long-term surveys of age structure in 13 ungulate and one ostrich species in the Serengeti, 1926–2018","year":2020,"lang":"en","type":"article","venue":"Scientific Data","topic":"Wildlife Ecology and Conservation","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 British Columbia","funders":"Zoologische Gesellschaft Frankfurt; Natural Sciences and Engineering Research Council of Canada; Government of Canada; Wildlife Conservation Society","keywords":"Ungulate; Geography; Ecology; Biodiversity; Juvenile; Biology; Habitat","score_opus":0.06183281563456003,"score_gpt":0.24654999900480473,"score_spread":0.1847171833702447,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3094042624","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":[0.9972951,0.000036903413,0.000022434222,0.0014689157,0.00015768841,0.00016026021,0.00046910817,0.0000049565924,0.00038464688],"genre_scores_gemma":[0.99871385,0.000010325136,0.00010285765,0.000201628,0.00001630877,0.0000012212429,0.0007184885,0.0000027852943,0.00023254876],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99883133,0.00022834714,0.0001793528,0.00040763625,0.0002058435,0.00014750927],"domain_scores_gemma":[0.9992706,0.0000726028,0.00006096585,0.00056037854,0.0000037764057,0.00003168415],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013296407,0.00006774857,0.00010567265,0.000034501358,0.00007710064,0.00006325513,0.000797584,0.000046466568,0.00077368075],"category_scores_gemma":[0.00014412387,0.000052796917,0.000007204217,0.00066925696,0.00048162576,0.0003573519,0.0005830866,0.00012288283,0.000034631103],"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":[0.0000054825155,0.00002866687,0.9898244,0.00001029712,0.0000022059294,0.000009886207,0.0008132087,0.00002729293,0.0025956596,0.000023265286,0.0055158064,0.0011438193],"study_design_scores_gemma":[0.00017389467,0.000014934598,0.9983778,0.0000073256238,0.0000046751697,0.0000011058492,0.00008610589,0.00027969,0.00013596464,0.00021745104,0.00064292055,0.000058158203],"about_ca_topic_score_codex":0.00019500716,"about_ca_topic_score_gemma":0.01879735,"teacher_disagreement_score":0.018602341,"about_ca_system_score_codex":0.000016118698,"about_ca_system_score_gemma":0.00001614495,"threshold_uncertainty_score":0.99910706},"labels":[],"label_agreement":null},{"id":"W3095025955","doi":"10.1038/s41597-020-00711-y","title":"Individual back-calculated size-at-age based on otoliths from Pacific coral reef fish species","year":2020,"lang":"en","type":"article","venue":"Scientific Data","topic":"Marine and fisheries research","field":"Environmental Science","cited_by":20,"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 Human Genome Research Institute; Fondation de France; Fondation BNP Paribas; BNP Paribas Cardif; Agence Nationale de la Recherche","keywords":"Coral reef; Coral reef fish; Fishery; Reef; Coral; Fish <Actinopterygii>; Biology; Oceanography; Geography; Ecology; Geology","score_opus":0.0891040629753068,"score_gpt":0.26381286344026394,"score_spread":0.17470880046495713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3095025955","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4225914,0.000005968904,0.00012330254,0.008981693,0.0012541176,0.0009732214,0.07144458,0.00021309328,0.49441263],"genre_scores_gemma":[0.845167,0.000008450119,0.003076038,0.003867749,0.00029891825,0.000015439973,0.0650611,0.00006584908,0.08243945],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9962211,0.00012885898,0.00028993675,0.0014201741,0.0013851777,0.00055473566],"domain_scores_gemma":[0.9971299,0.00016878273,0.00007611935,0.0022075938,0.000013795028,0.00040377324],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0005476151,0.0002078523,0.0002173243,0.00003996707,0.00040895952,0.00067748094,0.0026857832,0.00008755565,0.14802821],"category_scores_gemma":[0.0005266489,0.00018512401,0.000056498706,0.00091934577,0.0010312628,0.00046427984,0.0043424843,0.00029507483,0.0044523166],"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":[0.00009627933,0.0001356097,0.062381778,0.000009214855,0.000013219553,0.00009302937,0.00025030432,0.0000226089,0.002906172,0.000006503043,0.92933756,0.0047477037],"study_design_scores_gemma":[0.00044051293,0.000072084935,0.12321118,0.000006144,0.000011229147,6.5267614e-7,0.00016513832,0.01421202,0.00046264287,0.00003295119,0.8611516,0.00023388703],"about_ca_topic_score_codex":0.00032800046,"about_ca_topic_score_gemma":0.000491838,"teacher_disagreement_score":0.4225756,"about_ca_system_score_codex":0.00009560735,"about_ca_system_score_gemma":0.000041088704,"threshold_uncertainty_score":0.9963228},"labels":[],"label_agreement":null},{"id":"W30988412","doi":"10.1038/s41597-019-0038-1","title":"Desenvolupament d’un mètode d’odometria visual per a un robot mòbil en entorns exteriors","year":2013,"lang":"en","type":"dissertation","venue":"Scientific Data","topic":"Robotics and Sensor-Based Localization","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Humanities; Physics; Computer science; Art","score_opus":0.018831324122114888,"score_gpt":0.2646404752014437,"score_spread":0.2458091510793288,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W30988412","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":[0.85206586,0.0034483047,0.08601165,0.0000799531,0.04665478,0.002621181,0.004754253,0.0011810163,0.0031830007],"genre_scores_gemma":[0.7061347,0.00042339778,0.013150853,0.00003709541,0.0010688478,0.000106806634,0.24714872,0.00041663583,0.031512972],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968517,0.00008330693,0.00060684537,0.0010737546,0.0008303769,0.0005540066],"domain_scores_gemma":[0.997422,0.000075107724,0.00014017979,0.0019766034,0.0001641395,0.0002220153],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0007407311,0.00045020046,0.00041405013,0.00066522293,0.00027967684,0.0010442666,0.0013836378,0.00034749933,0.0016204701],"category_scores_gemma":[0.00016863404,0.00045153897,0.0001027958,0.00074455346,0.000071983886,0.00045068757,0.00020800902,0.00034656262,0.0011861322],"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":[0.00010701845,0.00103829,0.00043187165,0.0024304865,0.0012069026,0.000082404884,0.008126057,0.17436093,0.3200078,0.0005841343,0.28477407,0.20685007],"study_design_scores_gemma":[0.0011221443,0.00007571869,0.004894764,0.00048355677,0.00044458813,0.000009462697,0.002069261,0.85843873,0.023102041,0.00023784729,0.1071233,0.0019985905],"about_ca_topic_score_codex":0.0000814833,"about_ca_topic_score_gemma":0.00010780776,"teacher_disagreement_score":0.6840778,"about_ca_system_score_codex":0.00017574016,"about_ca_system_score_gemma":0.00010317157,"threshold_uncertainty_score":0.9999927},"labels":[],"label_agreement":null},{"id":"W3102112318","doi":"10.1038/s41597-020-00719-4","title":"Paired rRNA-depleted and polyA-selected RNA sequencing data and supporting multi-omics data from human T cells","year":2020,"lang":"en","type":"article","venue":"Scientific Data","topic":"RNA modifications and cancer","field":"Biochemistry, Genetics and Molecular Biology","cited_by":33,"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":"European Commission; British Heart Foundation; Government of Canada","keywords":"Ribosomal RNA; Biology; RNA; RNA splicing; Epigenetics; Computational biology; Transcriptome; RNA-Seq; Gene; Genetics; Gene expression","score_opus":0.15829019945819303,"score_gpt":0.3294361991482268,"score_spread":0.17114599969003377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3102112318","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":[0.9247479,0.0016801886,0.0070115714,0.00060679583,0.00032132794,0.00029465585,0.065238,0.000045724228,0.00005383905],"genre_scores_gemma":[0.8230238,0.000106139574,0.0067445072,0.00020454604,0.00018374108,0.000002477478,0.16949123,0.00002477647,0.00021879189],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99737334,0.000061768566,0.00032519622,0.001794344,0.00016613821,0.00027923475],"domain_scores_gemma":[0.99498934,0.000014811773,0.00017259688,0.004565155,0.000073044816,0.00018507188],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006770176,0.0001561968,0.0001545592,0.000031324693,0.0003840318,0.00042054435,0.0025285077,0.00008599567,0.000037635262],"category_scores_gemma":[0.000379766,0.00015589659,0.000009585977,0.00022503389,0.00025400685,0.000067903784,0.0048683397,0.00011396598,0.000009456805],"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":[0.000009763015,0.000016666338,0.0005808735,0.0000142105455,0.000036024736,0.0000029091839,0.00008350374,0.0000013819397,0.93702596,0.0000027289611,0.059014197,0.0032117784],"study_design_scores_gemma":[0.0020828494,0.00009509146,0.004719206,0.00005140398,0.00023806126,0.000012507585,0.0012525256,0.28771833,0.4000583,0.000047769063,0.30275607,0.00096788333],"about_ca_topic_score_codex":0.00025477,"about_ca_topic_score_gemma":0.0003914243,"teacher_disagreement_score":0.53696764,"about_ca_system_score_codex":0.000009288767,"about_ca_system_score_gemma":0.00021094998,"threshold_uncertainty_score":0.6357279},"labels":[],"label_agreement":null},{"id":"W3108117466","doi":"10.1038/s41597-020-00737-2","title":"North American historical monthly spatial climate dataset, 1901–2016","year":2020,"lang":"en","type":"article","venue":"Scientific Data","topic":"Remote Sensing in Agriculture","field":"Environmental Science","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Natural Resources Canada; Canadian Forest Service","funders":"Canadian Forest Service; U.S. Forest Service; Natural Resources Canada; Environment and Climate Change Canada","keywords":"Precipitation; Environmental science; Climatology; Mean radiant temperature; Climate change; Maximum temperature; Statistics; Atmospheric sciences; Mathematics; Meteorology; Geography; Geology","score_opus":0.02849479680893761,"score_gpt":0.23064362183725673,"score_spread":0.20214882502831913,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3108117466","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":[0.5817394,0.00041866858,0.0049989806,0.044309188,0.017613465,0.0028363648,0.2954336,0.001644607,0.05100569],"genre_scores_gemma":[0.80875164,0.000053216074,0.024334205,0.0036714708,0.0012102345,0.0000034163845,0.15968311,0.00008528251,0.002207434],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99698526,0.000074558135,0.00028000202,0.0013847437,0.00076780986,0.00050760404],"domain_scores_gemma":[0.99736834,0.000030052921,0.00016152527,0.0020465334,0.000010162008,0.0003834164],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00036286275,0.00019120266,0.00020903704,0.0000229522,0.00036646,0.00025135122,0.0021966319,0.000031037573,0.00046861937],"category_scores_gemma":[0.00021693863,0.0001452132,0.000034473273,0.00094891724,0.0006113179,0.00054672314,0.003026656,0.00020948633,0.005471511],"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":[0.000011779309,0.000041608324,0.005963356,0.000004276171,0.000004382584,0.000026342206,0.000113622555,0.00016731318,0.0013994592,7.2732496e-7,0.9603891,0.03187806],"study_design_scores_gemma":[0.000105793675,0.00003624325,0.07395538,0.0000037440677,0.000019318766,0.0000037344462,0.000024015091,0.011881677,0.00008687149,0.0000033091344,0.91365683,0.0002230904],"about_ca_topic_score_codex":0.0032238034,"about_ca_topic_score_gemma":0.008244315,"teacher_disagreement_score":0.2270122,"about_ca_system_score_codex":0.0002565274,"about_ca_system_score_gemma":0.00002395889,"threshold_uncertainty_score":0.99530286},"labels":[],"label_agreement":null},{"id":"W3108537578","doi":"10.1038/s41597-020-00763-0","title":"ClimateEU, scale-free climate normals, historical time series, and future projections for Europe","year":2020,"lang":"en","type":"article","venue":"Scientific Data","topic":"Climate variability and models","field":"Environmental Science","cited_by":124,"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; University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Climate change; Scale (ratio); Downscaling; Environmental science; Climate model; Climatology; Download; Adaptation (eye); Software; Computer science; Database; Environmental resource management; Meteorology; Geography; Cartography; Ecology; Geology","score_opus":0.04382605702617909,"score_gpt":0.2420340178003698,"score_spread":0.1982079607741907,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3108537578","genre_codex":"empirical","genre_gemma":"methods","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":[0.39868435,0.0014106499,0.008868234,0.24912937,0.019680984,0.011835549,0.19123307,0.0029430618,0.11621472],"genre_scores_gemma":[0.096211165,0.005905895,0.6044428,0.018023813,0.01440789,0.0012589415,0.117076546,0.0011695403,0.14150347],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99796516,0.000048910177,0.00026390213,0.0010347,0.00028376016,0.00040357083],"domain_scores_gemma":[0.9982083,0.00003490621,0.00007108706,0.0014364498,0.000019931784,0.00022934972],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009803121,0.00014548101,0.00016917684,0.000026169313,0.00067583704,0.00025355665,0.0011405033,0.000060448056,0.0009539716],"category_scores_gemma":[0.00017762397,0.00012911417,0.000031316973,0.00051891874,0.00031081605,0.0010276707,0.0028875377,0.00011406147,0.0004932097],"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":[0.00012186113,0.00015175369,0.0018006108,0.00011352469,0.000008054121,0.0000030710269,0.000754701,0.000046617995,0.010005313,0.0004022353,0.9830409,0.0035513465],"study_design_scores_gemma":[0.00026584012,0.00007992765,0.0005454481,0.0000045399042,0.000030906416,0.000009870756,0.000059680933,0.015146347,0.000064646956,0.00019550185,0.9834195,0.00017778519],"about_ca_topic_score_codex":0.000046413472,"about_ca_topic_score_gemma":0.0001333058,"teacher_disagreement_score":0.5955745,"about_ca_system_score_codex":0.0001007385,"about_ca_system_score_gemma":0.00002644756,"threshold_uncertainty_score":0.9999593},"labels":[],"label_agreement":null},{"id":"W3109120520","doi":"10.1038/s41597-020-00762-1","title":"Bioinformatic analysis of membrane and associated proteins in murine cardiomyocytes and human myocardium","year":2020,"lang":"en","type":"article","venue":"Scientific Data","topic":"RNA and protein synthesis mechanisms","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":"Princess Margaret Cancer Centre; University of Alberta; Ted Rogers Centre for Heart Research; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canada First Research Excellence Fund; Canadian Institutes of Health Research; Alberta Innovates; University of Toronto; Government of Canada","keywords":"Cell biology; Membrane; Computational biology; Membrane protein; Biology; Chemistry; Biochemistry","score_opus":0.03046961960581235,"score_gpt":0.2608618438097863,"score_spread":0.23039222420397393,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3109120520","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":[0.99749213,0.0004227281,0.0002999605,0.00016076553,0.000039755483,0.00024177249,0.001095979,0.0000068735785,0.00024000555],"genre_scores_gemma":[0.99699235,0.00002920257,0.00055084383,0.00004345334,0.000014580058,0.0000065132044,0.0022629143,0.0000054241277,0.00009472362],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990487,0.000057747213,0.0002198509,0.00039272197,0.00014902816,0.00013194092],"domain_scores_gemma":[0.9992,0.000008583887,0.000091131165,0.00059752096,0.00003357487,0.00006919222],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00074249384,0.000087053,0.00023755545,0.00011995141,0.000069034584,0.000066581866,0.00031624868,0.000058588445,0.0000152281655],"category_scores_gemma":[0.00023376412,0.000079038706,0.000036693546,0.00050035707,0.00013262292,0.000014002415,0.0005149325,0.00003522748,0.0000011999033],"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":[0.000013693744,0.000019665718,0.00267572,0.00006016495,0.00031906524,0.0000014872794,0.00013263752,0.000013257543,0.9950607,0.000035353118,0.00044386782,0.0012244119],"study_design_scores_gemma":[0.00090329186,0.00021715532,0.022506487,0.000048330527,0.0006296885,0.0000023678226,0.00032488385,0.004275719,0.9593391,0.00007451954,0.011321293,0.00035717816],"about_ca_topic_score_codex":0.0000517027,"about_ca_topic_score_gemma":0.000097765886,"teacher_disagreement_score":0.03572159,"about_ca_system_score_codex":0.0000029334774,"about_ca_system_score_gemma":0.000024859233,"threshold_uncertainty_score":0.32231048},"labels":[],"label_agreement":null},{"id":"W3114591989","doi":"10.1038/s41597-021-01084-6","title":"Global daily 1 km land surface precipitation based on cloud cover-informed downscaling","year":2021,"lang":"en","type":"preprint","venue":"Scientific Data","topic":"Climate variability and models","field":"Environmental Science","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":"Nuclear Safety and Security Commission; Deutsche Forschungsgemeinschaft; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; McGill University; Biodiversa+; Svenska Forskningsrådet Formas; Technology Agency of the Czech Republic; Agence Nationale de la Recherche; National Aeronautics and Space Administration; Vetenskapsrådet; National Science Foundation","keywords":"Downscaling; Precipitation; Environmental science; Orographic lift; Climatology; Cloud cover; Meteorology; Terrain; Orography; Cloud computing; Computer science; Geography; Geology","score_opus":0.055391883100898806,"score_gpt":0.3009565304965644,"score_spread":0.24556464739566558,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3114591989","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":[0.92575353,0.000041966046,0.009229897,0.000639417,0.008397655,0.00090691337,0.035404257,0.00014826859,0.019478096],"genre_scores_gemma":[0.91276944,0.00001959289,0.01105958,0.00031847635,0.00011195398,0.000016166563,0.07429485,0.000023247914,0.001386709],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9958902,0.00015942047,0.00045868783,0.0019234291,0.0011083848,0.000459887],"domain_scores_gemma":[0.9951672,0.00020660898,0.00022452629,0.0041772593,0.000035537436,0.00018887111],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0024415175,0.00029528697,0.000292954,0.000034518573,0.00035528257,0.0012278535,0.0021163838,0.00024872294,0.0033364939],"category_scores_gemma":[0.0006241182,0.0002856005,0.00009540159,0.0004832551,0.0004034248,0.00055640977,0.005280064,0.00031086613,0.0008519093],"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":[0.00005669481,0.000272345,0.016313521,0.00016239542,0.000018143583,0.000008108435,0.00032943633,0.8838832,0.00030264317,0.000024918756,0.097303726,0.0013248959],"study_design_scores_gemma":[0.0005565,0.000029250086,0.012221864,0.00028174996,0.0000762087,0.00000206526,0.00010905193,0.93581957,0.000165707,0.001128862,0.04902444,0.00058474374],"about_ca_topic_score_codex":0.0009971891,"about_ca_topic_score_gemma":0.0017813328,"teacher_disagreement_score":0.051936384,"about_ca_system_score_codex":0.0005893602,"about_ca_system_score_gemma":0.000350422,"threshold_uncertainty_score":0.9999596},"labels":[],"label_agreement":null},{"id":"W3118241888","doi":"10.1038/s41597-020-00790-x","title":"Dataset of spiking and LFP activity invasively recorded in the human amygdala during aversive dynamic stimuli","year":2021,"lang":"en","type":"article","venue":"Scientific Data","topic":"Memory and Neural Mechanisms","field":"Neuroscience","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":"Foundation for Research in Science and the Humanities; Russian Science Foundation; Universität Zürich; Mach-Gaensslen Foundation of Canada; Russian Foundation for Basic Research; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Amygdala; Neuroscience; Aversive Stimulus; Psychology","score_opus":0.24531642119854527,"score_gpt":0.3804034085416959,"score_spread":0.13508698734315064,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3118241888","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":[0.98717135,0.000011494892,0.0000343502,0.00018267802,0.00042564314,0.00017921987,0.011902211,0.000008675081,0.000084403015],"genre_scores_gemma":[0.9979394,0.000011631396,0.000111467736,0.000100938916,0.0000106047355,0.0000027587357,0.0015624232,0.0000059400995,0.0002548352],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9980029,0.00032016533,0.00019072206,0.00091190933,0.0003400747,0.00023423019],"domain_scores_gemma":[0.9978799,0.00026326772,0.00013240664,0.0016557593,0.0000215942,0.00004703901],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008898955,0.00010626667,0.00014425331,0.000102761674,0.00044944318,0.00020758998,0.001238623,0.00003095208,0.000095103685],"category_scores_gemma":[0.0010305058,0.00008598008,0.00001626548,0.00061036233,0.00028535086,0.0007190448,0.0013421429,0.00020062694,0.000015807871],"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":[0.000011267584,0.00006329578,0.000062518164,0.00004471522,0.0000012614747,0.00012650414,0.00024736943,0.0000031120253,0.99788386,0.00008430324,0.00080194446,0.00066984777],"study_design_scores_gemma":[0.000318588,0.000019695439,0.0038125303,0.000052644176,0.00001033058,0.00005657526,0.00030713144,0.0008253096,0.9931759,0.00053212437,0.00077923614,0.00010988137],"about_ca_topic_score_codex":0.00001577803,"about_ca_topic_score_gemma":0.00038162226,"teacher_disagreement_score":0.0107680755,"about_ca_system_score_codex":0.00001496948,"about_ca_system_score_gemma":0.0000528293,"threshold_uncertainty_score":0.3506166},"labels":[],"label_agreement":null},{"id":"W3122040552","doi":"10.1038/s41597-021-00800-6","title":"A complete dietary review of Japanese birds with special focus on molluscs","year":2021,"lang":"en","type":"article","venue":"Scientific Data","topic":"Avian ecology and behavior","field":"Environmental Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Merck Canada Inc. (Canada)","funders":"","keywords":"Archipelago; Predation; Ecology; Biology; Resource (disambiguation); Ecosystem; Agriculture; Geography","score_opus":0.05785304932552797,"score_gpt":0.2803396562191138,"score_spread":0.2224866068935858,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3122040552","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":[0.84358996,0.0036614772,0.00003910917,0.0073942565,0.005293325,0.0015288625,0.01612619,0.00017097122,0.12219588],"genre_scores_gemma":[0.8929512,0.0013001147,0.011302703,0.0045456435,0.000874061,0.000055380773,0.01542425,0.00009554118,0.07345111],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99849725,0.000071780385,0.00019136943,0.00062819733,0.0004031479,0.00020826784],"domain_scores_gemma":[0.9981509,0.000031006643,0.00008417667,0.0016428065,0.00001606764,0.000075063675],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0005396449,0.00009780587,0.0001839424,0.000020890515,0.00016382326,0.000025170559,0.00082502863,0.00003151943,0.014795122],"category_scores_gemma":[0.00007917062,0.00007395681,0.000030546544,0.0005245522,0.00071803085,0.00021640316,0.00086064,0.00010117746,0.0016458831],"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":[0.00006712089,0.00093426247,0.045452893,0.0004344529,0.000029800785,0.0004033852,0.0004314043,0.000011131305,0.008674791,0.00003176918,0.90689063,0.03663836],"study_design_scores_gemma":[0.0010684145,0.00041549993,0.49483255,0.0023076187,0.00030503163,0.00017090945,0.0004147836,0.00014081843,0.0027000066,0.00028226338,0.49663284,0.0007292859],"about_ca_topic_score_codex":0.000025102909,"about_ca_topic_score_gemma":0.00084957754,"teacher_disagreement_score":0.44937965,"about_ca_system_score_codex":0.000031164513,"about_ca_system_score_gemma":0.000040258685,"threshold_uncertainty_score":0.99913144},"labels":[],"label_agreement":null},{"id":"W3124931592","doi":"10.1038/s41597-021-00820-2","title":"A compilation of North American tree provenance trials and relevant historical climate data for seven species","year":2021,"lang":"en","type":"article","venue":"Scientific Data","topic":"Forest ecology and management","field":"Environmental Science","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Natural Resources Canada; Canadian Forest Service; Ontario Forest Research Institute; Ministry of Natural Resources and Forestry","funders":"","keywords":"Provenance; Climate change; Pinus <genus>; Abiotic component; Ecology; Range (aeronautics); Geography; Forestry; Biology; Botany; Engineering","score_opus":0.09550338386737549,"score_gpt":0.29889415795320823,"score_spread":0.20339077408583273,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3124931592","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":[0.69811255,0.0010729284,0.08439783,0.015444138,0.009384988,0.006116337,0.1764418,0.00021223952,0.0088172],"genre_scores_gemma":[0.8147782,0.00046831832,0.09729875,0.00031058452,0.00017808769,0.00006948635,0.06276594,0.00003418257,0.024096465],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99850595,0.00008432235,0.00031069323,0.0007079763,0.00020030115,0.00019074949],"domain_scores_gemma":[0.99781525,0.0001538889,0.00023394651,0.0017395548,0.00001288007,0.00004446967],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021387096,0.00007080122,0.0002426662,0.000025874662,0.0001786016,0.00004875703,0.00082067284,0.000012724927,0.000104480445],"category_scores_gemma":[0.000818345,0.00006066428,0.000018706063,0.00031139108,0.00045462427,0.0003766527,0.0025657131,0.00003820345,0.000021355083],"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":[0.00010100264,0.0002864444,0.08869556,0.00008723392,0.000040842624,0.000008551433,0.00015874005,0.000094786905,0.0011790708,0.0013321056,0.8230138,0.085001856],"study_design_scores_gemma":[0.00023525607,0.000033857945,0.4302895,0.0000059678578,0.00004318323,0.0000012523358,0.000034624936,0.005093193,0.00008384855,0.0003167044,0.5637881,0.000074499985],"about_ca_topic_score_codex":0.000039372546,"about_ca_topic_score_gemma":0.006480971,"teacher_disagreement_score":0.34159395,"about_ca_system_score_codex":0.000062780564,"about_ca_system_score_gemma":0.000020588506,"threshold_uncertainty_score":0.3616534},"labels":[],"label_agreement":null},{"id":"W3125634994","doi":"10.1038/s41597-021-00805-1","title":"High-resolution, large-scale laboratory measurements of a sandy beach and dynamic cobble berm revetment","year":2021,"lang":"en","type":"article","venue":"Scientific Data","topic":"Coastal and Marine Dynamics","field":"Earth and Planetary 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":"University of British Columbia","funders":"Australian Research Council; Horizon 2020 Framework Programme; Engineering and Physical Sciences Research Council; University of Bath; Deltares; European Commission; Research Councils UK","keywords":"Swash; Berm; Revetment; Cobble; Wave flume; Flume; Beach morphodynamics; Geology; Environmental science; Wave loading; Benthic zone; Wave height; Imbrication; Shoal; Hydrology (agriculture); Geomorphology; Geotechnical engineering; Oceanography; Breaking wave; Sediment; Sediment transport; Habitat; Ecology; Breakup; Submarine pipeline; Wave propagation","score_opus":0.024624088657585943,"score_gpt":0.23439753644425923,"score_spread":0.20977344778667328,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3125634994","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":[0.9394987,0.003416746,0.0010044002,0.00047921663,0.002735006,0.0003037533,0.050690554,0.00005082895,0.0018207696],"genre_scores_gemma":[0.9492632,0.000062130915,0.0073766764,0.00009041607,0.00003500327,0.0000011104627,0.0380007,0.0000051649868,0.0051656095],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99845946,0.00006854098,0.00022543748,0.000557489,0.0004270905,0.0002619946],"domain_scores_gemma":[0.9987056,0.000026690725,0.000081213795,0.00090449996,0.00016593261,0.000116019386],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010841414,0.000098946846,0.00015460332,0.00006127028,0.00024845806,0.00012525488,0.00041106198,0.00003445254,0.0006607022],"category_scores_gemma":[0.00008753499,0.000088519155,0.000018077084,0.00046661255,0.0001709882,0.0003166718,0.00034078452,0.00007400213,0.00003573766],"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":[0.00011846409,0.0007010972,0.7478828,0.00047435277,0.00018861942,0.00006655338,0.00088130945,0.0007913505,0.008451673,0.00023841449,0.13129976,0.108905606],"study_design_scores_gemma":[0.0018306467,0.00012697776,0.65876824,0.00013552127,0.00015516537,0.000027783097,0.00081789034,0.13447918,0.0010283575,0.0013301603,0.20070468,0.0005953778],"about_ca_topic_score_codex":0.0005273555,"about_ca_topic_score_gemma":0.032431044,"teacher_disagreement_score":0.13368782,"about_ca_system_score_codex":0.0000065507065,"about_ca_system_score_gemma":0.00019243342,"threshold_uncertainty_score":0.98522455},"labels":[],"label_agreement":null},{"id":"W3125770330","doi":"10.1038/s41597-021-00816-y","title":"Community-curated and standardised metadata of published ancient metagenomic samples with AncientMetagenomeDir","year":2021,"lang":"en","type":"article","venue":"Scientific Data","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":70,"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; Arts and Humanities Research Council; Universidad Nacional Autónoma de México; Max-Planck-Gesellschaft; Carlsbergfondet; Deutsche Forschungsgemeinschaft; European Commission; Research Councils UK; Wellcome Trust","keywords":"Metadata; Metagenomics; Computer science; Interoperability; Data science; Information retrieval; World Wide Web; Geospatial metadata; Biology; Data element; Meta Data Services","score_opus":0.049485412251043394,"score_gpt":0.27135146186826553,"score_spread":0.22186604961722214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3125770330","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":[0.97658724,0.00816728,0.0011010244,0.00012645064,0.0003271473,0.00017842418,0.013167511,0.000004290382,0.000340647],"genre_scores_gemma":[0.9794347,0.00018899333,0.007711958,0.00008426154,0.00003434639,0.0000068431996,0.011496896,0.000018234561,0.001023732],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981991,0.00019430283,0.00028846174,0.0007717561,0.00026071112,0.00028564027],"domain_scores_gemma":[0.9963251,0.000030578285,0.00014686894,0.002997579,0.00038057545,0.000119317825],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017308404,0.00017056595,0.0002878896,0.0000731058,0.00040146822,0.00034486206,0.0009426483,0.000048492715,0.000033355842],"category_scores_gemma":[0.00037506752,0.00013872754,0.000037750797,0.00039839777,0.0006369371,0.000015116173,0.0021816487,0.000104533945,0.0000014391044],"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":[0.00005322288,0.00012345202,0.0025509412,0.000052190953,0.00034519477,0.000004048631,0.00020095837,0.00002253934,0.98129433,0.00010027147,0.013853863,0.0013990032],"study_design_scores_gemma":[0.0012202944,0.00020286077,0.035272174,0.000020822848,0.0002494589,0.000033446555,0.0017806325,0.00005737313,0.29224995,0.00012615744,0.6684108,0.00037602862],"about_ca_topic_score_codex":0.000044740027,"about_ca_topic_score_gemma":0.00050674536,"teacher_disagreement_score":0.68904436,"about_ca_system_score_codex":0.00000917784,"about_ca_system_score_gemma":0.00037831502,"threshold_uncertainty_score":0.5657145},"labels":[],"label_agreement":null},{"id":"W3126221909","doi":"10.1038/s41597-021-00829-7","title":"The Cuban Human Brain Mapping Project, a young and middle age population-based EEG, MRI, and cognition dataset","year":2021,"lang":"en","type":"article","venue":"Scientific Data","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":65,"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":"Fonds de recherche du Québec – Nature et technologies; Helmholtz Association; University of Electronic Science and Technology of China; National Natural Science Foundation of China; Fondation Brain Canada","keywords":"Electroencephalography; Neuroimaging; Cognition; Population; Cognitive decline; Magnetic resonance imaging; Psychology; Audiology; Medicine; Neuroscience; Dementia; Disease; Pathology; Radiology","score_opus":0.15655278982966067,"score_gpt":0.3263458182746557,"score_spread":0.16979302844499503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3126221909","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":[0.7950346,0.0010987613,0.0018002134,0.039261796,0.0053006504,0.0024301906,0.15190326,0.00036948844,0.0028010416],"genre_scores_gemma":[0.95971006,0.000014137525,0.0004271756,0.0020007293,0.00008852039,0.000038091344,0.035775304,0.00001913842,0.0019268589],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99789476,0.00021599008,0.00017699285,0.001096977,0.00037894517,0.00023635042],"domain_scores_gemma":[0.9965963,0.002119148,0.00008061821,0.0011097444,0.000048151687,0.000046075435],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0012056537,0.000116272546,0.00010628797,0.00009541139,0.0027070697,0.0011137525,0.0003816767,0.00002550591,0.000014907845],"category_scores_gemma":[0.006925005,0.000096256015,0.000013360654,0.00054830086,0.0004951632,0.0005197023,0.00089461013,0.000114347655,0.0000109131315],"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":[0.000024865914,0.00014643233,0.005504883,0.00015912873,0.000025683059,0.00010817829,0.000515113,0.000006098213,0.2693386,0.002797765,0.71798825,0.0033850027],"study_design_scores_gemma":[0.001570916,0.000069160466,0.091092505,0.00028150287,0.00007463743,0.0001506351,0.0018876821,0.012089068,0.009011874,0.00841432,0.8746181,0.0007395548],"about_ca_topic_score_codex":0.00012640716,"about_ca_topic_score_gemma":0.0026973141,"teacher_disagreement_score":0.26032674,"about_ca_system_score_codex":0.000020114507,"about_ca_system_score_gemma":0.00007870641,"threshold_uncertainty_score":0.99992317},"labels":[],"label_agreement":null},{"id":"W3129379202","doi":"10.1038/s41597-021-00851-9","title":"Author Correction: The FLUXNET2015 dataset and the ONEFlux processing pipeline for eddy covariance data","year":2021,"lang":"en","type":"article","venue":"Scientific Data","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":113,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; University of Manitoba; Centre de Géomatique du Québec; University of Saskatchewan; Canadian Forest Service; Environment and Climate Change Canada; University of British Columbia; University of Waterloo; Global Institute for Water Security; Université Laval; Natural Resources Canada; Ministère des Ressources naturelles et des Forêts; Ontario Drive & Gear (Canada); McMaster University","funders":"Natural Environment Research Council; Sight Research UK","keywords":"Pipeline (software); Eddy covariance; Covariance; Computer science; Data science; Statistics; Mathematics; Biology; Ecosystem; Ecology; Programming language","score_opus":0.08306270731006536,"score_gpt":0.3033050218793115,"score_spread":0.22024231456924614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3129379202","genre_codex":"methods","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000558262,0.017615054,0.7144811,0.008220402,0.035518635,0.0010534474,0.21924752,0.00051582465,0.0027897395],"genre_scores_gemma":[0.09012617,0.00019470796,0.04371051,0.00096807367,0.003489571,0.00010326856,0.8074135,0.00016031809,0.053833876],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99865556,0.00004817297,0.00022881465,0.0006008586,0.0002143088,0.00025227206],"domain_scores_gemma":[0.99642557,0.00026173246,0.00004919301,0.003133091,0.00007621141,0.00005419329],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024793914,0.00012382734,0.0001341094,0.00002496981,0.00072980224,0.0009195416,0.0016819346,0.000036888025,0.00004762658],"category_scores_gemma":[0.0006500531,0.000076622695,0.000012663341,0.00042146075,0.00030708025,0.0006699727,0.0011853502,0.00016648269,0.000016256881],"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":[0.000009428001,0.000008347152,0.0000027754463,0.000045944395,0.000014257164,0.0000017301826,0.00014313002,0.0023954767,0.0001435724,0.00018521727,0.9530935,0.04395657],"study_design_scores_gemma":[0.00020217014,0.0000010478961,0.000003861239,0.000033182147,0.000028105724,0.000020867872,0.00010455331,0.4882306,0.00020058785,0.00007272739,0.51104236,0.00005995887],"about_ca_topic_score_codex":0.000017230244,"about_ca_topic_score_gemma":0.00030092447,"teacher_disagreement_score":0.6707706,"about_ca_system_score_codex":0.000009272072,"about_ca_system_score_gemma":0.00010449799,"threshold_uncertainty_score":0.88671607},"labels":[],"label_agreement":null},{"id":"W3136423134","doi":"10.1038/s41597-021-00874-2","title":"Author Correction: High-resolution, large-scale laboratory measurements of a sandy beach and dynamic cobble berm revetment","year":2021,"lang":"en","type":"article","venue":"Scientific Data","topic":"Coastal and Marine Dynamics","field":"Earth and Planetary Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Cobble; Berm; Revetment; Scale (ratio); Environmental science; Geology; Geotechnical engineering; Hydrology (agriculture); Ecology; Geography; Cartography; Biology","score_opus":0.02847751722859263,"score_gpt":0.24724697988356958,"score_spread":0.21876946265497696,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3136423134","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":[0.91137826,0.0045259795,0.003829141,0.0014094787,0.019261936,0.0006359746,0.054751407,0.00013281504,0.0040750317],"genre_scores_gemma":[0.9344553,0.000033545202,0.0047982214,0.00008209398,0.00006061213,0.0000018470212,0.03416872,0.0000063763064,0.026393296],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99839157,0.000084097235,0.00023943369,0.0005885317,0.0004407585,0.00025560486],"domain_scores_gemma":[0.9986937,0.000033435877,0.000093116716,0.00084875,0.00020541204,0.00012558747],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011711917,0.00010491927,0.00015685255,0.000070244714,0.00033522706,0.0001423561,0.00035144406,0.000041928575,0.00080880197],"category_scores_gemma":[0.00012162796,0.00009590404,0.000019825735,0.0005790082,0.00016758722,0.000334657,0.0002847059,0.0000923574,0.000037225152],"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":[0.00011748693,0.0005439323,0.4842395,0.00026843196,0.00014043428,0.000043056694,0.0008151493,0.0007948581,0.003153188,0.0000823228,0.3881119,0.121689744],"study_design_scores_gemma":[0.0010141855,0.00011261682,0.49756503,0.000106720116,0.00012066144,0.000038039252,0.0008540832,0.23604706,0.0005747651,0.00044765978,0.26270157,0.00041759605],"about_ca_topic_score_codex":0.00057459105,"about_ca_topic_score_gemma":0.034704275,"teacher_disagreement_score":0.2352522,"about_ca_system_score_codex":0.000009595866,"about_ca_system_score_gemma":0.00022280715,"threshold_uncertainty_score":0.98290986},"labels":[],"label_agreement":null},{"id":"W3137174954","doi":"10.1038/s41597-022-01143-6","title":"A large-scale study on research code quality and execution","year":2022,"lang":"en","type":"preprint","venue":"Scientific Data","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":"University of British Columbia","funders":"Engineering and Physical Sciences Research Council; Alan Turing Institute; Alfred P. Sloan Foundation","keywords":"Computer science; Code reuse; Reuse; Replication (statistics); Coding (social sciences); Code (set theory); Transparency (behavior); Database; Set (abstract data type); Programming language; Software; Computer security","score_opus":0.7493102534435432,"score_gpt":0.600662037413241,"score_spread":0.1486482160303022,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3137174954","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":[0.87456733,0.0003111113,0.0052822004,0.003468425,0.030126669,0.0032955538,0.06922964,0.00027508396,0.013443994],"genre_scores_gemma":[0.925193,0.000009253507,0.0012318736,0.00016344401,0.00030318557,0.00013057345,0.014769413,0.000037583595,0.05816167],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.97055876,0.0050859237,0.0016293956,0.00889799,0.01282732,0.0010005881],"domain_scores_gemma":[0.97095495,0.002341125,0.0005481146,0.025176084,0.00067019457,0.00030954488],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["metaresearch","open_science","insufficient_payload"],"category_scores_codex":[0.23560409,0.00031928218,0.000573075,0.0019093801,0.0033496022,0.010205069,0.015189155,0.00010973891,0.0014529082],"category_scores_gemma":[0.012664948,0.0002639218,0.00009080756,0.0032269522,0.0008009225,0.0004964623,0.101678796,0.0015420036,0.00091596326],"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":[0.000048435602,0.0012525825,0.003946444,0.000024144365,0.00002820695,0.000021423537,0.0044211415,0.00021578006,0.00001738158,0.0008078281,0.97631454,0.012902114],"study_design_scores_gemma":[0.0005272541,0.00012533298,0.06416018,0.0000479249,0.000028749306,0.0000014282158,0.051639717,0.020782132,0.0000059222402,0.025340958,0.8369264,0.00041398895],"about_ca_topic_score_codex":0.00029610473,"about_ca_topic_score_gemma":0.0012245314,"teacher_disagreement_score":0.22293913,"about_ca_system_score_codex":0.0001742846,"about_ca_system_score_gemma":0.00040639838,"threshold_uncertainty_score":0.9999813},"labels":[],"label_agreement":null},{"id":"W3139258240","doi":"10.1038/s41597-021-01034-2","title":"A curated dataset for data-driven turbulence modelling","year":2021,"lang":"en","type":"preprint","venue":"Scientific Data","topic":"Model Reduction and Neural Networks","field":"Physics and Astronomy","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Reynolds-averaged Navier–Stokes equations; Turbulence; Benchmark (surveying); Computer science; Feature (linguistics); Large eddy simulation; Data set; Algorithm; Direct numerical simulation; Parametric statistics; Reynolds number; Data mining; Physics; Statistical physics; Artificial intelligence; Mathematics; Mechanics; Geology","score_opus":0.2410856084800902,"score_gpt":0.36543114375714847,"score_spread":0.12434553527705827,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3139258240","genre_codex":"methods","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015709097,0.00018889617,0.5676659,0.00018960238,0.004087078,0.00045922125,0.42571014,0.000031857533,0.000096412194],"genre_scores_gemma":[0.06613217,0.000019591716,0.021087678,0.00003244564,0.0007267606,0.000039754013,0.9107471,0.000028125367,0.0011863834],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962376,0.00006407834,0.0004105408,0.0025453942,0.00033715536,0.00040527608],"domain_scores_gemma":[0.99039376,0.000052976568,0.0003343597,0.008906793,0.00015951236,0.00015262725],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0007156239,0.0002845219,0.0003320045,0.000078292105,0.00037579707,0.0015922232,0.004922367,0.00009582486,0.0006219071],"category_scores_gemma":[0.000022550617,0.00027653572,0.00006487442,0.0002407719,0.00016203921,0.00080232474,0.0103057865,0.0005218263,0.000044141965],"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":[0.0000099049275,0.00010087761,0.000009089081,0.00006926835,0.000089978086,0.0000017497399,0.000047474303,0.1711396,0.00005630788,0.00021238584,0.81611997,0.01214342],"study_design_scores_gemma":[0.000119228665,0.0000021778299,3.2988567e-7,0.000099684774,0.000073068986,6.2131886e-7,0.000063485626,0.7628656,0.000062541585,0.000771624,0.23571107,0.00023057433],"about_ca_topic_score_codex":0.00022381631,"about_ca_topic_score_gemma":0.0000173803,"teacher_disagreement_score":0.591726,"about_ca_system_score_codex":0.000014125126,"about_ca_system_score_gemma":0.00042721094,"threshold_uncertainty_score":0.9999687},"labels":[],"label_agreement":null},{"id":"W3159019058","doi":"10.1038/s41597-021-00900-3","title":"COVID-CT-MD, COVID-19 computed tomography scan dataset applicable in machine learning and deep learning","year":2021,"lang":"en","type":"article","venue":"Scientific Data","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":204,"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; Health Sciences Centre; University of Toronto; Sunnybrook Health Science Centre; McGill University Health Centre; Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Coronavirus disease 2019 (COVID-19); Computed tomography; Artificial intelligence; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Chest radiograph; Computer science; Pneumonia; Medicine; Tomography; Radiology; Machine learning; Medical physics; Radiography; Infectious disease (medical specialty); Pathology; Disease; Internal medicine","score_opus":0.052622199486004814,"score_gpt":0.3532226569827437,"score_spread":0.30060045749673886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3159019058","genre_codex":"empirical","genre_gemma":"dataset","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":[0.32457966,0.12489702,0.07820524,0.26741526,0.010215639,0.012029596,0.1745121,0.0058583524,0.002287145],"genre_scores_gemma":[0.40089217,0.00086879433,0.010851371,0.034879487,0.00028371878,0.00008073311,0.5497575,0.000154884,0.0022313546],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99589187,0.0003430308,0.00047733853,0.0019831616,0.0006819453,0.00062266865],"domain_scores_gemma":[0.99593014,0.00076901825,0.00016706673,0.0021267955,0.00009861995,0.000908338],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002964787,0.00028098153,0.00049981533,0.00066677725,0.0007570706,0.0005829641,0.00074649544,0.00007553247,0.000879719],"category_scores_gemma":[0.004979244,0.0002948231,0.000052214004,0.002691974,0.00055758114,0.00036677023,0.0022316566,0.0007769881,0.000091562935],"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":[0.00013595892,0.00080580724,0.22593226,0.0013964425,0.000121777724,0.002042016,0.0007568129,0.003468555,0.008265587,0.0001065272,0.7329492,0.024019063],"study_design_scores_gemma":[0.0019331087,0.000046675625,0.0015178171,0.00011691055,0.000097770244,0.00019812255,0.00030331142,0.04822017,0.0004129327,0.00005483657,0.94681257,0.0002857583],"about_ca_topic_score_codex":0.0016279853,"about_ca_topic_score_gemma":0.003229416,"teacher_disagreement_score":0.3752454,"about_ca_system_score_codex":0.00023848162,"about_ca_system_score_gemma":0.0011294688,"threshold_uncertainty_score":0.9999504},"labels":[],"label_agreement":null},{"id":"W3162096660","doi":"10.1038/s41597-021-00912-z","title":"Global data on earthworm abundance, biomass, diversity and corresponding environmental properties","year":2021,"lang":"en","type":"article","venue":"Scientific Data","topic":"Invertebrate Taxonomy and Ecology","field":"Agricultural and Biological Sciences","cited_by":70,"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 Research Chairs; Natural Resources Canada; University of Toronto; Université de Sherbrooke; McGill University; Saint Mary's University","funders":"Biotechnology and Biological Sciences Research Council; Deutsches Zentrum für integrative Biodiversitätsforschung Halle-Jena-Leipzig; Bundesministerium für Bildung und Forschung; Academy of Finland; Russian Foundation for Basic Research; Agence Nationale de la Recherche; Deutsche Forschungsgemeinschaft; Natural Sciences and Engineering Research Council of Canada; European Commission","keywords":"Earthworm; Abundance (ecology); Biomass (ecology); Diversity (politics); Ecology; Environmental science; Macroecology; Biodiversity; Biology","score_opus":0.0991375172588764,"score_gpt":0.22149763468346598,"score_spread":0.12236011742458958,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3162096660","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":[0.98920774,0.00023078787,0.000001860625,0.00047785105,0.00085265085,0.00008273295,0.008458686,0.000024828767,0.00066283514],"genre_scores_gemma":[0.99101067,0.00002049288,0.000057493915,0.0001661937,0.000072425966,8.261504e-7,0.0071376716,3.188872e-7,0.0015339243],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985615,0.00006196815,0.00010230942,0.0008410875,0.00018084946,0.0002522824],"domain_scores_gemma":[0.99932206,0.000032173037,0.000040658633,0.000514471,0.000009477044,0.00008115476],"candidate_categories":["sts","open_science"],"consensus_categories":[],"category_scores_codex":[0.0004620942,0.0000919353,0.00010068297,0.000006095566,0.0017340649,0.00023239467,0.0011900751,0.000049096856,0.00078960735],"category_scores_gemma":[0.000057696274,0.000040045063,0.000012883587,0.00024780454,0.00034798647,0.00057160814,0.009240887,0.000052980362,0.00020031969],"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":[0.00017332991,0.00059806596,0.47129923,0.000024444877,0.0000689222,0.00016111867,0.00022668678,0.0000016937745,0.11013997,0.0005584144,0.21246605,0.20428206],"study_design_scores_gemma":[0.00020373154,0.00008227505,0.3310324,0.000021186324,0.000022784723,0.000038762588,0.00087822776,0.00170609,0.0027108835,0.00016067567,0.6628703,0.0002727123],"about_ca_topic_score_codex":0.00008390514,"about_ca_topic_score_gemma":0.0031720975,"teacher_disagreement_score":0.45040423,"about_ca_system_score_codex":0.0000247686,"about_ca_system_score_gemma":0.00001547064,"threshold_uncertainty_score":0.99956554},"labels":[],"label_agreement":null},{"id":"W3164073423","doi":"10.1038/s41597-021-00922-x","title":"Regional zircon U-Pb geochronology for the Maniitsoq region, southwest Greenland","year":2021,"lang":"en","type":"article","venue":"Scientific Data","topic":"Geological and Geochemical Analysis","field":"Earth and Planetary Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Geochronology; Zircon; Geology; Geochemistry","score_opus":0.07962031749569724,"score_gpt":0.24219144157598796,"score_spread":0.16257112408029073,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3164073423","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":[0.55873674,0.046601433,0.0879281,0.22780499,0.012205056,0.002190081,0.04112928,0.0005538952,0.022850398],"genre_scores_gemma":[0.94433564,0.00016277668,0.0044442434,0.0018467427,0.0005866263,0.0000056374697,0.035690304,0.0000044918074,0.012923514],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99839425,0.00005583548,0.00019147007,0.0007734752,0.00023224262,0.0003527009],"domain_scores_gemma":[0.9982283,0.00041052702,0.00006717324,0.0010609395,0.00013114147,0.00010192191],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005662993,0.00010699044,0.00014966833,0.000035173056,0.00059722766,0.00021341539,0.0012006962,0.00006163401,0.0065988866],"category_scores_gemma":[0.00029783073,0.00006168665,0.00007903527,0.00042553348,0.000520135,0.00020665598,0.00018560488,0.00011155772,0.00054901827],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008062695,0.00010013357,0.12825893,0.00004463539,0.00020204062,0.00010577467,0.00013834432,0.00049330445,0.0015925812,0.0018989668,0.7568531,0.11023154],"study_design_scores_gemma":[0.00028667066,0.000029979878,0.11415714,0.000007893428,0.00010368727,0.00009200735,0.0003107297,0.012330691,0.00034996102,0.028667415,0.84346455,0.00019924006],"about_ca_topic_score_codex":0.0011606875,"about_ca_topic_score_gemma":0.023078913,"teacher_disagreement_score":0.3855989,"about_ca_system_score_codex":0.000001662556,"about_ca_system_score_gemma":0.0000816724,"threshold_uncertainty_score":0.99474734},"labels":[],"label_agreement":null},{"id":"W3165720173","doi":"10.1038/s41597-021-00916-9","title":"A 120,000-year long climate record from a NW-Greenland deep ice core at ultra-high resolution","year":2021,"lang":"en","type":"article","venue":"Scientific Data","topic":"Geology and Paleoclimatology Research","field":"Earth and Planetary Sciences","cited_by":68,"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","funders":"FP7 Environment; FP7 Ideas: European Research Council; Natural Environment Research Council; National Institute of Polar Research; Institut Polaire Français Paul Emile Victor; Centre National de la Recherche Scientifique; Korea Polar Research Institute; Agence Nationale de la Recherche; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Natural Resources Canada; Fonds Wetenschappelijk Onderzoek; Office of Polar Programs; Fonds De La Recherche Scientifique - FNRS; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Research Foundation; European Commission; Danmarks Grundforskningsfond; Villum Fonden; National Science Foundation","keywords":"Stadial; Ice core; Eemian; Geology; Chronology; Glacial period; Interglacial; Paleoclimatology; Abrupt climate change; Oceanography; Physical geography; Climatology; Climate change; Paleontology; Global warming; Geography; Effects of global warming","score_opus":0.059446238654265494,"score_gpt":0.27403551176324836,"score_spread":0.21458927310898288,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3165720173","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":[0.9753845,0.0015446268,0.000093904804,0.0005155438,0.0027104663,0.00017132491,0.012448954,0.00006166829,0.0070690312],"genre_scores_gemma":[0.9218045,0.0002937404,0.002298129,0.00013541624,0.00013969619,0.0000017462546,0.071311355,0.0000056122467,0.0040098066],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99685997,0.00032574826,0.00030375554,0.0012640265,0.0004519866,0.00079449476],"domain_scores_gemma":[0.9971493,0.0004709677,0.00010196345,0.0019189288,0.000121184894,0.00023766741],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0015808502,0.00016731829,0.00025456064,0.000118877564,0.0010342438,0.00023810648,0.0012432009,0.00018668103,0.019191045],"category_scores_gemma":[0.00041392152,0.00014914821,0.00004551688,0.0006361565,0.000667262,0.00044353303,0.00033171967,0.00033014893,0.0066295266],"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":[0.00012134831,0.000023697527,0.9812328,0.000021673199,0.000028450626,0.0002554399,0.00010482778,0.0000414327,0.00010070729,0.000026330325,0.015785886,0.0022573923],"study_design_scores_gemma":[0.00053804653,0.000039939943,0.9650682,0.000036626196,0.00004615888,0.00012553159,0.00020166929,0.0076668486,0.000181571,0.0008841386,0.024971563,0.00023968222],"about_ca_topic_score_codex":0.0014241105,"about_ca_topic_score_gemma":0.16387676,"teacher_disagreement_score":0.16245265,"about_ca_system_score_codex":0.0000037832876,"about_ca_system_score_gemma":0.00012508135,"threshold_uncertainty_score":0.9941439},"labels":[],"label_agreement":null},{"id":"W3173654308","doi":"10.1038/s41597-021-00948-1","title":"Profiling the small non-coding RNA transcriptome of the human placenta","year":2021,"lang":"en","type":"article","venue":"Scientific Data","topic":"Cancer-related molecular mechanisms research","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":"BC Children's Hospital; University of British Columbia; Canadian Centre for Applied Research in Cancer Control; Izaak Walton Killam Health Centre","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; Canadian Institutes of Health Research; National Institutes of Health","keywords":"Transcriptome; Biology; microRNA; Placenta; Gene expression profiling; RNA; Computational biology; Genetics; Gene expression; Gene; Small nucleolar RNA; Bioinformatics; Fetus; Pregnancy; Non-coding RNA","score_opus":0.0531514596618521,"score_gpt":0.31158717941894265,"score_spread":0.25843571975709057,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3173654308","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":[0.9460856,0.0026145405,0.03353835,0.0018212032,0.0044951737,0.0013492987,0.0034384727,0.000024870604,0.006632513],"genre_scores_gemma":[0.9925451,0.000030532337,0.00044613722,0.00009388594,0.00009872879,0.00001041095,0.0018399227,0.000019619874,0.00491561],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99844205,0.00011250511,0.00019310684,0.00062212674,0.00035143414,0.0002787717],"domain_scores_gemma":[0.99698865,0.000009065055,0.0000666287,0.0027416947,0.00014514619,0.000048800954],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009647142,0.000098568125,0.00009188316,0.000030547842,0.00040439318,0.0001405625,0.0018746409,0.000075423624,0.000056769528],"category_scores_gemma":[0.00016299493,0.000066229855,0.00008200744,0.00039666065,0.00028295742,0.000005000065,0.0013893802,0.0001852364,0.000006881059],"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":[0.000006584912,0.000026400248,0.00001668964,0.000026334252,0.00003413477,0.000002522642,0.00004721101,0.00002770672,0.9919917,0.00022210287,0.0069833416,0.00061525224],"study_design_scores_gemma":[0.0002470488,0.000015130538,0.00007164987,0.000034258923,0.000022510781,0.000009598238,0.00020292851,0.00044845403,0.96879715,0.000051764033,0.030018767,0.000080716534],"about_ca_topic_score_codex":0.000020074953,"about_ca_topic_score_gemma":0.00020051993,"teacher_disagreement_score":0.04645957,"about_ca_system_score_codex":0.000015107577,"about_ca_system_score_gemma":0.00033222014,"threshold_uncertainty_score":0.34835804},"labels":[],"label_agreement":null},{"id":"W3174112108","doi":"10.1038/s41597-021-00947-2","title":"Eight soybean reference genome resources from varying latitudes and agronomic traits","year":2021,"lang":"en","type":"article","venue":"Scientific Data","topic":"Soybean genetics and cultivation","field":"Agricultural and Biological Sciences","cited_by":33,"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 Key Project; Ministry of Science and Technology of the People's Republic of China; Chinese Academy of Sciences","keywords":"Biology; Genome; Latitude; Agronomy; Biotechnology; Geography; Gene; Genetics","score_opus":0.0739302925013132,"score_gpt":0.2376375944388343,"score_spread":0.16370730193752112,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3174112108","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":[0.9949841,0.0007226225,0.0000058486216,0.00035472942,0.00015082133,0.000055479944,0.0026867916,0.000021969117,0.0010176545],"genre_scores_gemma":[0.98963165,0.000028712513,0.0007212854,0.00006470323,0.00015052021,0.000001592975,0.008542644,7.1825565e-7,0.0008581996],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9988431,0.000041203235,0.0001389063,0.00065255316,0.000161948,0.00016228622],"domain_scores_gemma":[0.99954486,0.000071796116,0.000051320487,0.0002131175,0.000045946603,0.00007294328],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024369126,0.00008126304,0.000089271394,0.000007903123,0.00036820766,0.0005310522,0.00051190483,0.000040614963,0.00053986453],"category_scores_gemma":[0.000050395065,0.000035972414,0.000014492279,0.00021935631,0.000100253645,0.00018823007,0.00048728962,0.000056431953,0.00005073577],"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":[0.0000027610429,0.000026106289,0.001734445,0.0000021552614,0.000009028721,0.0000020011776,0.00019808512,0.0000015428177,0.9619979,0.00009652225,0.0012848648,0.03464457],"study_design_scores_gemma":[0.00010837592,0.000017211472,0.81186897,0.000021290538,0.000016180342,0.0000022214924,0.00068003417,0.00042068044,0.0054307687,0.0012731021,0.17996284,0.00019830416],"about_ca_topic_score_codex":0.00009483326,"about_ca_topic_score_gemma":0.0006993114,"teacher_disagreement_score":0.95656717,"about_ca_system_score_codex":0.0000071807453,"about_ca_system_score_gemma":0.000011955715,"threshold_uncertainty_score":0.5911138},"labels":[],"label_agreement":null},{"id":"W3176041963","doi":"10.1038/s41597-021-00939-2","title":"GlobSnow v3.0 Northern Hemisphere snow water equivalent dataset","year":2021,"lang":"en","type":"article","venue":"Scientific Data","topic":"Cryospheric studies and observations","field":"Earth and Planetary Sciences","cited_by":221,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Environment and Climate Change Canada","funders":"Academy of Finland; European Space Agency","keywords":"Snow; Water equivalent; Northern Hemisphere; Environmental science; Snowpack; Radiometer; Climatology; Defense Meteorological Satellite Program; Satellite; Meteorology; Remote sensing; Geography; Geology","score_opus":0.07065568232724688,"score_gpt":0.26332201574937014,"score_spread":0.19266633342212325,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3176041963","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43354154,0.009027042,0.0011827643,0.010598516,0.0156241525,0.000626448,0.5168164,0.0004315611,0.012151598],"genre_scores_gemma":[0.1419806,0.00020275876,0.003983026,0.0010977197,0.0005063557,0.000002604179,0.8356646,0.000017686383,0.016544698],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979297,0.000042106476,0.00023608441,0.0008684818,0.0004543279,0.0004693275],"domain_scores_gemma":[0.99740136,0.00006979117,0.000041214436,0.002236337,0.000105579216,0.00014572087],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00054873864,0.00013976563,0.00015067465,0.0000125605575,0.0006986864,0.00051083486,0.0011842586,0.000036714344,0.017179959],"category_scores_gemma":[0.00015387539,0.00009824557,0.00003588375,0.0003998861,0.00019705265,0.000482262,0.0005580274,0.00009787664,0.0037238677],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000061524647,0.000042238622,0.07355642,0.000019895419,0.000037514048,0.00006195655,0.00012716636,0.0002551177,0.00015740028,0.000013495862,0.8822046,0.04351803],"study_design_scores_gemma":[0.000139862,0.000008923392,0.0369873,0.00001351084,0.00002505495,0.00001174435,0.000491194,0.0024790787,0.00039061208,0.00017120516,0.95910764,0.0001738722],"about_ca_topic_score_codex":0.0010055553,"about_ca_topic_score_gemma":0.050462734,"teacher_disagreement_score":0.31884816,"about_ca_system_score_codex":0.0000060534676,"about_ca_system_score_gemma":0.000111068846,"threshold_uncertainty_score":0.99705184},"labels":[],"label_agreement":null},{"id":"W3180664812","doi":"10.1038/s41597-021-00968-x","title":"A comprehensive annotation dataset of intact LTR retrotransposons of 300 plant genomes","year":2021,"lang":"en","type":"article","venue":"Scientific Data","topic":"Chromosomal and Genetic Variations","field":"Agricultural and Biological 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 British Columbia; Université Laval","funders":"Fundamental Research Funds for the Central Universities; Beijing Forestry University; National Natural Science Foundation of China","keywords":"Retrotransposon; Genome; Annotation; Biology; Long terminal repeat; Computational biology; Genetics; Transposable element; Evolutionary biology; Gene","score_opus":0.0803311561539355,"score_gpt":0.27020608102150895,"score_spread":0.18987492486757346,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3180664812","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":[0.7033252,0.0003395126,0.00001093482,0.00041384553,0.0002558559,0.000088092485,0.2954763,0.000007777402,0.00008250606],"genre_scores_gemma":[0.7708576,0.00003734626,0.00082594913,0.000027028347,0.000039414383,0.0000015537333,0.22810665,3.9461892e-7,0.00010409942],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.999011,0.0000510204,0.00024114846,0.0003593922,0.0002215125,0.000115964394],"domain_scores_gemma":[0.999273,0.00009991007,0.00010734307,0.00033594508,0.0001396229,0.000044193446],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014948564,0.00006154614,0.00012760627,0.000012529012,0.00012104096,0.00004495999,0.0005230451,0.00002963251,0.00070653704],"category_scores_gemma":[0.00004369578,0.00002729142,0.000029003157,0.00051589805,0.0001246722,0.00013416131,0.00024129453,0.000039707713,0.000016414242],"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":[0.000009610692,0.0001316559,0.0019826745,0.000023871045,0.000020792782,0.0000041301164,0.00015213274,0.00000864373,0.9715711,0.0002536725,0.016282907,0.009558847],"study_design_scores_gemma":[0.00025313877,0.00012409511,0.21334718,0.00006386196,0.00006397333,0.000018678633,0.0011607168,0.00097036886,0.09704614,0.00084502395,0.68589795,0.00020885622],"about_ca_topic_score_codex":0.000102861304,"about_ca_topic_score_gemma":0.00078269705,"teacher_disagreement_score":0.87452495,"about_ca_system_score_codex":0.0000044813296,"about_ca_system_score_gemma":0.000035618326,"threshold_uncertainty_score":0.77360857},"labels":[],"label_agreement":null},{"id":"W3181216097","doi":"10.1038/s41597-021-00955-2","title":"A sub-national real-time epidemiological and vaccination database for the COVID-19 pandemic in Canada","year":2021,"lang":"en","type":"article","venue":"Scientific Data","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Guelph; SickKids Foundation; Hospital for Sick Children; Public Health Ontario; University of Toronto","funders":"Medical Research Council; National Institute for Health and Care Research; Wellcome Trust","keywords":"Pandemic; Coronavirus disease 2019 (COVID-19); Dashboard; Public health; Epidemiology; Outbreak; Vaccination; Open data; Geography; Political science; Medicine; Database; Computer science; World Wide Web; Nursing; Virology; Infectious disease (medical specialty)","score_opus":0.13854344895396647,"score_gpt":0.3767589396202392,"score_spread":0.23821549066627273,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3181216097","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":[0.6085061,0.003552056,0.005324378,0.036161073,0.0020390507,0.0031079222,0.34002325,0.000189711,0.0010964749],"genre_scores_gemma":[0.6801311,0.0006561057,0.0038679834,0.007118463,0.00024937803,0.00013276155,0.3055641,0.000027096545,0.0022530335],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.998178,0.00017533623,0.00027680228,0.00073641975,0.0004030891,0.00023034244],"domain_scores_gemma":[0.9963354,0.0019700548,0.00008078423,0.0012208734,0.00017427467,0.00021862512],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0041055353,0.00009117717,0.0002006614,0.000054336506,0.0001767106,0.000055567143,0.00040192434,0.0000277118,0.0003239176],"category_scores_gemma":[0.017341813,0.000064642,0.000018669693,0.00037148735,0.000097294076,0.00019051634,0.0005132772,0.00009839968,0.000014070043],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008963676,0.00005582127,0.1091578,0.00009579112,0.000025489957,0.000064491345,0.000019152469,0.00003755119,0.0026005183,0.00031716205,0.8841216,0.0034149634],"study_design_scores_gemma":[0.002568923,0.0000150512615,0.4455865,0.00004094175,0.00006773534,0.00016169465,0.00016513786,0.07966857,0.00006850252,0.00092255126,0.47052565,0.0002087516],"about_ca_topic_score_codex":0.06945659,"about_ca_topic_score_gemma":0.6832219,"teacher_disagreement_score":0.6137653,"about_ca_system_score_codex":0.0005422721,"about_ca_system_score_gemma":0.006607014,"threshold_uncertainty_score":0.9990246},"labels":[],"label_agreement":null},{"id":"W3188227111","doi":"10.1038/s41597-021-00983-y","title":"Global data set of long-term summertime vertical temperature profiles in 153 lakes","year":2021,"lang":"en","type":"article","venue":"Scientific Data","topic":"Marine and coastal ecosystems","field":"Earth and Planetary Sciences","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ministry of the Environment, Conservation and Parks; Toronto Metropolitan University; University of Alberta; Université Laval; Laurentian University; University of Regina; International Institute for Sustainable Development","funders":"Natural Sciences and Engineering Research Council of Canada; Analyses et Expérimentations pour les Ecosystèmes; Suomen Ympäristökeskus; Russian Science Foundation; Institut National de la Recherche Agronomique; Ministry of Environment; Ministry of Business, Innovation and Employment; Vetenskapsrådet; University of California, Davis; University of Regina; Österreichischen Akademie der Wissenschaften; Ministère de l’Environnement, de la Protection de la nature et des Parcs; National Science Foundation; Belgian Federal Science Policy Office; Sight Research UK; Global Lake Ecological Observatory Network; Agence Nationale de la Recherche; Natural Environment Research Council; Florida International University; Klima- und Energiefonds; Russian Foundation for Basic Research; Queen's University; South Florida Water Management District; Canada Research Chairs","keywords":"Expansive; Environmental science; Climate change; Term (time); Global warming; Global change; Climatology; Geology; Atmospheric sciences; Physical geography; Hydrology (agriculture); Oceanography; Geography","score_opus":0.04959490324252962,"score_gpt":0.2750340758207046,"score_spread":0.22543917257817497,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3188227111","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":[0.9300844,0.0010469668,0.000012399996,0.0003540438,0.0013731943,0.00016415518,0.06255394,0.000022939503,0.0043879338],"genre_scores_gemma":[0.8963368,0.000012435515,0.00017111354,0.000036918922,0.00008980151,3.699362e-7,0.102198586,0.0000020752611,0.0011519039],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99793893,0.000107736756,0.00031823642,0.0008794779,0.00043754687,0.00031804416],"domain_scores_gemma":[0.9970755,0.000050331237,0.000040240047,0.0026540228,0.00006186475,0.00011804631],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00083709444,0.00011646419,0.00020667305,0.000050066752,0.000096869946,0.00032869878,0.0020222166,0.00006474542,0.0027416532],"category_scores_gemma":[0.00023449863,0.00009484793,0.000021027008,0.0008445775,0.00016892476,0.0007618563,0.0008755486,0.00010376827,0.0002106319],"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":[0.000021362262,0.000045057724,0.92101634,0.00011098284,0.000015806394,0.00016735442,0.000028576998,0.000017928232,0.00023611009,0.00004370425,0.056162905,0.02213386],"study_design_scores_gemma":[0.0003677832,0.000033876513,0.95588976,0.00014170204,0.000028361004,0.00007505951,0.00023122624,0.01621119,0.0006371387,0.00013582897,0.025978839,0.00026922955],"about_ca_topic_score_codex":0.0012371443,"about_ca_topic_score_gemma":0.1290593,"teacher_disagreement_score":0.12782216,"about_ca_system_score_codex":0.0000033608387,"about_ca_system_score_gemma":0.0003208228,"threshold_uncertainty_score":0.99816996},"labels":[],"label_agreement":null},{"id":"W3194100603","doi":"10.1038/s41597-021-01005-7","title":"Community composition of aquatic fungi across the thawing Arctic","year":2021,"lang":"en","type":"article","venue":"Scientific Data","topic":"Climate change and permafrost","field":"Earth and Planetary 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":"Université Laval; Center for Northern Studies; Université du Québec à Chicoutimi","funders":"Uppsala Multidisciplinary Center for Advanced Computational Science; Science for Life Laboratory; Sveriges Lantbruksuniversitet","keywords":"Permafrost; Thermokarst; Arctic; Environmental science; Aquatic ecosystem; Total organic carbon; Dissolved organic carbon; Environmental chemistry; Detritus; Ecology; Carbon fibers; Sediment; Biogeochemistry; Biology; Chemistry","score_opus":0.15627784578772005,"score_gpt":0.318352947738224,"score_spread":0.16207510195050392,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3194100603","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":[0.9603304,0.0010233566,0.00004219808,0.0005366836,0.0012113205,0.00008050828,0.035507705,0.000012666592,0.0012551192],"genre_scores_gemma":[0.93553257,0.000025351419,0.0000715647,0.00013681414,0.00004242706,1.9965067e-7,0.0639039,0.0000015238929,0.00028562505],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9989041,0.00024501732,0.0001616436,0.00021226384,0.00026624926,0.000210689],"domain_scores_gemma":[0.9979609,0.00031106212,0.000061534905,0.0015675018,0.00005194701,0.000047053207],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0018108216,0.00006349686,0.00009729116,0.00001924996,0.0009025054,0.00030918908,0.00096477545,0.000022713126,0.002791379],"category_scores_gemma":[0.000088213375,0.000043956356,0.000027645607,0.00040760558,0.00032777805,0.00031599152,0.00024211881,0.00016611618,0.0002749134],"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":[0.00004258462,0.00024024757,0.8304978,0.00039300375,0.0000747364,0.000040565847,0.01934626,0.00025637366,0.03253729,0.000085433494,0.05520185,0.06128388],"study_design_scores_gemma":[0.00037126482,0.000046915437,0.9066941,0.00020695214,0.00006617867,0.0000860702,0.016886234,0.035606865,0.004440958,0.0014293849,0.033882488,0.00028259217],"about_ca_topic_score_codex":0.004725453,"about_ca_topic_score_gemma":0.060568824,"teacher_disagreement_score":0.07619632,"about_ca_system_score_codex":0.0000022632582,"about_ca_system_score_gemma":0.000043333028,"threshold_uncertainty_score":0.9981202},"labels":[],"label_agreement":null},{"id":"W3194353469","doi":"10.1038/s41597-022-01389-0","title":"Inter-species cell detection - datasets on pulmonary hemosiderophages in equine, human and feline specimens","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"AI in cancer detection","field":"Computer Science","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":"University of Guelph","funders":"","keywords":"Annotation; Computer science; Pipeline (software); Artificial intelligence; Cytology; Hemosiderin; Pathology; Medicine","score_opus":0.053244949372914664,"score_gpt":0.2823903223557649,"score_spread":0.22914537298285023,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3194353469","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":[0.70844316,0.0030786917,0.18668878,0.006669588,0.040855113,0.003284295,0.036958624,0.0016212243,0.0124005275],"genre_scores_gemma":[0.99446476,0.000008903713,0.0012546098,0.00012081279,0.000106790925,0.000025249828,0.0020316849,0.000012514732,0.0019746996],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974256,0.00014486689,0.0002808035,0.0013152629,0.0005322017,0.00030123157],"domain_scores_gemma":[0.9970292,0.00005877118,0.000117464464,0.0027030369,0.000021930964,0.000069621216],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013623106,0.00014759979,0.00013271083,0.000402799,0.000797966,0.00053238403,0.002378546,0.000025833764,0.00017750802],"category_scores_gemma":[0.000031807995,0.00015738214,0.000017555674,0.0009858831,0.000160427,0.0010774321,0.005451539,0.00031850836,0.000037334692],"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":[0.00007210075,0.00076897757,0.00040117142,0.00008375135,0.0000158288,0.00031426697,0.0008174731,0.0006213453,0.57039607,0.00087679864,0.2686821,0.15695012],"study_design_scores_gemma":[0.0011007442,0.0008238401,0.007872279,0.000054287644,0.000017000793,0.00017649993,0.000703547,0.13393003,0.11331375,0.0029842302,0.73818606,0.0008377355],"about_ca_topic_score_codex":0.000086609434,"about_ca_topic_score_gemma":0.00034284368,"teacher_disagreement_score":0.46950394,"about_ca_system_score_codex":0.00019183467,"about_ca_system_score_gemma":0.000040736988,"threshold_uncertainty_score":0.67949533},"labels":[],"label_agreement":null},{"id":"W3194760139","doi":"10.1038/s41597-021-00941-8","title":"Open-access quantitative MRI data of the spinal cord and reproducibility across participants, sites and manufacturers","year":2021,"lang":"en","type":"article","venue":"Scientific Data","topic":"Advanced Neuroimaging Techniques and Applications","field":"Medicine","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":"Philips (Canada); McGill University; Centre Hospitalier Universitaire de Sherbrooke; International Collaboration On Repair Discoveries; University of British Columbia; Université de Montréal; Université de Sherbrooke; Centre Hospitalier Universitaire Sainte-Justine; Polytechnique Montréal; Montreal Neurological Institute and Hospital; Mila - Quebec Artificial Intelligence Institute","funders":"National Institute of Neurological Disorders and Stroke; Staatssekretariat für Bildung, Forschung und Innovation; Economic and Social Research Council; Engineering and Physical Sciences Research Council; Natural Sciences and Engineering Research Council of Canada; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; CRIS Cancer Foundation; Regione Puglia; University College London Hospitals NHS Foundation Trust; Ministero dell’Istruzione, dell’Università e della Ricerca; Ministero della Salute; Concordia University; Agentura Pro Zdravotnický Výzkum České Republiky; National Institutes of Health; Rosetrees Trust; European Commission; Multiple Sclerosis Society; Bundesministerium für Bildung und Forschung; National Imaging Facility; National Institute for Health and Care Research; University of Pennsylvania; SpinalCure Australia; University of Minnesota; National Science Foundation; Compute Canada; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; Polytechnique Montréal; Wellcome Trust; Institut de Valorisation des Données; AstraZeneca; Craig H. Neilsen Foundation; McGill University; Canada First Research Excellence Fund; Max-Planck-Gesellschaft","keywords":"Protocol (science); Reproducibility; Computer science; Spinal cord; Documentation; Data mining; Medicine; Statistics; Mathematics; Pathology","score_opus":0.6245720496163727,"score_gpt":0.5767339061992035,"score_spread":0.04783814341716919,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3194760139","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":[0.97710985,0.00088953576,0.00205192,0.009303352,0.0002566038,0.0007403863,0.009503441,0.000037135735,0.00010778686],"genre_scores_gemma":[0.9789385,0.000099192366,0.01814502,0.0002599098,0.00001516891,0.000009316887,0.0017568694,0.000009039199,0.00076698064],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9976369,0.000044819986,0.00019837862,0.0017907402,0.00016344877,0.00016570064],"domain_scores_gemma":[0.98995715,0.000044924953,0.00011040975,0.0097200265,0.00009863014,0.00006886664],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0017389944,0.000074910815,0.00016230528,0.000013965857,0.00027861982,0.00038245367,0.0020976078,0.00001643681,0.000017623679],"category_scores_gemma":[0.0016168478,0.000051979492,0.000009079192,0.00034067745,0.00087198993,0.00073388603,0.014951757,0.00011193956,0.0000011823142],"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":[0.00120456,0.001297933,0.23418726,0.0011080113,0.00015555492,0.00006166913,0.0009659761,0.0000049692617,0.22136533,0.0059276978,0.41619608,0.11752496],"study_design_scores_gemma":[0.000780884,0.00017075146,0.5823219,0.00032497212,0.00019970427,0.00010520746,0.0009842508,0.0027938688,0.1386297,0.008398251,0.2650311,0.00025944266],"about_ca_topic_score_codex":0.000051584786,"about_ca_topic_score_gemma":0.00013941227,"teacher_disagreement_score":0.3481346,"about_ca_system_score_codex":0.000006068723,"about_ca_system_score_gemma":0.00010308314,"threshold_uncertainty_score":0.9930151},"labels":[{"model":"gemma","categories":["metaresearch","open_science"],"domain":"reproducibility","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":["metaresearch","open_science"],"domain":"reproducibility","study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W3194991922","doi":"10.1038/s41597-021-01001-x","title":"Monitoring non-pharmaceutical public health interventions during the COVID-19 pandemic","year":2021,"lang":"en","type":"article","venue":"Scientific Data","topic":"Food Security and Health in Diverse Populations","field":"Health Professions","cited_by":25,"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 Health Centre; McGill University","funders":"Economic and Social Research Council; Medical Research Council; Canadian Institutes of Health Research; Government of Canada","keywords":"Psychological intervention; Mandate; Pandemic; Public health; Coronavirus disease 2019 (COVID-19); Business; Public relations; Data science; Political science; Medicine; Computer science; Nursing; Infectious disease (medical specialty)","score_opus":0.7925991294067783,"score_gpt":0.6259501303240302,"score_spread":0.1666489990827481,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3194991922","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":[0.55488217,0.011094095,0.009250153,0.34144112,0.05392736,0.004376418,0.019949818,0.0011802407,0.0038986302],"genre_scores_gemma":[0.97759396,0.00056309736,0.0010175166,0.004223733,0.0008781229,0.00012883257,0.0033415114,0.000029092867,0.012224114],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99562395,0.0011743645,0.000850697,0.0008246564,0.00053024775,0.0009960965],"domain_scores_gemma":[0.99565655,0.0005285185,0.00027539762,0.0024148056,0.00023593756,0.00088876544],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0071779517,0.00013848156,0.00024011124,0.00016865582,0.009568969,0.00021950324,0.0014250452,0.00011517964,0.002246025],"category_scores_gemma":[0.0027812123,0.00011569724,0.00009403331,0.0010789494,0.00031076514,0.0005605248,0.0025277054,0.001110605,0.00093631557],"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":[0.000026448515,0.00048639992,0.573901,0.005075115,0.00011009027,0.00003731403,0.020298535,0.00003135368,0.00027814662,0.00597683,0.38834724,0.0054315384],"study_design_scores_gemma":[0.00078469823,0.000011080336,0.057270207,0.0003404724,0.00002277357,0.000021819129,0.010540827,0.0007055178,0.0000063728144,0.000494682,0.9296445,0.00015700124],"about_ca_topic_score_codex":0.0003457215,"about_ca_topic_score_gemma":0.0026623702,"teacher_disagreement_score":0.5412973,"about_ca_system_score_codex":0.0005907023,"about_ca_system_score_gemma":0.0036105635,"threshold_uncertainty_score":0.9998416},"labels":[],"label_agreement":null},{"id":"W3195389227","doi":"10.1038/s41597-021-01007-5","title":"MNI-FTD templates, unbiased average templates of frontotemporal dementia variants","year":2021,"lang":"en","type":"article","venue":"Scientific Data","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Douglas Mental Health University Institute; McGill University; Centres Intégré Universitaires de Santé et de Services Sociaux; Montreal Neurological Institute and Hospital","funders":"National Institute on Aging; Alzheimer Society Research Program; University of California, San Francisco; Canadian Institutes of Health Research; University of Southern California; Alzheimer Society; National Institutes of Health; Consortium canadien en neurodégénérescence associée au vieillissement; Sanofi","keywords":"Frontotemporal dementia; Template; Computer science; Atrophy; Semantic dementia; Neuroimaging; Dementia; Probabilistic logic; Artificial intelligence; Medicine; Biology; Neuroscience; Pathology; Disease","score_opus":0.07653904424421291,"score_gpt":0.3469934429536982,"score_spread":0.2704543987094853,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3195389227","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":[0.9617217,0.0023775261,0.0036055064,0.0011602341,0.0022233634,0.0011166179,0.007566315,0.0001281186,0.020100605],"genre_scores_gemma":[0.97009987,0.000028548831,0.0030769382,0.000113821094,0.00007514284,0.000009384995,0.012544384,0.00002252761,0.0140294],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9967169,0.00014304779,0.0005016169,0.0010341703,0.0010689355,0.00053529005],"domain_scores_gemma":[0.9968344,0.00008272464,0.00013553548,0.0021632968,0.00051813666,0.00026592024],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00176342,0.0001882071,0.00036619685,0.00021815312,0.00025344142,0.0002382547,0.00070301694,0.00007619375,0.005395195],"category_scores_gemma":[0.0004392536,0.00016827765,0.00008817927,0.00080758875,0.0003356806,0.00049461686,0.0010609002,0.00020062772,0.0003735064],"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":[0.00039159096,0.0022987723,0.42561382,0.00050254446,0.0011698774,0.001438829,0.0002577662,0.000002467211,0.17860691,0.00034609123,0.36895147,0.020419847],"study_design_scores_gemma":[0.0084573515,0.00057493325,0.6179298,0.00078826846,0.00096997153,0.0002634114,0.000991525,0.004826152,0.1638598,0.0012358053,0.19939531,0.00070762425],"about_ca_topic_score_codex":0.00012996832,"about_ca_topic_score_gemma":0.000106707805,"teacher_disagreement_score":0.19231601,"about_ca_system_score_codex":0.000033638928,"about_ca_system_score_gemma":0.00073743303,"threshold_uncertainty_score":0.99551404},"labels":[],"label_agreement":null},{"id":"W3196272632","doi":"10.1038/s41597-021-01002-w","title":"Inter-laboratory mass spectrometry dataset based on passive sampling of drinking water for non-target analysis","year":2021,"lang":"en","type":"article","venue":"Scientific Data","topic":"Isotope Analysis in Ecology","field":"Environmental Science","cited_by":30,"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":"Rijkswaterstaat; RECETOX Přírodovědecké Fakulty Masarykovy Univerzity; Masarykova Univerzita; Centre National de la Recherche Scientifique; Vlaamse Instelling voor Technologisch Onderzoek; Universitat de Girona; Örebro Universitet; Consiglio Nazionale delle Ricerche; Université Claude Bernard Lyon 1; Eidgenössische Anstalt für Wasserversorgung Abwasserreinigung und Gewässerschutz; Universität für Bodenkultur Wien; Bureau de Recherches Géologiques et Minières; National and Kapodistrian University of Athens; Euskal Herriko Unibertsitatea; Sveriges Lantbruksuniversitet; Aarhus Universitets Forskningsfond; University of Queensland; Vrije Universiteit Amsterdam; Institut National de Recherche pour l'Agriculture, l'Alimentation et l'Environnement; Norsk Institutt for Vannforskning; Jihočeská Univerzita v Českých Budějovicích; Universiteit van Amsterdam; Agence Nationale de la Recherche; Aarhus Universitet; Canadian Institute for Advanced Research; Ministry of Infrastructure and Water Management; Colorado State University","keywords":"Sampling (signal processing); Mass spectrometry; Environmental science; Passive sampling; Environmental chemistry; Chemistry; Computer science; Chromatography; Statistics; Mathematics; Calibration","score_opus":0.0235785649677717,"score_gpt":0.28273208864293287,"score_spread":0.25915352367516115,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3196272632","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":[0.19770283,0.00002085676,0.7073212,0.0011027094,0.0021796783,0.00062785734,0.08965935,0.000048466056,0.0013370268],"genre_scores_gemma":[0.780278,0.0000013066278,0.11065614,0.00039020364,0.000047672635,0.000018231083,0.10806962,0.000018875322,0.00051993335],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99744546,0.00009817751,0.00038551752,0.0011956716,0.00044447245,0.0004306676],"domain_scores_gemma":[0.9963842,0.00017641867,0.00014842524,0.0031646742,0.00004504794,0.0000812391],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0016800215,0.0001491347,0.00033521204,0.00032886016,0.0002491713,0.00015407168,0.0015558425,0.000060236074,0.0075679882],"category_scores_gemma":[0.00026571887,0.00012370516,0.00010761724,0.0018893228,0.0003435477,0.00035793384,0.0012570765,0.000119100776,0.0002771738],"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":[0.000059013608,0.0006541058,0.09398114,0.000058464102,0.0009137929,0.000063411375,0.00024856138,0.02977361,0.6123853,0.00004225278,0.2604174,0.0014029611],"study_design_scores_gemma":[0.00072284846,0.00009362384,0.008000261,0.00002840708,0.0011625972,0.0000011393691,0.00036143739,0.28687757,0.5020711,0.0007775441,0.19934806,0.000555449],"about_ca_topic_score_codex":0.000020913643,"about_ca_topic_score_gemma":0.0004517836,"teacher_disagreement_score":0.5966651,"about_ca_system_score_codex":0.0001293868,"about_ca_system_score_gemma":0.0000492188,"threshold_uncertainty_score":0.99333924},"labels":[],"label_agreement":null},{"id":"W3197085852","doi":"10.1038/s41597-021-01026-2","title":"Author Correction: Open-access quantitative MRI data of the spinal cord and reproducibility across participants, sites and manufacturers","year":2021,"lang":"en","type":"erratum","venue":"Scientific Data","topic":"Medical Imaging and Analysis","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Philips (Canada); McGill University; Centre Hospitalier Universitaire de Sherbrooke; International Collaboration On Repair Discoveries; University of British Columbia; Université de Montréal; Université de Sherbrooke; Centre Hospitalier Universitaire Sainte-Justine; Polytechnique Montréal; Montreal Neurological Institute and Hospital; Mila - Quebec Artificial Intelligence Institute","funders":"National Center for Advancing Translational Sciences; National Institute of Biomedical Imaging and Bioengineering","keywords":"Reproducibility; Data science; Medicine; Computer science; Information retrieval; Statistics; Mathematics","score_opus":0.2917936382257923,"score_gpt":0.4651536342517678,"score_spread":0.17335999602597552,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3197085852","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.117916,0.08151405,0.008592025,0.011584384,0.6028649,0.002992482,0.1693859,0.0005706834,0.0045795795],"genre_scores_gemma":[0.22396708,0.0024677538,0.0047639525,0.00031089026,0.0018883186,0.000051933584,0.13227679,0.00021775528,0.63405555],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9959397,0.00014984056,0.00044927126,0.0026337581,0.00047692345,0.00035050765],"domain_scores_gemma":[0.9886753,0.00007850398,0.00018098588,0.010795974,0.00011187768,0.00015733528],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.005419082,0.0002301536,0.0005023219,0.000058396647,0.00039615002,0.00218156,0.0054024486,0.000118605974,0.00011852588],"category_scores_gemma":[0.004002961,0.00016680884,0.000032295444,0.00070565904,0.0011098693,0.0010296678,0.012861225,0.0006306463,0.000004053988],"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":[0.000010095527,0.00002465168,0.0006256356,0.00040147878,0.00012714588,0.0000049308305,0.0001511867,0.000021514712,0.00007751198,0.0000027354538,0.9879626,0.010590497],"study_design_scores_gemma":[0.00015664156,0.000023776545,0.009485951,0.0008629028,0.0004143935,0.000012684116,0.0010973925,0.12382548,0.0005373648,0.00009486954,0.86312234,0.00036622697],"about_ca_topic_score_codex":0.0003460854,"about_ca_topic_score_gemma":0.0012081378,"teacher_disagreement_score":0.62947595,"about_ca_system_score_codex":0.000020294628,"about_ca_system_score_gemma":0.00018512862,"threshold_uncertainty_score":0.9999788},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"editorial","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W3202927809","doi":"10.1038/s41597-021-01006-6","title":"AusTraits, a curated plant trait database for the Australian flora","year":2021,"lang":"en","type":"article","venue":"Scientific Data","topic":"Species Distribution and Climate Change","field":"Environmental Science","cited_by":199,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Université de Montréal","funders":"Australian Research Data Commons; NSW Department of Planning,Industry and Environment; Australian Research Council; Soochow University; Department of Biodiversity, Conservation and Attractions; Centre for Australian National Biodiversity Research; Department of Education and Training; Department of Environment, Land, Water and Planning, State Government of Victoria","keywords":"Taxon; Trait; Scope (computer science); Biology; Database; Ecology; Flora (microbiology); Field (mathematics); Taxonomic rank; Geography; Computer science","score_opus":0.16331794623119344,"score_gpt":0.3183892448547478,"score_spread":0.15507129862355434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3202927809","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09880063,0.0002966201,0.0025454555,0.024244841,0.007641576,0.001560773,0.8506601,0.00025637785,0.013993663],"genre_scores_gemma":[0.33474985,0.000095295596,0.0023703573,0.001573691,0.0003594341,0.00016810432,0.5424934,0.000058916226,0.11813096],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99828696,0.000031564243,0.0001838085,0.0007316733,0.00038137304,0.00038459754],"domain_scores_gemma":[0.9979277,0.00007162326,0.00005412386,0.0017957427,0.000023477583,0.00012733045],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00077037327,0.00011517579,0.000093026785,0.0000146106695,0.0005841045,0.00046650774,0.0013640713,0.000038142567,0.09820227],"category_scores_gemma":[0.00020499363,0.00008319599,0.000040864594,0.00057626585,0.00045048931,0.00043791783,0.0009690929,0.00009540295,0.0014765637],"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":[0.000007748596,0.00006885041,0.00011054226,0.000007999206,0.000009306857,0.000011118908,0.00006598049,0.000005521892,0.013330659,0.00069965224,0.98374724,0.0019353697],"study_design_scores_gemma":[0.00026279813,0.0000070472624,0.0069037,0.000007689567,0.000030001007,0.000020633877,0.0018398549,0.0009898209,0.0035835316,0.00004726565,0.98617846,0.00012922533],"about_ca_topic_score_codex":0.00011679638,"about_ca_topic_score_gemma":0.002244806,"teacher_disagreement_score":0.30816668,"about_ca_system_score_codex":0.00009792143,"about_ca_system_score_gemma":0.00004378825,"threshold_uncertainty_score":0.9993009},"labels":[],"label_agreement":null},{"id":"W3203260001","doi":"10.1038/s41597-021-01031-5","title":"COVID Border Accountability Project, a hand-coded global database of border closures introduced during 2020","year":2021,"lang":"en","type":"article","venue":"Scientific Data","topic":"COVID-19 epidemiological studies","field":"Mathematics","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":"Carleton University","funders":"Nanovic Institute for European Studies; University of Notre Dame","keywords":"Timeline; Accountability; Audit; Categorization; Social media; Pandemic; Political science; Immigration; Coronavirus disease 2019 (COVID-19); Public relations; Database; Data science; Business; Geography; World Wide Web; Computer science; Accounting","score_opus":0.24236091395207404,"score_gpt":0.48592408357320527,"score_spread":0.24356316962113123,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3203260001","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":[0.9233399,0.001912739,0.004022752,0.008814988,0.0023443082,0.001576197,0.05620686,0.00031068755,0.0014715912],"genre_scores_gemma":[0.91843164,0.00021324652,0.059288878,0.0011852621,0.00077404804,0.0001566223,0.014731928,0.00006532444,0.0051530255],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9956334,0.00041533262,0.00084023393,0.001834989,0.00072027923,0.00055576046],"domain_scores_gemma":[0.9929974,0.0011636465,0.00031601678,0.0048146416,0.0005526906,0.00015557827],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0043368954,0.00027273095,0.0006528529,0.000051200233,0.0005414171,0.0002226357,0.0015839793,0.000092900766,0.0011346244],"category_scores_gemma":[0.06531892,0.00021779018,0.00010207897,0.0014632181,0.00087306043,0.00044556495,0.005216312,0.00021516913,0.000036756708],"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":[0.00030212555,0.0016191063,0.037369132,0.0029548346,0.00036668748,0.00008222761,0.0009361064,0.000017709972,0.03316466,0.003934407,0.91743916,0.0018138435],"study_design_scores_gemma":[0.004363519,0.00010176116,0.047362283,0.00046210657,0.0006294604,0.00006838316,0.0025552688,0.002545863,0.02881284,0.05066134,0.86079365,0.0016435389],"about_ca_topic_score_codex":0.00050354586,"about_ca_topic_score_gemma":0.00433474,"teacher_disagreement_score":0.060982022,"about_ca_system_score_codex":0.00018416948,"about_ca_system_score_gemma":0.0008867208,"threshold_uncertainty_score":0.99977845},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W3203937348","doi":"10.1038/s41597-021-01033-3","title":"The “Narratives” fMRI dataset for evaluating models of naturalistic language comprehension","year":2021,"lang":"en","type":"article","venue":"Scientific Data","topic":"Neurobiology of Language and Bilingualism","field":"Neuroscience","cited_by":153,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Children's Hospital; University of British Columbia; McGill University; Montreal Neurological Institute and Hospital","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Institute of Mental Health; Advanced Research Projects Agency; U.S. Department of Health and Human Services; National Institutes of Health; National Institute of Biomedical Imaging and Bioengineering; Intel Corporation; Defense Advanced Research Projects Agency; U.S. Department of Defense","keywords":"Narrative; Computer science; Metadata; Comprehension; Neuroimaging; Variety (cybernetics); Benchmark (surveying); Data collection; Natural language processing; Psychology; Artificial intelligence; Linguistics; World Wide Web; Neuroscience","score_opus":0.24730925129721867,"score_gpt":0.4295171565604403,"score_spread":0.18220790526322164,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3203937348","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":[0.8620178,0.0019098428,0.0012987019,0.0020642478,0.004318538,0.00079127756,0.12714463,0.00006103427,0.00039390274],"genre_scores_gemma":[0.9469437,0.00002041283,0.004825233,0.0009447853,0.00011419262,0.000013424027,0.044415712,0.00002013192,0.0027024061],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99806625,0.00029224317,0.00026422882,0.0008168192,0.00030448512,0.00025597282],"domain_scores_gemma":[0.9964652,0.001121804,0.00014481155,0.0021065918,0.00012050605,0.00004110069],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012675222,0.00010051321,0.00014001092,0.000035893623,0.00067494623,0.00018448626,0.0013749105,0.00003520173,0.00004030271],"category_scores_gemma":[0.0029736394,0.00006570567,0.00003528221,0.0003007924,0.00056128006,0.000302567,0.00096504646,0.00012208633,0.0000129521695],"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":[0.00001999636,0.000033222634,6.1810425e-7,0.00002166403,0.000003546843,0.00004817158,0.0008626437,0.000032948126,0.93605864,0.0006580873,0.059958227,0.0023022136],"study_design_scores_gemma":[0.0008802984,0.00009664438,0.000010715724,0.00008031198,0.00005319115,0.0002501753,0.0045139226,0.06786964,0.82384515,0.009164152,0.0929156,0.0003201784],"about_ca_topic_score_codex":0.000007881589,"about_ca_topic_score_gemma":0.000062317245,"teacher_disagreement_score":0.112213485,"about_ca_system_score_codex":0.000006397534,"about_ca_system_score_gemma":0.00013129246,"threshold_uncertainty_score":0.51912093},"labels":[],"label_agreement":null},{"id":"W3205684707","doi":"10.1038/s41597-021-01050-2","title":"SMAP-HydroBlocks, a 30-m satellite-based soil moisture dataset for the conterminous US","year":2021,"lang":"en","type":"article","venue":"Scientific Data","topic":"Soil Moisture and Remote Sensing","field":"Environmental Science","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":"Global Institute for Water Security; University of Saskatchewan","funders":"National Oceanic and Atmospheric Administration; U.S. Department of Commerce; National Aeronautics and Space Administration","keywords":"Environmental science; Satellite; Water content; Remote sensing; Spatial variability; Spatial ecology; Atmospheric sciences; Climatology; Geography; Geology","score_opus":0.03861151678310767,"score_gpt":0.26925541692380023,"score_spread":0.23064390014069255,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3205684707","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":[0.36542487,0.024603322,0.048323035,0.057050426,0.052722935,0.010522359,0.33495942,0.0011419262,0.10525169],"genre_scores_gemma":[0.87371427,0.00003807905,0.005549768,0.0045987973,0.00041153003,0.000009306802,0.106240205,0.000056816792,0.009381197],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976327,0.00007432681,0.00024761225,0.0011043688,0.0004945716,0.00044641845],"domain_scores_gemma":[0.99598294,0.00025337978,0.000094991265,0.0035191916,0.000028043492,0.00012145878],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010012691,0.00018566835,0.00016948287,0.000025196685,0.000827675,0.0005375905,0.0015358025,0.000076298355,0.0003307972],"category_scores_gemma":[0.00027239442,0.00012492719,0.0000663102,0.00040710726,0.00072201097,0.0002336452,0.0010934066,0.00016578392,0.00056629966],"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":[0.000022805389,0.00015079888,0.0016507991,0.000026942005,0.000034552795,0.00009823782,0.00016966627,0.00053837535,0.0119520305,0.000016794249,0.864535,0.12080405],"study_design_scores_gemma":[0.00041504396,0.000013946155,0.01039213,0.000022907538,0.00007613859,0.00003308364,0.00013045609,0.012957636,0.0062957993,0.00012208245,0.9693308,0.0002099891],"about_ca_topic_score_codex":0.00063406146,"about_ca_topic_score_gemma":0.013567142,"teacher_disagreement_score":0.5082894,"about_ca_system_score_codex":0.000059223166,"about_ca_system_score_gemma":0.00010137449,"threshold_uncertainty_score":0.75707835},"labels":[],"label_agreement":null},{"id":"W3208039415","doi":"10.1038/s41597-021-01069-5","title":"A curated diverse molecular database of blood-brain barrier permeability with chemical descriptors","year":2021,"lang":"en","type":"article","venue":"Scientific Data","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":121,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Blood–brain barrier; Computer science; Categorical variable; Permeability (electromagnetism); Benchmark (surveying); Computational biology; Artificial intelligence; Chemistry; Neuroscience; Central nervous system; Biology; Machine learning; Membrane; Biochemistry","score_opus":0.04931558276298247,"score_gpt":0.3073137946991274,"score_spread":0.2579982119361449,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3208039415","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":[0.56469274,0.00013089427,0.43100315,0.00049168017,0.0006242719,0.00015283645,0.0026401163,0.0000638119,0.00020051663],"genre_scores_gemma":[0.60670227,0.0000010739442,0.38881397,0.00019542429,0.000025607846,0.0000067214814,0.0039067077,0.000013855631,0.00033434265],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99686223,0.00033707486,0.00028774454,0.001394727,0.0008345297,0.0002836951],"domain_scores_gemma":[0.99486095,0.00025172185,0.00013361716,0.004164221,0.00041366753,0.00017581558],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018148088,0.0001490179,0.00019494288,0.00010178348,0.00012775062,0.00038069297,0.002817535,0.00003408933,0.000111811096],"category_scores_gemma":[0.0019074458,0.00013314113,0.000046357123,0.0016461882,0.00049519696,0.0014227533,0.0039566723,0.00014168897,0.000017761811],"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":[0.000033896704,0.00079482194,0.001026307,0.00014143143,0.00015224512,0.0004491269,0.0008462444,0.0015223528,0.94507706,0.020244228,0.020323927,0.009388333],"study_design_scores_gemma":[0.0012079771,0.00004650349,0.0009865947,0.00014298098,0.00012121881,0.00012920522,0.00030746282,0.30922797,0.6735,0.004379803,0.009359026,0.0005912453],"about_ca_topic_score_codex":0.000027827307,"about_ca_topic_score_gemma":0.000016305572,"teacher_disagreement_score":0.30770564,"about_ca_system_score_codex":0.000025001797,"about_ca_system_score_gemma":0.00091826526,"threshold_uncertainty_score":0.5429338},"labels":[],"label_agreement":null},{"id":"W3208632558","doi":"10.1038/s41597-021-01067-7","title":"Geolocation of unpublished archaeological sites in the Peruvian Amazon","year":2021,"lang":"en","type":"article","venue":"Scientific Data","topic":"Amazonian Archaeology and Ethnohistory","field":"Arts and Humanities","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 Toronto; McGill University","funders":"University of Toronto; Japan Society for the Promotion of Science; Ministry of Education, Culture, Sports, Science and Technology; Social Sciences and Humanities Research Council of Canada; Government of Canada; McGill University","keywords":"Geolocation; Amazon rainforest; Geography; Archaeology; World Wide Web; Biology; Ecology; Computer science","score_opus":0.14368336207317597,"score_gpt":0.2884888730588309,"score_spread":0.14480551098565494,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3208632558","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":[0.915093,0.0016801624,0.000088958695,0.014453562,0.0022667255,0.00023412902,0.00087431865,0.00004884021,0.06526031],"genre_scores_gemma":[0.9834059,0.000009248876,0.00017567971,0.00035357746,0.00011542466,0.0000054841366,0.0026528616,0.0000035694252,0.013278241],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988114,0.0002021072,0.0001995003,0.00039061697,0.00021344604,0.00018290739],"domain_scores_gemma":[0.9984487,0.00014130517,0.00006177723,0.0012114279,0.0001133887,0.000023348288],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001548949,0.000068490044,0.00011153728,0.00010471938,0.00029126773,0.000085629465,0.0010745702,0.000036344212,0.00284208],"category_scores_gemma":[0.00039265753,0.000045891098,0.000025997313,0.00014373276,0.0031633123,0.00036285835,0.0005656727,0.00017496549,0.000106642234],"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":[0.000023436092,0.00031787352,0.016959896,0.00006453625,0.000020261788,0.000062710445,0.20905507,0.0000069917637,0.0006074556,0.51903653,0.24884437,0.005000844],"study_design_scores_gemma":[0.00018020063,0.000024513916,0.020590795,0.00001715651,0.000013792197,0.000008872345,0.015770711,0.0004053489,0.000123532,0.012241155,0.9505185,0.000105425024],"about_ca_topic_score_codex":0.00011467832,"about_ca_topic_score_gemma":0.012352734,"teacher_disagreement_score":0.7016741,"about_ca_system_score_codex":0.000011127662,"about_ca_system_score_gemma":0.00011055667,"threshold_uncertainty_score":0.9995495},"labels":[],"label_agreement":null},{"id":"W3210441536","doi":"10.1038/s41597-021-01073-9","title":"Attributes of the food and physical activity built environments from the Southern Cone of Latin America","year":2021,"lang":"en","type":"article","venue":"Scientific Data","topic":"Obesity, Physical Activity, Diet","field":"Medicine","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":"International Development Research Centre","keywords":"Latin Americans; Limiting; Geography; Built environment; Incentive; Physical activity; Healthy food; Environmental health; Walkability; Active living; Environmental quality; Regional science; Environmental planning; Business; Political science; Ecology; Medicine; Economics; Engineering","score_opus":0.060731334286667396,"score_gpt":0.28170590909923926,"score_spread":0.22097457481257188,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3210441536","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":[0.98656964,0.00007171816,0.000041450297,0.0011719797,0.00014282374,0.00016437237,0.011762995,0.00000588997,0.00006915546],"genre_scores_gemma":[0.9987765,0.0000035935307,0.00008690394,0.000036811984,0.000070569644,0.0000018552694,0.00054854207,0.000008200363,0.0004670364],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99866754,0.00012580217,0.00011196836,0.00045633528,0.00049414916,0.00014422458],"domain_scores_gemma":[0.9973984,0.00034488426,0.0001457206,0.0020226438,0.000034251076,0.000054152013],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001956197,0.00009758891,0.0002731117,0.000010204591,0.00011399744,0.000030494713,0.0005091928,0.00002581696,0.000049485807],"category_scores_gemma":[0.0003455763,0.000056237895,0.00006128669,0.00027805363,0.0010760162,0.00010720654,0.0016855305,0.00016220025,0.000025936342],"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":[0.000042239484,0.008876008,0.15232435,0.00006885419,0.0002906227,0.0000028758093,0.0012815038,0.0000029714577,0.8185773,0.0001146201,0.0069896826,0.01142901],"study_design_scores_gemma":[0.00049128244,0.00006661237,0.7864689,0.000057282537,0.0001923252,9.151158e-7,0.00047947426,0.00086342,0.2061392,0.0009099635,0.0042531034,0.00007745594],"about_ca_topic_score_codex":0.00013792425,"about_ca_topic_score_gemma":0.000060710125,"teacher_disagreement_score":0.6341446,"about_ca_system_score_codex":0.00001143644,"about_ca_system_score_gemma":0.000063918415,"threshold_uncertainty_score":0.39646268},"labels":[],"label_agreement":null},{"id":"W3215310298","doi":"10.1038/s41597-022-01638-2","title":"A multi-sensor human gait dataset captured through an optical system and inertial measurement units","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Gait Recognition and Analysis","field":"Engineering","cited_by":23,"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 Interdisciplinary Research in Music Media and Technology","funders":"Fundação de Amparo à Pesquisa do Estado de São Paulo; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior; Centre for Interdisciplinary Research in Music Media and Technology","keywords":"Gait; Inertial frame of reference; Inertial measurement unit; Computer science; Units of measurement; Computer vision; Artificial intelligence; Remote sensing; Geography; Physical medicine and rehabilitation; Physics; Medicine","score_opus":0.17279967380175246,"score_gpt":0.29239765996487965,"score_spread":0.1195979861631272,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3215310298","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":[0.49018514,0.0014655264,0.021189153,0.00041191932,0.007034344,0.0015446949,0.4737644,0.0016556967,0.0027491536],"genre_scores_gemma":[0.92172724,0.0000017856016,0.0016778474,0.000030995852,0.00005517372,0.000017553153,0.07636212,0.00001846373,0.00010880161],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983821,0.000079854995,0.00022220273,0.00052846246,0.0005580849,0.00022930556],"domain_scores_gemma":[0.9986182,0.000007531455,0.000027409824,0.0011504869,0.00007299614,0.0001233809],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00092412654,0.00012418618,0.00015149031,0.00010835133,0.00053189823,0.00028840956,0.000625842,0.000024629317,0.00023361197],"category_scores_gemma":[0.000046326917,0.00012211896,0.000015358126,0.000481631,0.00009130025,0.0004045898,0.00051532185,0.00016023788,0.00004165001],"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":[0.00002117767,0.0004682134,0.00014460641,0.00043287975,0.00038515546,0.00014591959,0.0015644361,0.008270607,0.40650862,0.00060861453,0.5785869,0.0028628898],"study_design_scores_gemma":[0.0015064596,0.000047830996,0.00057630375,0.00005132082,0.00030688875,0.00006977795,0.0059458674,0.45545623,0.0028639499,0.000012037026,0.53251886,0.0006444543],"about_ca_topic_score_codex":0.00009052379,"about_ca_topic_score_gemma":0.0003694373,"teacher_disagreement_score":0.4471856,"about_ca_system_score_codex":0.000072340335,"about_ca_system_score_gemma":0.000027190192,"threshold_uncertainty_score":0.49798664},"labels":[],"label_agreement":null},{"id":"W3215526847","doi":"10.1038/s41597-022-01507-y","title":"The RETA Benchmark for Retinal Vascular Tree Analysis","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":33,"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 Key Research and Development Program of China; Capital Medical University","keywords":"Segmentation; Annotation; Computer science; Benchmark (surveying); Tree (set theory); Artificial intelligence; Workflow; Software; Visualization; Task (project management); Pattern recognition (psychology); Database","score_opus":0.045044382642986484,"score_gpt":0.32508216363956427,"score_spread":0.2800377809965778,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3215526847","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":[0.59970796,0.031749696,0.07662788,0.15607646,0.014290431,0.006829929,0.041864812,0.0010914891,0.07176133],"genre_scores_gemma":[0.7932052,0.00007795159,0.006867442,0.00054270803,0.00038303403,0.00014474237,0.049840562,0.00004152839,0.14889684],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978059,0.000108192275,0.00026002235,0.0007542876,0.0007730893,0.00029852768],"domain_scores_gemma":[0.9962657,0.00013956311,0.00010396389,0.0032671723,0.0001250462,0.00009854316],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0048411,0.00009522333,0.00023865723,0.0002506448,0.0018346353,0.00029443012,0.001208178,0.000013269325,0.00039731493],"category_scores_gemma":[0.00051581475,0.000064567066,0.00032120684,0.002355669,0.0002581814,0.00007309042,0.0007572186,0.00016910803,0.000021368274],"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":[0.000181829,0.00023377225,0.0153369,0.000049625258,0.003243855,0.000033869605,0.00028347477,0.00015972108,0.002163326,0.000498673,0.8943957,0.083419256],"study_design_scores_gemma":[0.00030095337,0.00004663018,0.0037522486,0.0000056023036,0.0038919635,0.000009306722,0.00062610285,0.070104174,0.00007053179,0.0002153492,0.92088145,0.0000957084],"about_ca_topic_score_codex":0.00005113856,"about_ca_topic_score_gemma":0.000071506845,"teacher_disagreement_score":0.19349721,"about_ca_system_score_codex":0.000042783016,"about_ca_system_score_gemma":0.00011484956,"threshold_uncertainty_score":0.99946487},"labels":[],"label_agreement":null},{"id":"W3216017632","doi":"10.1038/s41597-021-01088-2","title":"BSE49, a diverse, high-quality benchmark dataset of separation energies of chemical bonds","year":2021,"lang":"en","type":"article","venue":"Scientific Data","topic":"Free Radicals and Antioxidants","field":"Chemistry","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":"University of British Columbia, Okanagan Campus; University of British Columbia","funders":"Agencia Estatal de Investigación; British Columbia Knowledge Development Fund; Natural Sciences and Engineering Research Council of Canada; University of British Columbia; Ministerio de Ciencia e Innovación; Western Canada Research Grid; Compute Canada","keywords":"Molecule; Covalent bond; Homolysis; Chemistry; Bond energy; Sextuple bond; Bond cleavage; Computational chemistry; Bond length; Radical; Bond order; Organic chemistry","score_opus":0.062073017165149375,"score_gpt":0.3402202235745776,"score_spread":0.27814720640942825,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3216017632","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":[0.84820116,0.0002582982,0.000038906997,0.00006290934,0.00026322604,0.000019197902,0.1497973,0.00001453545,0.0013444697],"genre_scores_gemma":[0.83868605,0.000016514463,0.0014250244,0.000012142293,0.00005453043,0.0000011211054,0.15864024,0.000005515176,0.00115889],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9982879,0.000028624903,0.00044039247,0.00057870476,0.0004914934,0.00017287109],"domain_scores_gemma":[0.99735314,0.000070834125,0.00020415056,0.0021870274,0.000116275005,0.00006855415],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005978604,0.000094803814,0.00022882831,0.00003086002,0.00006361272,0.00006932402,0.00090112,0.00007205327,0.002548964],"category_scores_gemma":[0.00038587037,0.000090035755,0.000035615347,0.0003075505,0.00046328056,0.0003091884,0.0010644215,0.00008105298,0.000015353304],"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":[0.000008816887,0.00014080206,0.0002817744,0.00015212357,0.00002026675,0.000005116418,0.000022129956,0.000003458901,0.7494241,0.000849281,0.24809775,0.0009943836],"study_design_scores_gemma":[0.0002737456,0.0000031980594,0.00032304376,0.000060354832,0.000031755266,0.000002913269,0.000117471005,0.000345442,0.92852217,0.00027322897,0.06993828,0.000108383516],"about_ca_topic_score_codex":0.00011357796,"about_ca_topic_score_gemma":0.000040894396,"teacher_disagreement_score":0.17909808,"about_ca_system_score_codex":0.00001195942,"about_ca_system_score_gemma":0.000148927,"threshold_uncertainty_score":0.99836284},"labels":[],"label_agreement":null},{"id":"W3216508885","doi":"10.1038/s41597-021-01083-7","title":"Crash and disengagement data of autonomous vehicles on public roads in California","year":2021,"lang":"en","type":"article","venue":"Scientific Data","topic":"Traffic and Road Safety","field":"Engineering","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Crash; Software deployment; Disengagement theory; Public domain; Computer science; Publication; Transport engineering; Suite; Computer security; Data science; Business; Engineering; Geography; Advertising; Political science; Law","score_opus":0.08127586703752618,"score_gpt":0.26722206499781825,"score_spread":0.18594619796029208,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3216508885","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":[0.9503809,0.0021061758,0.0016036553,0.0012969215,0.0029090752,0.0003122876,0.036306545,0.0003021782,0.004782252],"genre_scores_gemma":[0.99163103,0.00005920439,0.0007365529,0.000013711155,0.000025711051,0.0000014829112,0.0071987063,0.000011593818,0.00032198135],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988376,0.000036692458,0.00021764426,0.0005089653,0.00019723496,0.00020184719],"domain_scores_gemma":[0.9975652,0.000041909538,0.000020542135,0.0022831704,0.000019458525,0.00006973201],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00084985455,0.000087011955,0.00012703257,0.000093431525,0.000079810634,0.00013121644,0.00088997337,0.000033264103,0.00008147901],"category_scores_gemma":[0.0001129694,0.00008061662,0.000009163646,0.0003408638,0.00010773068,0.00028215916,0.0011553736,0.0001248576,0.000046251684],"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":[0.000013292083,0.0006271231,0.026624396,0.0005411626,0.00014340809,0.0001248133,0.0007513624,0.008658572,0.006079054,0.0023372052,0.503023,0.45107657],"study_design_scores_gemma":[0.0005854899,0.000010147188,0.103699915,0.00008886382,0.000023097478,0.000005475095,0.00037997315,0.28257456,0.0008875268,0.000088666966,0.611386,0.0002702563],"about_ca_topic_score_codex":0.000008370001,"about_ca_topic_score_gemma":0.0003489908,"teacher_disagreement_score":0.4508063,"about_ca_system_score_codex":0.000022202685,"about_ca_system_score_gemma":0.00007169929,"threshold_uncertainty_score":0.32874504},"labels":[],"label_agreement":null},{"id":"W35241693","doi":"10.1038/s41597-022-01154-3","title":"Role Representations at the Core of School Principals' Practices in the Midst of School Reform in Quebec.","year":2002,"lang":"en","type":"article","venue":"Scientific Data","topic":"Education, sociology, and vocational training","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Core (optical fiber); Political science; Pedagogy; School choice; Mathematics education; Sociology; Public administration; Psychology; Law","score_opus":0.5458783606244283,"score_gpt":0.5288809495672291,"score_spread":0.016997411057199208,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W35241693","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":[0.88412815,0.0007092188,0.0000024787587,0.021563359,0.00086635427,0.00055511435,0.00029775396,0.000011820632,0.09186574],"genre_scores_gemma":[0.9829228,0.00012560547,0.00027348936,0.00009178882,0.00019031177,0.00003207903,0.0003469509,0.000003558887,0.016013417],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.99807286,0.0005782165,0.0003475826,0.00032810093,0.0004801235,0.00019310358],"domain_scores_gemma":[0.99713767,0.0011338077,0.000421248,0.0011244203,0.0001387234,0.0000441155],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.010124448,0.000054626846,0.000094207535,0.00010539969,0.00054818543,0.000104414794,0.0015606522,0.000051293522,0.00064607675],"category_scores_gemma":[0.010269987,0.000035863908,0.00002360437,0.0009782213,0.0017063968,0.0007191156,0.00018409344,0.00016446738,0.000059257505],"study_design_candidate":"qualitative","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":[0.000012597443,0.0007805886,0.4389634,0.00004852607,0.00003621868,9.90889e-7,0.32713786,0.00005405524,0.0011851026,0.11051368,0.11823719,0.0030297767],"study_design_scores_gemma":[0.00017195391,0.000008081451,0.31608418,0.000043152286,0.000013543109,7.1200157e-7,0.56966627,0.00021018517,0.00003515892,0.0020929226,0.111599006,0.00007485864],"about_ca_topic_score_codex":0.0531938,"about_ca_topic_score_gemma":0.31577566,"teacher_disagreement_score":0.26258188,"about_ca_system_score_codex":0.00014594686,"about_ca_system_score_gemma":0.00038107263,"threshold_uncertainty_score":0.9980669},"labels":[],"label_agreement":null},{"id":"W4214595825","doi":"10.1038/s41597-022-01162-3","title":"Worldwide diversity of endophytic fungi and insects associated with dormant tree twigs","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Plant Pathogens and Fungal Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"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 Research, Development and Innovation Office; Bundesamt für Umwelt; Australian Centre for International Agricultural Research; Agentúra na Podporu Výskumu a Vývoja; Ministry of Agriculture of the People's Republic of China; Ministarstvo Prosvete, Nauke i Tehnološkog Razvoja; Department of Forestry, Fisheries and the Environment; Eidgenössische Technische Hochschule Zürich; Russian Foundation for Basic Research; Eesti Teadusfondi; Siberian Branch, Russian Academy of Sciences; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; McGill University; Génome Québec; Javna Agencija za Raziskovalno Dejavnost RS; Hungarian Scientific Research Fund; Uniwersytet Rolniczy im. Hugona Kołłątaja w Krakowie; Department of Agriculture, Environment and Rural Affairs, UK Government; Instituto Nacional de investigação Agrária e Veterinária; Agriculture and Agri-Food Canada; National Science Foundation","keywords":"Biology; Gymnosperm; Plant use of endophytic fungi in defense; Taxon; Ecology; Herbivore; Marine fungi; Biodiversity; Botany","score_opus":0.024484448356290343,"score_gpt":0.215701642575229,"score_spread":0.19121719421893865,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4214595825","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":[0.96753156,0.0007449063,0.000016722517,0.000012592461,0.000156841,0.00008782848,0.031022923,0.0000061698656,0.00042043437],"genre_scores_gemma":[0.987943,0.000016610886,0.00004477456,0.00004374486,0.000011643586,0.0000026909918,0.011022582,0.000004375675,0.0009105992],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99913526,0.00004808489,0.00007896406,0.0003834567,0.00021379603,0.00014046187],"domain_scores_gemma":[0.9992451,0.000013160319,0.00006695712,0.00058356504,0.00003152123,0.000059682752],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003133081,0.000067772955,0.00008287132,0.000045893565,0.00036091142,0.000027110958,0.0004560855,0.000015562804,0.000036709695],"category_scores_gemma":[0.000054234486,0.00005985555,0.00001798571,0.00017488161,0.00012703601,0.000007889483,0.0023755569,0.000044090957,0.0000012609663],"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":[0.00021067754,0.00025630233,0.071104534,0.0000264199,0.00012919366,0.000049387385,0.000093524424,0.000032692646,0.8895741,0.000026222673,0.03634793,0.002148989],"study_design_scores_gemma":[0.002963736,0.00097633485,0.8730385,0.00006876981,0.00046228204,0.000076444754,0.0006521566,0.0015252875,0.03467956,0.00011281158,0.084635526,0.0008086152],"about_ca_topic_score_codex":0.0000175213,"about_ca_topic_score_gemma":0.00012408447,"teacher_disagreement_score":0.8548946,"about_ca_system_score_codex":0.0000074840823,"about_ca_system_score_gemma":0.00006778392,"threshold_uncertainty_score":0.29609615},"labels":[],"label_agreement":null},{"id":"W4214842975","doi":"10.1038/s41597-022-01152-5","title":"Data on the diets of Salish Sea harbour seals from DNA metabarcoding","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Marine animal studies overview","field":"Environmental Science","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":"Université du Québec à Montréal; University of British Columbia; Vancouver Island University; Fisheries and Oceans Canada","funders":"Pacific Salmon Foundation; Washington State University","keywords":"Phoca; Harbour; Predation; Fishery; Harbor seal; Marine ecosystem; Trophic level; Biology; Apex predator; Ecosystem; Ecology; DNA barcoding; Environmental DNA; Marine conservation; Biodiversity; Geography","score_opus":0.15018950995247163,"score_gpt":0.2973172623125636,"score_spread":0.14712775236009198,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4214842975","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":[0.7658807,0.00088397786,0.00004670133,0.0063191643,0.0027943996,0.000966297,0.17185138,0.00009459883,0.05116277],"genre_scores_gemma":[0.98828125,0.00004193596,0.0005313856,0.0008264896,0.000065312095,0.000020087762,0.007919064,0.000019861918,0.0022945867],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99694216,0.00022240622,0.00026832955,0.0011153226,0.0011472685,0.0003045083],"domain_scores_gemma":[0.9941739,0.00023804697,0.00016157255,0.0053533562,0.000007440117,0.00006569033],"candidate_categories":["open_science","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.0034967673,0.00012911395,0.00018645932,0.00002484764,0.0009412906,0.00015147358,0.007263845,0.00001249291,0.021863066],"category_scores_gemma":[0.00046295315,0.00009440914,0.000033745764,0.00063408836,0.00039650706,0.00049442874,0.038230658,0.00018792797,0.00045532547],"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":[0.000011885232,0.00011524488,0.0113697015,0.000006968529,0.000042720432,0.00000606879,0.00014433819,0.000029861509,0.0021926388,0.00024604853,0.9777057,0.008128784],"study_design_scores_gemma":[0.00010198268,0.000021927071,0.04947269,0.000008428003,0.000041908123,7.414372e-7,0.00032741856,0.002905651,0.0003683482,0.0003593098,0.94625866,0.00013295558],"about_ca_topic_score_codex":0.0037643693,"about_ca_topic_score_gemma":0.0025822755,"teacher_disagreement_score":0.22240058,"about_ca_system_score_codex":0.00006986781,"about_ca_system_score_gemma":0.000021926991,"threshold_uncertainty_score":0.9981073},"labels":[],"label_agreement":null},{"id":"W4220673714","doi":"10.1038/s41597-022-01210-y","title":"Open access dataset of task-free hemodynamic activity in 4-month-old infants during sleep using fNIRS","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Non-Invasive Vital Sign Monitoring","field":"Engineering","cited_by":11,"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":"Ministerio de Economía y Competitividad; Eusko Jaurlaritza; Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Task (project management); Hemodynamics; Sleep (system call); Computer science; Psychology; Medicine; Internal medicine","score_opus":0.06863746598377127,"score_gpt":0.3324490765443133,"score_spread":0.26381161056054203,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220673714","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":[0.9408997,0.00008326161,0.0005007827,0.000010958422,0.0021799277,0.00045519706,0.05559176,0.00006080806,0.00021759728],"genre_scores_gemma":[0.9923381,0.0000034528155,0.00111227,0.000004142104,0.000043176104,0.000027018496,0.006376015,0.000044201002,0.00005157595],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975618,0.000089028246,0.0003966712,0.00086587446,0.0005938264,0.0004927655],"domain_scores_gemma":[0.9954541,0.000070139045,0.00013116196,0.004218853,0.00002586031,0.00009991355],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0014950704,0.00020295753,0.0003039843,0.00046152074,0.0003531115,0.00076121755,0.010603683,0.000037198748,0.00014507852],"category_scores_gemma":[0.00020767773,0.00024464383,0.000026490945,0.0015641972,0.00011625932,0.004341004,0.028590143,0.0003494967,0.000008887375],"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":[0.00004864126,0.0001312509,0.01830969,0.0002191993,0.00004768334,0.000078666104,0.00018720877,0.07013242,0.90076137,0.000011042692,0.00803445,0.0020383673],"study_design_scores_gemma":[0.005267526,0.00006308588,0.074697874,0.0004862141,0.00012988536,0.000074322576,0.0009933288,0.4879038,0.4146816,0.0011282739,0.012228218,0.0023458668],"about_ca_topic_score_codex":0.00174544,"about_ca_topic_score_gemma":0.0010463386,"teacher_disagreement_score":0.48607978,"about_ca_system_score_codex":0.00036329732,"about_ca_system_score_gemma":0.00008093869,"threshold_uncertainty_score":0.9976286},"labels":[],"label_agreement":null},{"id":"W4220828579","doi":"10.1038/s41597-022-01197-6","title":"An expert-curated global database of online newspaper articles on spiders and spider bites","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Animal and Plant Science Education","field":"Psychology","cited_by":14,"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 Scarborough Hospital; McGill University; University of Toronto; Espace pour la vie","funders":"Science and Engineering Research Board; Helsingin Yliopisto","keywords":"Spider; Newspaper; Metadata; Social media; Data science; Database; World Wide Web; Computer science; Ecology; Biology; Sociology; Media studies","score_opus":0.12992224496705482,"score_gpt":0.39505248393556575,"score_spread":0.26513023896851096,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220828579","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":[0.97993046,0.00036005536,0.000042691718,0.0013122235,0.0018345941,0.0001182278,0.015976744,0.000027717053,0.00039729464],"genre_scores_gemma":[0.98788553,0.000004123863,0.0007827856,0.0004194495,0.000072954805,0.0000059614886,0.010050007,0.0000046811424,0.00077451795],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99846244,0.000137291,0.00019321621,0.0006835535,0.00030747693,0.00021600696],"domain_scores_gemma":[0.9984997,0.00006168816,0.00008708675,0.0012081898,0.000034803637,0.000108528846],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00090863986,0.00008337766,0.000095950294,0.00008572135,0.00032980263,0.00008324562,0.0007912264,0.000017584836,0.0028505719],"category_scores_gemma":[0.00010601648,0.00007116889,0.00001149828,0.00064998923,0.00030394376,0.00042121465,0.00033179377,0.00008015394,0.00006513901],"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":[0.0002787862,0.0029094103,0.037318483,0.000014222221,0.00003040927,0.000023881168,0.0042618834,0.000047571364,0.06831505,0.00957372,0.82557297,0.051653594],"study_design_scores_gemma":[0.0016206966,0.0015535293,0.47115338,0.00006396613,0.000073976385,0.00016586386,0.08544554,0.014570058,0.0015749265,0.0021903897,0.420667,0.0009206907],"about_ca_topic_score_codex":0.0008471326,"about_ca_topic_score_gemma":0.00038969418,"teacher_disagreement_score":0.4338349,"about_ca_system_score_codex":0.000016391046,"about_ca_system_score_gemma":0.0000783348,"threshold_uncertainty_score":0.99806094},"labels":[],"label_agreement":null},{"id":"W4220979273","doi":"10.1038/s41597-022-01231-7","title":"Neurocognitive aging data release with behavioral, structural and multi-echo functional MRI measures","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":58,"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; McGill University; Douglas Mental Health University Institute; McGill Genome Centre; University of Toronto; Toronto Metropolitan University; Montreal Neurological Institute and Hospital","funders":"National Center for Research Resources; Canadian Institutes of Health Research; U.S. Department of Health and Human Services; Government of Canada; National Institutes of Health; Natural Sciences and Engineering Research Council of Canada","keywords":"Socioemotional selectivity theory; Neurocognitive; Neuroimaging; Context (archaeology); Psychology; Cognition; Cognitive psychology; Developmental psychology; Neuroscience; Biology","score_opus":0.2409381386783846,"score_gpt":0.3359719223071308,"score_spread":0.0950337836287462,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220979273","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":[0.8801162,0.0005277507,0.004632504,0.008006205,0.008409554,0.0016696792,0.09561476,0.00054349896,0.00047984908],"genre_scores_gemma":[0.9931795,0.0000056970894,0.0009636418,0.0010248744,0.00008928463,0.000039424744,0.0032031047,0.000027619299,0.0014668377],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9957649,0.0002723383,0.00017541394,0.0023140602,0.0011289375,0.00034435093],"domain_scores_gemma":[0.99646246,0.00090976,0.000112948226,0.00230706,0.00009649467,0.00011127577],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.00096074096,0.00019403885,0.00015341824,0.00018452304,0.0029182087,0.00046569004,0.0016255601,0.00001599183,0.00021533712],"category_scores_gemma":[0.0029148145,0.00017259725,0.000016042211,0.00073966157,0.0008296496,0.0015042379,0.007125711,0.00037445905,0.000023442517],"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":[0.0010120696,0.0011591183,0.02298052,0.00008907046,0.00012252745,0.0006851791,0.0021261033,0.0016112047,0.1705698,0.0007930705,0.7382742,0.060577117],"study_design_scores_gemma":[0.0076512676,0.0009793849,0.08935714,0.000095487914,0.0005642331,0.0022248577,0.009611622,0.19198632,0.017532488,0.0010487944,0.67609596,0.00285246],"about_ca_topic_score_codex":0.0000866992,"about_ca_topic_score_gemma":0.00034881194,"teacher_disagreement_score":0.19037512,"about_ca_system_score_codex":0.00004748081,"about_ca_system_score_gemma":0.00018086331,"threshold_uncertainty_score":0.9983799},"labels":[],"label_agreement":null},{"id":"W4221074757","doi":"10.1038/s41597-022-01249-x","title":"‘Citizens’ Attitudes Under Covid19’, a cross-country panel survey of public opinion in 11 advanced democracies","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"COVID-19 epidemiological studies","field":"Mathematics","cited_by":37,"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":"Région Occitanie Pyrénées-Méditerranée; European University Institute; Centre National de la Recherche Scientifique; Agence Française de Développement; UniCredit and Universities Foundation; Agence Nationale de la Recherche; Harvard Business School; Conseil Régional Aquitaine; Temple University; McGill University; Università Bocconi; World Bank Group","keywords":"Public opinion; Coronavirus disease 2019 (COVID-19); Pandemic; Panel survey; Political science; Survey research; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); 2019-20 coronavirus outbreak; Corporate governance; Public health; Survey data collection; Opinion survey; Cross country; Public relations; Economic growth; Demographic economics; Sociology; Opinion leadership; Socioeconomics; Politics; Economics; Medicine; Law; Virology","score_opus":0.6626786409163391,"score_gpt":0.5076800047267307,"score_spread":0.1549986361896084,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4221074757","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":[0.96447474,0.0015394909,0.002758536,0.002233232,0.003819163,0.0008758266,0.023813982,0.00020466287,0.0002803692],"genre_scores_gemma":[0.9930915,0.000051472438,0.0018675113,0.00028476072,0.000027304555,0.000059573944,0.003750948,0.000021362172,0.00084556977],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9959335,0.0008152224,0.000808228,0.001086752,0.00079110515,0.0005652409],"domain_scores_gemma":[0.9924069,0.004715351,0.00037239946,0.0022024156,0.00021672131,0.00008619647],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.014388258,0.00020081697,0.0005343861,0.00020675205,0.00070835644,0.00018959836,0.0021856248,0.00005782465,0.00045094028],"category_scores_gemma":[0.025587806,0.00017504138,0.000051157574,0.0015878484,0.00090516853,0.0004510729,0.0053138994,0.00026589457,0.000017599532],"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":[0.000057748195,0.0006747525,0.81845653,0.00041743545,0.000060751452,0.0000052979226,0.00023882544,0.00070277904,0.0004984302,0.01681408,0.16105947,0.001013921],"study_design_scores_gemma":[0.0007172756,0.000046996163,0.9010865,0.0000416573,0.0000107122,0.0000038607327,0.00042741807,0.0010927409,0.000026973086,0.04136528,0.054864276,0.0003162806],"about_ca_topic_score_codex":0.00097048184,"about_ca_topic_score_gemma":0.004775821,"teacher_disagreement_score":0.1061952,"about_ca_system_score_codex":0.00021188508,"about_ca_system_score_gemma":0.00024351879,"threshold_uncertainty_score":0.98262006},"labels":[],"label_agreement":null},{"id":"W4221157599","doi":"10.1038/s41597-022-01836-y","title":"Multi-day dataset of forearm and wrist electromyogram for hand gesture recognition and biometrics","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Muscle activation and electromyography studies","field":"Engineering","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Biometrics; Computer science; Wrist; Electromyography; Usability; Artificial intelligence; Gesture recognition; Gesture; Pattern recognition (psychology); Wearable computer; Forearm; Speech recognition; Physical medicine and rehabilitation; Human–computer interaction; Medicine","score_opus":0.07645241778837612,"score_gpt":0.27372020277188547,"score_spread":0.19726778498350933,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4221157599","genre_codex":"dataset","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":[0.42224938,0.011549197,0.046100948,0.0003497764,0.0020209746,0.0019157631,0.5154147,0.00026896494,0.00013027094],"genre_scores_gemma":[0.849831,0.0002931503,0.011712491,0.000040494662,0.000037646594,0.00010311678,0.13786422,0.000027740045,0.00009016241],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992194,0.000016813983,0.00014218832,0.00030876536,0.00014205191,0.00017074613],"domain_scores_gemma":[0.9994031,0.00007792207,0.000040233175,0.00040209416,0.00003731005,0.00003933399],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006761946,0.00007951931,0.0001079978,0.00037739135,0.00039646312,0.0001199089,0.00022119787,0.000019011057,0.000017320463],"category_scores_gemma":[0.00010188011,0.00008011944,0.000012950332,0.0009594801,0.00014028818,0.00019316768,0.00024893534,0.00007991299,2.300927e-7],"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":[0.0000179348,0.00011611726,0.00073525385,0.00024039256,0.0001393096,7.880303e-7,0.0003755926,0.000013145885,0.06040657,0.000021783155,0.5310776,0.4068555],"study_design_scores_gemma":[0.0012094986,0.00018726836,0.014386157,0.000014755235,0.00009191808,0.000010691324,0.0004669661,0.020729473,0.0068474025,0.00044178424,0.95528555,0.00032854348],"about_ca_topic_score_codex":0.000014699435,"about_ca_topic_score_gemma":0.000039040275,"teacher_disagreement_score":0.4275816,"about_ca_system_score_codex":0.000011105237,"about_ca_system_score_gemma":0.000009541279,"threshold_uncertainty_score":0.32671762},"labels":[],"label_agreement":null},{"id":"W4225545880","doi":"10.1038/s41597-022-01216-6","title":"A comprehensive LFQ benchmark dataset on modern day acquisition strategies in proteomics","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":65,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Spinal Cord Injury BC","funders":"Vlaamse regering; Fonds Wetenschappelijk Onderzoek; Agence Nationale de la Recherche","keywords":"Computer science; Data acquisition; Benchmark (surveying); Data mining; Proteomics; Data science; Biology","score_opus":0.045270968687654976,"score_gpt":0.32205059355483034,"score_spread":0.2767796248671754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225545880","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34738302,0.00024656128,0.035245504,0.0009575662,0.00042572716,0.0017713011,0.604244,0.00037929104,0.009347017],"genre_scores_gemma":[0.5382797,0.000015026606,0.032111894,0.00020694235,0.00006847872,0.00082514464,0.4275656,0.00003366972,0.00089355046],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99833727,0.000031831354,0.00023082929,0.0008481873,0.00030965736,0.00024224831],"domain_scores_gemma":[0.99725974,0.000042200645,0.00011197353,0.0025095255,0.00002875502,0.000047835052],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00039646952,0.00012779923,0.00011938873,0.0000878115,0.0005055347,0.00022076847,0.0015377965,0.00003603692,0.0009641877],"category_scores_gemma":[0.000015272602,0.00014078611,0.00001799938,0.0002963186,0.00013752125,0.00031597354,0.0016686764,0.00032900774,0.000026680238],"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":[0.000090782254,0.00055864005,0.00007291542,0.000103218284,0.000014703649,0.000025433816,0.000382989,0.007398316,0.72443473,0.010469275,0.24982274,0.006626266],"study_design_scores_gemma":[0.00061768264,0.00004222092,0.000058263144,0.000052641928,0.000015133676,0.000016247728,0.001580181,0.04869705,0.058660757,0.08167274,0.80804133,0.0005457398],"about_ca_topic_score_codex":0.00003574375,"about_ca_topic_score_gemma":0.000022259066,"teacher_disagreement_score":0.665774,"about_ca_system_score_codex":0.00010977589,"about_ca_system_score_gemma":0.00010773355,"threshold_uncertainty_score":0.99994904},"labels":[],"label_agreement":null},{"id":"W4226138129","doi":"10.1038/s41597-022-01141-8","title":"A construction classification system database for understanding resource use in building construction","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Sustainable Building Design and Assessment","field":"Engineering","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":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto","keywords":"Interoperability; Computer science; Ontology; Field (mathematics); Resource (disambiguation); Database; Building material; Materials management; Data science; Construction engineering; Architectural engineering; Civil engineering; World Wide Web; Engineering; Operations management","score_opus":0.12537023880506995,"score_gpt":0.2868134783604212,"score_spread":0.16144323955535125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226138129","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":[0.07564146,0.00009984554,0.91345733,0.00008346514,0.004436139,0.0010333664,0.0042385943,0.0005334261,0.00047634827],"genre_scores_gemma":[0.96352637,0.0000018662697,0.03221633,0.000005945222,0.00005641974,0.00011080538,0.0039563915,0.000027921042,0.0000979496],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99847275,0.00008179663,0.00028633114,0.0005552263,0.00030656325,0.00029735538],"domain_scores_gemma":[0.9987246,0.00013536654,0.000072505834,0.0009866882,0.00002827404,0.00005257643],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017462595,0.00011185425,0.00012305588,0.0004407844,0.0006156289,0.00041658815,0.0004901944,0.000028746468,0.00001923427],"category_scores_gemma":[0.000091059206,0.00013559709,0.000021926344,0.00078947766,0.00010815625,0.00074864604,0.00029140123,0.00016619718,0.0000015595207],"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":[0.00012368124,0.00009357179,0.0025863908,0.0011409203,0.000084144245,0.00002840493,0.0004934785,0.07173273,0.08322435,0.7264646,0.100350656,0.013677048],"study_design_scores_gemma":[0.00069283135,0.000015723006,0.00008449674,0.00009554406,0.000031657382,0.00007036898,0.043568745,0.8678193,0.0005693782,0.0012448904,0.085541345,0.00026571602],"about_ca_topic_score_codex":0.000018906056,"about_ca_topic_score_gemma":0.000010184889,"teacher_disagreement_score":0.8878849,"about_ca_system_score_codex":0.0013666075,"about_ca_system_score_gemma":0.000095640105,"threshold_uncertainty_score":0.5529489},"labels":[],"label_agreement":null},{"id":"W4235512955","doi":"10.1038/s41597-021-01044-0","title":"Author Correction: Open-access quantitative MRI data of the spinal cord and reproducibility across participants, sites and manufacturers","year":2021,"lang":"en","type":"erratum","venue":"Scientific Data","topic":"Medical Imaging and Analysis","field":"Engineering","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Philips (Canada); McGill University; Centre Hospitalier Universitaire de Sherbrooke; International Collaboration On Repair Discoveries; University of British Columbia; Université de Montréal; Université de Sherbrooke; Centre Hospitalier Universitaire Sainte-Justine; Polytechnique Montréal; Montreal Neurological Institute and Hospital; Mila - Quebec Artificial Intelligence Institute","funders":"National Center for Advancing Translational Sciences; National Institute of Biomedical Imaging and Bioengineering","keywords":"Reproducibility; Computer science; Data science; Medicine; Information retrieval; Statistics; Mathematics","score_opus":0.2917936382257923,"score_gpt":0.4651536342517678,"score_spread":0.17335999602597552,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4235512955","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.117916,0.08151405,0.008592025,0.011584384,0.6028649,0.002992482,0.1693859,0.0005706834,0.0045795795],"genre_scores_gemma":[0.22396708,0.0024677538,0.0047639525,0.00031089026,0.0018883186,0.000051933584,0.13227679,0.00021775528,0.63405555],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9959397,0.00014984056,0.00044927126,0.0026337581,0.00047692345,0.00035050765],"domain_scores_gemma":[0.9886753,0.00007850398,0.00018098588,0.010795974,0.00011187768,0.00015733528],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.005419082,0.0002301536,0.0005023219,0.000058396647,0.00039615002,0.00218156,0.0054024486,0.000118605974,0.00011852588],"category_scores_gemma":[0.004002961,0.00016680884,0.000032295444,0.00070565904,0.0011098693,0.0010296678,0.012861225,0.0006306463,0.000004053988],"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":[0.000010095527,0.00002465168,0.0006256356,0.00040147878,0.00012714588,0.0000049308305,0.0001511867,0.000021514712,0.00007751198,0.0000027354538,0.9879626,0.010590497],"study_design_scores_gemma":[0.00015664156,0.000023776545,0.009485951,0.0008629028,0.0004143935,0.000012684116,0.0010973925,0.12382548,0.0005373648,0.00009486954,0.86312234,0.00036622697],"about_ca_topic_score_codex":0.0003460854,"about_ca_topic_score_gemma":0.0012081378,"teacher_disagreement_score":0.62947595,"about_ca_system_score_codex":0.000020294628,"about_ca_system_score_gemma":0.00018512862,"threshold_uncertainty_score":0.9999788},"labels":[],"label_agreement":null},{"id":"W4250125441","doi":"10.1038/s41597-020-0515-6","title":"Publisher Correction: A global database of Holocene paleotemperature records","year":2020,"lang":"en","type":"erratum","venue":"Scientific Data","topic":"Geology and Paleoclimatology Research","field":"Earth and Planetary Sciences","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":"Okanagan University College; University of British Columbia, Okanagan Campus; Bishop's University; Okanagan College; Geological Survey of Canada; University of Ottawa; University of New Brunswick; Center for Northern Studies; Concordia University; Université du Québec à Montréal; University of British Columbia; Fisheries and Oceans Canada; Mount Royal University; Université Laval; Natural Resources Canada","funders":"","keywords":"Holocene; Database; Geology; Data science; Oceanography; Computer science","score_opus":0.04864310150019533,"score_gpt":0.282948224771884,"score_spread":0.2343051232716887,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4250125441","genre_codex":"editorial","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010432568,0.012467789,0.00002551728,0.003196693,0.58161736,0.00054859754,0.054315757,0.00011734251,0.3466677],"genre_scores_gemma":[0.011069285,0.0005014917,0.00061258976,0.00028724625,0.0013245574,0.0000021582869,0.63714,0.000008923246,0.34905377],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99573815,0.00038560768,0.0004949851,0.0018306718,0.00086859456,0.00068200484],"domain_scores_gemma":[0.99575114,0.00014874045,0.00028069672,0.0032130212,0.00025965393,0.00034675875],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00179662,0.00033781774,0.00059667224,0.00019461832,0.0004610623,0.0004783559,0.0042837085,0.00082229316,0.012001239],"category_scores_gemma":[0.0013331295,0.0002870743,0.00009252821,0.0018004328,0.0013547379,0.0008775104,0.0006515458,0.0017816728,0.0013047179],"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":[0.00004155437,0.000017864902,0.35206786,0.00012469028,0.00004211314,0.00008157727,0.000017524419,0.0000026877788,1.0130789e-7,0.0000044479234,0.6466642,0.000935358],"study_design_scores_gemma":[0.00020520974,0.00008261947,0.07110734,0.00014108478,0.00007257533,0.00015059917,0.00008592045,0.002289272,8.332159e-7,0.00022589967,0.9253254,0.00031323155],"about_ca_topic_score_codex":0.00053147535,"about_ca_topic_score_gemma":0.0153915025,"teacher_disagreement_score":0.58282423,"about_ca_system_score_codex":0.0000028844372,"about_ca_system_score_gemma":0.00137101,"threshold_uncertainty_score":0.99995816},"labels":[],"label_agreement":null},{"id":"W4280533865","doi":"10.1038/s41597-022-01330-5","title":"A benchmark dataset for Hydrogen Combustion","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Division of Chemistry; Natural Sciences and Engineering Research Council of Canada; Office of Science; National Energy Research Scientific Computing Center; China Scholarship Council; U.S. Department of Energy; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Potential energy surface; Combustion; Ab initio; Benchmark (surveying); Hydrogen; Reaction coordinate; Chemistry; Potential energy; Density functional theory; Computer science; Statistical physics; Computational chemistry; Physics; Atomic physics; Physical chemistry","score_opus":0.0528722733954892,"score_gpt":0.3192898238311557,"score_spread":0.26641755043566645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4280533865","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33738998,0.00017075668,0.009814845,0.0015760761,0.014995767,0.0014157677,0.63360775,0.0002769974,0.0007520685],"genre_scores_gemma":[0.45365098,0.0000017922607,0.059814364,0.0008722416,0.00040001606,0.00041458855,0.4800456,0.00005870385,0.0047417055],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99682844,0.00026640084,0.00031097687,0.0012837366,0.00084390456,0.0004665401],"domain_scores_gemma":[0.9965069,0.0001418557,0.00019165919,0.003005931,0.0000504394,0.00010318059],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008551876,0.00013177177,0.0001605139,0.00012540305,0.0020428018,0.00069122144,0.004563924,0.000020575824,0.00883648],"category_scores_gemma":[0.0006566431,0.00012901248,0.000024585763,0.00046864364,0.00034025806,0.0006998572,0.004514709,0.00011031898,0.00046476675],"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":[0.000025121304,0.000060726146,0.000039945164,0.000019706344,0.0000017307241,0.000002754551,0.00007903973,0.0031977794,0.40849197,0.00041868706,0.58692485,0.0007377176],"study_design_scores_gemma":[0.00028704052,0.000074784424,0.00006623546,0.0000049763394,0.000018275357,0.000024180059,0.000093599905,0.051065575,0.019215189,0.001481939,0.9274415,0.0002267531],"about_ca_topic_score_codex":0.00006105682,"about_ca_topic_score_gemma":0.000023012619,"teacher_disagreement_score":0.38927677,"about_ca_system_score_codex":0.000060596063,"about_ca_system_score_gemma":0.00016488385,"threshold_uncertainty_score":0.99925643},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W4280538994","doi":"10.1038/s41597-022-01326-1","title":"A global inventory of animal diversity measured in different grazing treatments","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Rangeland Management and Livestock Ecology","field":"Environmental Science","cited_by":8,"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; University of Toronto; University of Alberta","funders":"Killam Trusts; Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Biodiversity; Grazing; Ecosystem; Ecology; Domestication; Conservation grazing; Geography; Terrestrial ecosystem; Biology; Environmental resource management; Agroforestry; Environmental science","score_opus":0.05652990885548431,"score_gpt":0.25401390766263576,"score_spread":0.19748399880715145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4280538994","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":[0.9951137,0.000024221035,0.00001419763,0.00007214737,0.00048124974,0.00020073522,0.0005825231,0.000012216876,0.0034990662],"genre_scores_gemma":[0.9987519,0.0000010705035,0.000047220656,0.000013661451,0.0000056427025,0.000009034411,0.0004122492,0.0000022243505,0.00075704034],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9986774,0.000101770165,0.00013085584,0.00046438232,0.00042111136,0.00020448765],"domain_scores_gemma":[0.9992557,0.000008344068,0.000067190405,0.0006206471,0.000002105299,0.000045994788],"candidate_categories":["open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005798262,0.00007474709,0.00011186915,0.000053970187,0.00041945506,0.000018429362,0.0011054853,0.000013030939,0.0016610331],"category_scores_gemma":[0.000018267338,0.00006784719,0.000025145324,0.00041738406,0.00017639944,0.00020550007,0.008553694,0.000043930948,0.000035764228],"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":[0.000037655598,0.00029305005,0.94807607,0.0000035120238,0.000013485239,0.000010175504,0.00018530907,0.00006849249,0.00062162,0.00006571119,0.049604025,0.0010209208],"study_design_scores_gemma":[0.0004699756,0.00008496482,0.98648703,0.0000017456182,0.000021775419,9.332181e-7,0.00022411213,0.00083859003,0.0000113846445,0.0004400554,0.011348085,0.00007134219],"about_ca_topic_score_codex":0.00070517755,"about_ca_topic_score_gemma":0.0030455696,"teacher_disagreement_score":0.03841099,"about_ca_system_score_codex":0.00026987068,"about_ca_system_score_gemma":0.000008378057,"threshold_uncertainty_score":0.9994649},"labels":[],"label_agreement":null},{"id":"W4280604425","doi":"10.1038/s41597-022-01334-1","title":"Recommendations for repositories and scientific gateways from a neuroscience perspective","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Research Data Management Practices","field":"Computer Science","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; Montreal Neurological Institute and Hospital","funders":"Karolinska Institutet","keywords":"Perspective (graphical); Gateway (web page); Set (abstract data type); Service (business); World Wide Web; Key (lock); Data science; Computer science; Neuroscience; Psychology; Business","score_opus":0.25733234120299003,"score_gpt":0.4056090017322596,"score_spread":0.14827666052926958,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4280604425","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":[0.0093155755,0.0018421593,0.80946076,0.094651826,0.036334693,0.002950813,0.04198541,0.0006501427,0.0028086281],"genre_scores_gemma":[0.43117675,0.00017908843,0.43190452,0.0013531704,0.00059000636,0.0012285054,0.024413377,0.00008619446,0.109068364],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9954063,0.0002640593,0.00024992623,0.0025821927,0.0010449109,0.0004525691],"domain_scores_gemma":[0.9935909,0.00041461148,0.00019339456,0.005416384,0.00023262696,0.00015206797],"candidate_categories":["sts","scholarly_communication","open_science"],"consensus_categories":["scholarly_communication","open_science"],"category_scores_codex":[0.005581965,0.00012395914,0.000117485826,0.00038427746,0.005351574,0.022474319,0.010165373,0.000013099149,0.000036758756],"category_scores_gemma":[0.0021574432,0.00012693857,0.000025609244,0.0020620837,0.0006772501,0.030564463,0.018783716,0.00020282826,0.0000103063785],"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":[0.000017227083,0.000203861,0.00014427857,0.000011904798,0.000017982942,0.000016662523,0.0019650906,0.00002479142,0.0074257166,0.45531136,0.5283482,0.0065129087],"study_design_scores_gemma":[0.00019010284,0.000056932957,0.0003484922,0.000004584588,0.000011207058,0.000007896195,0.001898063,0.040359564,0.00025861253,0.012671079,0.94403374,0.00015972111],"about_ca_topic_score_codex":0.00028161335,"about_ca_topic_score_gemma":0.000093919254,"teacher_disagreement_score":0.44264027,"about_ca_system_score_codex":0.000108421664,"about_ca_system_score_gemma":0.0003278387,"threshold_uncertainty_score":0.9959433},"labels":[],"label_agreement":null},{"id":"W4281486635","doi":"10.1038/s41597-022-01338-x","title":"MusMorph, a database of standardized mouse morphology data for morphometric meta-analyses","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Morphological variations and asymmetry","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Alberta Children's Hospital; University of Alberta; Alberta Bone and Joint Health Institute; University of Calgary","funders":"National Institute of Dental and Craniofacial Research; National Institute of Diabetes and Digestive and Kidney Diseases; National Heart, Lung, and Blood Institute; Alberta Children's Hospital Foundation; Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; National Human Genome Research Institute; Alberta Children's Hospital Research Institute; Alberta Innovates - Health Solutions; National Institutes of Health; U.S. Department of Health and Human Services; Children's Hospital Foundation; Government of Canada; Alberta Innovates; University of Calgary","keywords":"Workflow; Computer science; Context (archaeology); Scripting language; Morphometrics; Pipeline (software); File format; Biology; Database; Artificial intelligence; Information retrieval","score_opus":0.5703114693802749,"score_gpt":0.45797957275730233,"score_spread":0.11233189662297255,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281486635","genre_codex":"dataset","genre_gemma":"methods","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":[0.016059231,0.0011465111,0.2617361,0.0005476115,0.0010270235,0.0011676407,0.71796167,0.00010560746,0.00024863708],"genre_scores_gemma":[0.10296816,0.000023853147,0.6895272,0.00024243287,0.00011313284,0.00033051008,0.19516228,0.00008290273,0.011549495],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99557734,0.00041661886,0.0008925015,0.001619105,0.0010541651,0.00044028592],"domain_scores_gemma":[0.9867688,0.0015800059,0.00061291136,0.010685873,0.00022759478,0.00012480501],"candidate_categories":["open_science","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.009948225,0.00023954744,0.0009196976,0.00077499804,0.0006942385,0.00015501885,0.0060819746,0.000051596937,0.007813033],"category_scores_gemma":[0.0075821728,0.00018234598,0.00022420553,0.002803033,0.00029749612,0.00053664093,0.009453977,0.0002356327,0.00001868368],"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":[0.00006688561,0.0007165862,0.000014442305,0.00008673098,0.0013787568,0.000016779246,0.00002253563,0.000041134626,0.025741305,0.008629529,0.96295565,0.000329652],"study_design_scores_gemma":[0.0035175227,0.00025519618,0.00003943283,0.0000097214825,0.014250606,0.00008119561,0.001003283,0.029694406,0.0104748225,0.017537903,0.92223066,0.00090527546],"about_ca_topic_score_codex":0.0000906047,"about_ca_topic_score_gemma":0.000024950343,"teacher_disagreement_score":0.5227994,"about_ca_system_score_codex":0.00004580363,"about_ca_system_score_gemma":0.00022031252,"threshold_uncertainty_score":0.9992956},"labels":[],"label_agreement":null},{"id":"W4281659215","doi":"10.1038/s41597-022-01314-5","title":"Indoor heat measurement data from low-income households in rural and urban South Asia","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Climate Change and Health Impacts","field":"Environmental Science","cited_by":33,"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":"Government College University, Lahore; Department for International Development; International Development Research Centre","keywords":"Geography; Socioeconomic status; Urban heat island; Heat stress; South asia; Socioeconomics; Rural area; Thermal comfort; Environmental science; Environmental health; Meteorology; Population; Medicine","score_opus":0.1739709056250032,"score_gpt":0.30670960178359713,"score_spread":0.13273869615859393,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281659215","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":[0.9712542,0.0003902436,0.000010142034,0.0007284057,0.0010595488,0.0004028522,0.02556214,0.000041463263,0.0005509536],"genre_scores_gemma":[0.99141985,0.000014453458,0.00014331781,0.00029583555,0.000065150416,0.000014765286,0.0077779,0.000016888413,0.0002518603],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9969101,0.000119977005,0.00029414895,0.0010265829,0.0011234792,0.0005256879],"domain_scores_gemma":[0.9964901,0.0000293128,0.00006640501,0.0031553817,0.000005145582,0.0002536584],"candidate_categories":["open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0031956073,0.00014361761,0.00017613312,0.000073590105,0.0005868786,0.00025036695,0.0024307284,0.00003115086,0.0052283015],"category_scores_gemma":[0.00012169704,0.00013754074,0.000010880183,0.0005405775,0.00024421012,0.00078962516,0.01005968,0.00022821117,0.00040785043],"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":[0.00005730627,0.00023806668,0.45054275,0.000029556255,0.000007763791,0.00003713184,0.0030198,0.000035402965,0.0055285157,0.0000033849929,0.53449804,0.0060023144],"study_design_scores_gemma":[0.0017485907,0.000117007614,0.8013431,0.00012986656,0.00003755929,0.000013100906,0.0045167343,0.013180768,0.00020843552,0.0003139774,0.17779541,0.00059548864],"about_ca_topic_score_codex":0.0022845368,"about_ca_topic_score_gemma":0.0048341756,"teacher_disagreement_score":0.3567026,"about_ca_system_score_codex":0.00030895273,"about_ca_system_score_gemma":0.000054240776,"threshold_uncertainty_score":0.9979468},"labels":[],"label_agreement":null},{"id":"W4281704256","doi":"10.1038/s41597-022-01342-1","title":"Downburst-like experimental impinging jet measurements at the WindEEE Dome","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Wind and Air Flow Studies","field":"Environmental Science","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Ontario Tech University; McGill University; Wind Energy Institute of Canada; Western University","funders":"European Commission","keywords":"Thunderstorm; Jet (fluid); Meteorology; Context (archaeology); Geology; Dome (geology); Outflow; Wind tunnel; Environmental science; Physics; Mechanics","score_opus":0.07372112800546714,"score_gpt":0.2776835011676654,"score_spread":0.20396237316219823,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281704256","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":[0.97282994,0.00089900533,0.000027396636,0.0017220592,0.006003016,0.0005108905,0.0018162929,0.00009837188,0.016093053],"genre_scores_gemma":[0.9821259,0.0000015877569,0.00011210461,0.0004371637,0.000068312416,0.000046793626,0.0006176336,0.000014224382,0.016576272],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99716675,0.00009659995,0.00018439218,0.00086445204,0.0012449268,0.00044288562],"domain_scores_gemma":[0.99812275,0.000026819933,0.00007293823,0.0016955483,0.000004722443,0.00007721351],"candidate_categories":["sts","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0017948997,0.00014870727,0.00011160535,0.000034214267,0.003762522,0.00019176262,0.0021490667,0.00001284203,0.01312803],"category_scores_gemma":[0.000028468048,0.00010397917,0.000047158814,0.00048173784,0.00060347613,0.000377081,0.011399665,0.00013866919,0.0011703259],"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":[0.00001254605,0.00013953638,0.016214311,0.0000020567327,0.000023733824,0.000007720669,0.0013956917,0.00037699207,0.07307132,0.0000066916955,0.9065649,0.0021845018],"study_design_scores_gemma":[0.00034792663,0.000031545555,0.005952452,0.000004694395,0.000016817505,0.000016417802,0.002185295,0.00051002373,0.006607206,0.000043387678,0.9840465,0.00023772274],"about_ca_topic_score_codex":0.000114750714,"about_ca_topic_score_gemma":0.00014139531,"teacher_disagreement_score":0.07748161,"about_ca_system_score_codex":0.00034900196,"about_ca_system_score_gemma":0.00001613113,"threshold_uncertainty_score":0.9996074},"labels":[],"label_agreement":null},{"id":"W4281713424","doi":"10.1038/s41597-022-01371-w","title":"Voluntary consensus based geospatial data standards for the global illegal trade in wild fauna and flora","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Wildlife Ecology and Conservation","field":"Environmental Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Esri (Canada)","funders":"Division of Civil, Mechanical and Manufacturing Innovation; College of Engineering, Michigan State University; Michigan State University; National Science Foundation","keywords":"Geospatial analysis; Wildlife; Citizen journalism; Data discovery; Data science; Citizen science; Environmental resource management; Geography; Metadata; Computer science; Ecology; World Wide Web; Biology; Remote sensing; Environmental science","score_opus":0.0375187251057688,"score_gpt":0.28029885888343137,"score_spread":0.24278013377766255,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281713424","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":[0.82638484,0.00019151445,0.0018312543,0.02362628,0.003064978,0.0010417211,0.1434963,0.000039732106,0.0003233479],"genre_scores_gemma":[0.9875438,0.0000021036053,0.0013137341,0.0013051716,0.000046943616,0.000042684696,0.009534808,0.0000069894777,0.000203739],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99819756,0.00012279571,0.00018660663,0.0007743455,0.0004647925,0.0002538789],"domain_scores_gemma":[0.9980106,0.000193224,0.000061421284,0.0016801956,0.000005090905,0.000049492992],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0031881079,0.00008917267,0.000092627946,0.000021701742,0.0009561418,0.0001030746,0.0017651242,0.000028833982,0.0010476157],"category_scores_gemma":[0.0002220076,0.0000755,0.000012532122,0.00037719577,0.0006397763,0.00029311562,0.0025761784,0.0001322732,0.000008686105],"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":[0.00013639052,0.00007711952,0.26150376,0.0000051999946,0.000009115014,0.000008522362,0.000092758884,0.0009434464,0.000023067862,0.000075595635,0.72579736,0.01132767],"study_design_scores_gemma":[0.0006527007,0.000035272762,0.31094515,0.0000024349386,0.000022951821,0.000010720026,0.00029058073,0.2466729,0.000003038287,0.0003464759,0.44091251,0.00010525731],"about_ca_topic_score_codex":0.0009615263,"about_ca_topic_score_gemma":0.012987039,"teacher_disagreement_score":0.28488484,"about_ca_system_score_codex":0.0001710854,"about_ca_system_score_gemma":0.00019610972,"threshold_uncertainty_score":0.9998656},"labels":[],"label_agreement":null},{"id":"W4281730041","doi":"10.1038/s41597-022-01396-1","title":"A global database of woody tissue carbon concentrations","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Forest Ecology and Biodiversity Studies","field":"Agricultural and Biological Sciences","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"The Scarborough Hospital; University of Toronto","funders":"Centre for Global Change Science, University of Toronto; U.S. Forest Service; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Northern Research Station; University of Toronto; University of Toronto Scarborough; Impact Fund; U.S. Department of Agriculture","keywords":"Woody plant; Biome; Database; Environmental science; Coarse woody debris; Biology; Ecology; Ecosystem; Computer science","score_opus":0.05071179355147193,"score_gpt":0.2554810614561086,"score_spread":0.20476926790463668,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281730041","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":[0.949565,0.00020212759,6.5296865e-7,0.0010687561,0.00080891856,0.00012798505,0.046766914,0.00002219141,0.0014374836],"genre_scores_gemma":[0.9902162,0.0000041596572,0.00004922165,0.000050705028,0.000025892523,0.0000033273484,0.009022448,9.370322e-8,0.00062797545],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99916613,0.000053742024,0.0000951554,0.00033347533,0.00020417332,0.00014729374],"domain_scores_gemma":[0.99963635,0.000036483623,0.000053456355,0.0002082063,0.000031738055,0.000033767268],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003879915,0.000047341546,0.000074793934,0.0000059109025,0.0007822683,0.000028126637,0.00090693415,0.000013952978,0.0009970074],"category_scores_gemma":[0.000053781372,0.00002111053,0.00001404965,0.00052037695,0.00028531515,0.00010045333,0.0019112797,0.000043447657,0.000015223429],"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":[0.00006152625,0.0006497286,0.32260352,0.000014683822,0.000064602486,0.00003074855,0.00023416991,0.000018212137,0.04508322,0.003038899,0.6167049,0.011495827],"study_design_scores_gemma":[0.00022316065,0.00026238157,0.25471207,0.000004532092,0.00005201192,0.000011099705,0.002919501,0.0003357676,0.0008740655,0.0005007965,0.7398972,0.00020742965],"about_ca_topic_score_codex":0.00049487775,"about_ca_topic_score_gemma":0.003113855,"teacher_disagreement_score":0.12319231,"about_ca_system_score_codex":0.000018401448,"about_ca_system_score_gemma":0.000018292785,"threshold_uncertainty_score":0.9999162},"labels":[],"label_agreement":null},{"id":"W4281760743","doi":"10.1038/s41597-022-01381-8","title":"CAN-SAR: A database of Canadian species at risk information","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Species Distribution and Climate Change","field":"Environmental Science","cited_by":13,"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; Carleton University; Environment and Climate Change Canada","funders":"Environment and Climate Change Canada","keywords":"Listing (finance); Threatened species; Database; Computer science; Environmental resource management; Business; Ecology; Biology; Habitat; Environmental science","score_opus":0.05533889582137173,"score_gpt":0.23479111536652028,"score_spread":0.17945221954514856,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281760743","genre_codex":"dataset","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":[0.44264373,0.000038531314,0.000017566348,0.0012830573,0.0013975024,0.0002646043,0.45416716,0.000030552903,0.1001573],"genre_scores_gemma":[0.85433483,0.000055604272,0.00014032012,0.00034666876,0.000015180363,0.000013468476,0.13464001,0.0000070266847,0.01044687],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987155,0.000041904328,0.00017840591,0.0002748183,0.0005378197,0.0002515114],"domain_scores_gemma":[0.9984173,0.000013150546,0.000114445334,0.0012944646,0.000010601134,0.00014999814],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0008455794,0.00006573841,0.00006719158,0.00017373283,0.0009058629,0.000083639025,0.0011189121,0.000012509456,0.25567415],"category_scores_gemma":[0.00010906451,0.00006689483,0.000019358664,0.0011542095,0.0003096942,0.00059198466,0.0027119922,0.00008175971,0.0016725721],"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":[0.0000048265283,0.000019478217,0.010154598,0.00000412485,0.0000027829763,0.0000016318237,0.00036702625,0.00004189144,0.00097641425,0.00039717415,0.98738414,0.00064588746],"study_design_scores_gemma":[0.000113895825,0.000008346519,0.0315302,0.0000011249923,0.0000073202214,0.0000038666553,0.002455147,0.00039528726,0.0004381053,0.0000173168,0.9649507,0.00007872499],"about_ca_topic_score_codex":0.14796302,"about_ca_topic_score_gemma":0.5377956,"teacher_disagreement_score":0.41169113,"about_ca_system_score_codex":0.0008258286,"about_ca_system_score_gemma":0.00005931726,"threshold_uncertainty_score":0.99910474},"labels":[],"label_agreement":null},{"id":"W4281769686","doi":"10.1038/s41597-022-01341-2","title":"Multi sequence average templates for aging and neurodegenerative disease populations","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":16,"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; University of Alberta; McGill University","funders":"Consortium canadien en neurodégénérescence associée au vieillissement","keywords":"Dementia; Cognitive impairment; Template; Dementia with Lewy bodies; Atrophy; Vascular dementia; Cognition; Magnetic resonance imaging; Disease; Medicine; Neuroscience; Audiology; Psychology; Pathology; Computer science; Radiology","score_opus":0.23881487453547012,"score_gpt":0.423258379006209,"score_spread":0.18444350447073887,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281769686","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":[0.96921027,0.00040944127,0.006815193,0.003169863,0.0007862939,0.0015464894,0.017866379,0.000061144885,0.00013493998],"genre_scores_gemma":[0.97433627,0.00000391616,0.0030554049,0.00020195053,0.00003350244,0.00010951861,0.012233128,0.000009575157,0.0100167105],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9986942,0.000060380076,0.000115100505,0.0005746548,0.0003417658,0.00021393687],"domain_scores_gemma":[0.99908215,0.000040846215,0.000030026316,0.0005971413,0.00008524074,0.0001646042],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00072756066,0.00006854843,0.00007914995,0.00012519534,0.0010279681,0.00017278423,0.00024689536,0.000005702427,0.0002782243],"category_scores_gemma":[0.00026108095,0.00006323937,0.000021037838,0.0002537682,0.0001452902,0.00024910903,0.00080395944,0.000093413146,0.000008134065],"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":[0.00055588176,0.0016901089,0.60450363,0.00050905487,0.00015573588,0.00039949376,0.0015416133,0.0002990845,0.16352233,0.0019093112,0.17898911,0.04592463],"study_design_scores_gemma":[0.004002088,0.0003240949,0.4275761,0.000068333546,0.00026684077,0.00005915708,0.0010786903,0.37550634,0.0023430635,0.0011747958,0.18719186,0.00040865658],"about_ca_topic_score_codex":0.000015814285,"about_ca_topic_score_gemma":0.000013357141,"teacher_disagreement_score":0.37520725,"about_ca_system_score_codex":0.000025720054,"about_ca_system_score_gemma":0.00014593573,"threshold_uncertainty_score":0.79064035},"labels":[],"label_agreement":null},{"id":"W4282836069","doi":"10.1038/s41597-022-01398-z","title":"Optimising the classification of feature-based attention in frequency-tagged electroencephalography data","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"EEG and Brain-Computer Interfaces","field":"Neuroscience","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":"Canadian Institute for Advanced Research","funders":"Centre of Excellence for Integrative Brain Function, Australian Research Council; Medical Research Council; Department of Education and Training; National Health and Medical Research Council; Canadian Institute for Advanced Research","keywords":"Electroencephalography; Feature (linguistics); Computer science; Pattern recognition (psychology); Artificial intelligence; Psychology; Neuroscience; Linguistics","score_opus":0.1058437764238055,"score_gpt":0.3185147871910828,"score_spread":0.2126710107672773,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4282836069","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":[0.9690646,0.000367723,0.00903703,0.0067736465,0.0035023424,0.0008598509,0.0092821065,0.00011931979,0.0009934122],"genre_scores_gemma":[0.9936487,0.0000031354398,0.0024949664,0.00020382411,0.000024621178,0.000013105669,0.003467765,0.000008880277,0.00013496501],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99696755,0.0004865705,0.00028626493,0.0011756324,0.0007529188,0.00033103308],"domain_scores_gemma":[0.9956055,0.00023291344,0.00022558337,0.0038627866,0.000038775266,0.00003443513],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0032477519,0.00010746803,0.00011812085,0.00034505906,0.00067309494,0.0003254195,0.0062887836,0.00002377871,0.00006456613],"category_scores_gemma":[0.00040564925,0.00008433914,0.000032221953,0.002210833,0.00043690624,0.0006839003,0.0018448989,0.00033098427,0.000006369855],"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":[0.000017541823,0.0001683654,0.001525829,0.000013293337,0.0000031769516,0.0000043801083,0.0001134232,0.00021435172,0.9639853,0.0007811194,0.030822346,0.0023508715],"study_design_scores_gemma":[0.0018195884,0.000316006,0.06275317,0.0001639162,0.00008087195,0.00006468027,0.001381246,0.6678377,0.1988357,0.005954063,0.05995866,0.0008344351],"about_ca_topic_score_codex":0.000039937582,"about_ca_topic_score_gemma":0.00008166274,"teacher_disagreement_score":0.7651496,"about_ca_system_score_codex":0.000036872356,"about_ca_system_score_gemma":0.00015219241,"threshold_uncertainty_score":0.9990877},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"observational","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W4282928084","doi":"10.1038/s41597-022-01386-3","title":"A longitudinal multi-scanner multimodal human neuroimaging dataset","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":13,"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; Centre for Addiction and Mental Health","funders":"National Institute of Mental Health; U.S. Department of Health and Human Services","keywords":"Neuroimaging; Scanner; Modalities; Human brain; Computer science; Diffusion MRI; Consistency (knowledge bases); Artificial intelligence; Medical physics; Psychology; Medicine; Neuroscience; Magnetic resonance imaging; Radiology","score_opus":0.21471255176186121,"score_gpt":0.36186154707270757,"score_spread":0.14714899531084635,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4282928084","genre_codex":"dataset","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":[0.40397146,0.00021370368,0.0016423487,0.015576985,0.020257285,0.0015906862,0.5545055,0.0008422854,0.0013996963],"genre_scores_gemma":[0.97773826,7.8490905e-7,0.00066700054,0.002075194,0.00012682122,0.000060970873,0.015592907,0.00003279293,0.00370527],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9957369,0.00029026097,0.00024237219,0.0022673674,0.00097305316,0.0004900725],"domain_scores_gemma":[0.995868,0.0008202406,0.00011409016,0.003058903,0.00003546353,0.00010326498],"candidate_categories":["sts","open_science"],"consensus_categories":[],"category_scores_codex":[0.0015047364,0.00018821236,0.00016648528,0.00024781437,0.0041614296,0.00046063412,0.00285144,0.0000130129865,0.0008761466],"category_scores_gemma":[0.0044513047,0.00019560936,0.00003994069,0.0009233169,0.0006427415,0.0009403113,0.00912704,0.0003844994,0.00027993083],"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":[0.000017450711,0.00033961437,0.002042112,0.000010056736,0.000007883569,0.00011801609,0.00014644541,0.00034663003,0.13347377,0.00035056588,0.8623653,0.00078212627],"study_design_scores_gemma":[0.00076160126,0.000054421704,0.009381358,0.000004955842,0.000022184855,0.000121209894,0.00024514383,0.0333974,0.0036308959,0.00016253236,0.9518369,0.0003814083],"about_ca_topic_score_codex":0.00017039411,"about_ca_topic_score_gemma":0.00021562784,"teacher_disagreement_score":0.5737668,"about_ca_system_score_codex":0.00008723734,"about_ca_system_score_gemma":0.00009946676,"threshold_uncertainty_score":0.99888694},"labels":[],"label_agreement":null},{"id":"W4282932896","doi":"10.1038/s41597-022-01463-7","title":"Datasets for benchmarking antimicrobial resistance genes in bacterial metagenomic and whole genome sequencing","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","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":"Dalhousie University; Sunnybrook Health Science Centre; Public Health Agency of Canada; Sunnybrook Hospital; McMaster University","funders":"Biotechnology and Biological Sciences Research Council; Medical Research Council; Joint Programming Initiative on Antimicrobial Resistance; Canadian Institutes of Health Research; Quadram Institute Bioscience; Universiteit van Amsterdam; Government of Canada","keywords":"Metagenomics; Computational biology; Biology; Genome; Gene prediction; Genomics; Whole genome sequencing; Identification (biology); DNA sequencing; Gene; Genetics","score_opus":0.03591850040073827,"score_gpt":0.26020224917409196,"score_spread":0.2242837487733537,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4282932896","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":[0.93531,0.0021484152,0.00013300226,0.00009348021,0.0009549828,0.00029990537,0.0610234,0.000002007254,0.000034777197],"genre_scores_gemma":[0.9313124,0.00011600821,0.0064657223,0.00009501609,0.00029325188,0.000047443296,0.06112145,0.000021707257,0.00052702345],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.998574,0.00005414565,0.00020107088,0.0008216066,0.000087801236,0.0002613383],"domain_scores_gemma":[0.9989308,0.000013000823,0.000075794356,0.00092369627,0.000019379215,0.000037317404],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010127045,0.00011156829,0.0001331912,0.000065556174,0.0005065034,0.00012455754,0.00068183726,0.000026176604,0.000015828105],"category_scores_gemma":[0.00003507952,0.00012406272,0.000023716473,0.000106034015,0.0001236509,0.0000040116447,0.002092178,0.000048319223,0.0000010873991],"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":[0.000053292322,0.000013839403,0.00020018649,0.000021529335,0.000023344033,0.0000019586012,0.000064840184,0.00010443244,0.9868191,0.0000109645525,0.012109902,0.00057661586],"study_design_scores_gemma":[0.00052349287,0.000042983294,0.0013956185,0.000004342598,0.000022324935,0.000007805426,0.00014574855,0.00017750017,0.021614494,0.000048193047,0.97580725,0.00021027307],"about_ca_topic_score_codex":0.000021817394,"about_ca_topic_score_gemma":0.00066816143,"teacher_disagreement_score":0.9652046,"about_ca_system_score_codex":0.00002821559,"about_ca_system_score_gemma":0.00012758265,"threshold_uncertainty_score":0.5059131},"labels":[],"label_agreement":null},{"id":"W4282962995","doi":"10.1038/s41597-022-01401-7","title":"A large, curated, open-source stroke neuroimaging dataset to improve lesion segmentation algorithms","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Acute Ischemic Stroke Management","field":"Medicine","cited_by":149,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Research Institute for Aging; Heart and Stroke Foundation; University of Waterloo; Sunnybrook Health Science Centre; Ontario Brain Institute; University of Toronto; University of British Columbia","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Institute of Neurological Disorders and Stroke; Medical Research Council; National Institute of General Medical Sciences; Wellcome Trust; U.S. Department of Veterans Affairs","keywords":"Generalizability theory; Segmentation; Computer science; Artificial intelligence; Neuroimaging; Atlas (anatomy); Pattern recognition (psychology); Stroke (engine); Machine learning; Medicine; Mathematics; Statistics","score_opus":0.06612173964472086,"score_gpt":0.35520756388031677,"score_spread":0.2890858242355959,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4282962995","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10466748,0.00028340946,0.09574472,0.017522115,0.011438303,0.009417011,0.7517484,0.0005270113,0.008651554],"genre_scores_gemma":[0.066362396,0.0000126285695,0.0368044,0.009346709,0.00036113942,0.0003702934,0.7949009,0.0001288231,0.0917127],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9967853,0.00008566306,0.00032709938,0.0014066756,0.000941292,0.00045395966],"domain_scores_gemma":[0.996333,0.000029221621,0.00013387768,0.003238953,0.00005859559,0.00020635407],"candidate_categories":["open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0019867155,0.00016999732,0.00020640575,0.00026888808,0.00074079086,0.0005445679,0.0023440702,0.000016627138,0.0009140257],"category_scores_gemma":[0.00016500558,0.00017013693,0.000025166915,0.000814677,0.00006227687,0.0006860632,0.016778458,0.00027092878,0.00028981402],"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":[0.000052697047,0.00019195583,0.00019417708,0.000022999518,0.000031015974,0.000059292637,0.00017920817,0.00002812342,0.067858,0.000007394835,0.90597534,0.025399797],"study_design_scores_gemma":[0.0014840504,0.00010680331,0.000158371,0.000016298207,0.00010074848,0.00003645288,0.0031055855,0.01720556,0.0038229171,0.000002379175,0.9737935,0.00016732133],"about_ca_topic_score_codex":0.00013711848,"about_ca_topic_score_gemma":0.000013581286,"teacher_disagreement_score":0.083061144,"about_ca_system_score_codex":0.00016080227,"about_ca_system_score_gemma":0.00013170391,"threshold_uncertainty_score":0.9999993},"labels":[{"model":"gemma","categories":["open_science"],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W4282979725","doi":"10.1038/s41597-022-01391-6","title":"Long-term ice phenology records spanning up to 578 years for 78 lakes around the Northern Hemisphere","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Arctic and Antarctic ice dynamics","field":"Earth and Planetary Sciences","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ministry of Environment; York University","funders":"Division of Environmental Biology; Vetenskapsrådet; National Science Foundation; Siberian Branch, Russian Academy of Sciences; Svenska Forskningsrådet Formas; York University; Leibniz-Institut für Angewandte Geophysik; University of Wisconsin-Madison","keywords":"Phenology; Climate change; Physical geography; Cryosphere; Climatology; Ice core; Geography; Northern Hemisphere; Environmental science; Sea ice; Oceanography; Ecology; Geology; Biology","score_opus":0.03937940469166653,"score_gpt":0.26067399814258424,"score_spread":0.2212945934509177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4282979725","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":[0.98156744,0.00016822005,0.0019837937,0.0017421838,0.005809779,0.00044191716,0.007142418,0.000048588972,0.0010956427],"genre_scores_gemma":[0.97055733,0.000006474859,0.0009271761,0.0006672878,0.00028335012,0.0000099837025,0.00911837,0.000009560847,0.018420491],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99824584,0.00007583251,0.00020060579,0.0006675096,0.00036420033,0.000446018],"domain_scores_gemma":[0.9983372,0.00022150256,0.00009147202,0.0012022213,0.000042081494,0.00010550191],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0013139789,0.00011747936,0.00013195963,0.000049553444,0.0013601063,0.00027244812,0.0020619403,0.00002794783,0.0025299513],"category_scores_gemma":[0.00013886247,0.00009263205,0.00004191677,0.00041652386,0.00022979507,0.00025568838,0.00043476655,0.00019505426,0.00027072956],"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":[0.00016623533,0.000045034274,0.59020454,0.000052122738,0.000077611,0.000039996896,0.0038665123,0.004240441,0.00006228373,0.000112482805,0.09673168,0.30440107],"study_design_scores_gemma":[0.00055559544,0.00023241274,0.15093613,0.00002838301,0.00009387274,0.00011971664,0.013400153,0.04254212,0.000007158898,0.0012083398,0.79033124,0.0005448706],"about_ca_topic_score_codex":0.0006868239,"about_ca_topic_score_gemma":0.015361469,"teacher_disagreement_score":0.6935996,"about_ca_system_score_codex":0.000013824535,"about_ca_system_score_gemma":0.00016378488,"threshold_uncertainty_score":0.99994},"labels":[],"label_agreement":null},{"id":"W4283012421","doi":"10.1038/s41597-022-01423-1","title":"A dataset of simulated patient-physician medical interviews with a focus on respiratory cases","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Tellabs (Canada); University of Waterloo; Polytechnique Montréal; Western University","funders":"","keywords":"Computer science; Conversation; Artificial intelligence; Focus (optics); Natural language processing; Set (abstract data type); Converse; Machine learning; Psychology","score_opus":0.0875093153622667,"score_gpt":0.35201481907884236,"score_spread":0.26450550371657566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283012421","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":[0.68725175,0.0022623194,0.021997754,0.015933862,0.011795119,0.003989983,0.25354078,0.0009937384,0.0022347067],"genre_scores_gemma":[0.98441744,7.220165e-7,0.0018847974,0.0023901204,0.000038966402,0.000019117402,0.011177172,0.000018043827,0.000053635784],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9957798,0.0006688255,0.00044362165,0.0011165068,0.0016737028,0.0003175101],"domain_scores_gemma":[0.9940192,0.00028435042,0.00029825137,0.005138886,0.00008122846,0.00017809452],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0022627194,0.00014246975,0.00021603706,0.00024036078,0.00047857128,0.00014570574,0.0055860546,0.000027367216,0.00026957362],"category_scores_gemma":[0.0005342471,0.0001147929,0.000025722831,0.0013317487,0.00021769796,0.00041494463,0.0058774143,0.0004588566,0.00004872155],"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":[0.00012895306,0.000821592,0.0011470038,0.00014457059,0.000047367594,0.0008806485,0.002233394,0.0034582743,0.000108078726,0.0031192265,0.6102218,0.37768912],"study_design_scores_gemma":[0.00042401548,0.0013023235,0.00021004176,0.00012930277,0.000009896291,0.00004903255,0.00021737195,0.18593399,0.0002006565,0.00021528667,0.8110432,0.00026489535],"about_ca_topic_score_codex":0.00043123096,"about_ca_topic_score_gemma":0.00031286126,"teacher_disagreement_score":0.3774242,"about_ca_system_score_codex":0.000052007592,"about_ca_system_score_gemma":0.00047901808,"threshold_uncertainty_score":0.9997942},"labels":[],"label_agreement":null},{"id":"W4283020606","doi":"10.1038/s41597-022-01373-8","title":"PISCOeo_pm, a reference evapotranspiration gridded database based on FAO Penman-Monteith in Peru","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Plant Water Relations and Carbon Dynamics","field":"Environmental Science","cited_by":26,"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":"Government of Canada; United States Agency for International Development","keywords":"Evapotranspiration; Cru; Wind speed; Environmental science; Penman–Monteith equation; Multivariate interpolation; Meteorology; Air temperature; Climatology; Dew point; Geography; Precipitation; Mathematics; Geology; Bilinear interpolation","score_opus":0.04865238788339328,"score_gpt":0.2543612250733049,"score_spread":0.20570883718991162,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283020606","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":[0.9442707,0.000029036368,0.0022750662,0.0007226425,0.0011435648,0.000765151,0.026526354,0.000095862124,0.024171645],"genre_scores_gemma":[0.97436166,0.0000018340369,0.000998759,0.000192395,0.000008253482,0.000040286435,0.022132443,0.000010322894,0.0022540647],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977363,0.00013515679,0.00022381233,0.00087266957,0.00075590366,0.00027618103],"domain_scores_gemma":[0.9981071,0.00003478779,0.00006497664,0.0017156205,0.0000053678436,0.00007219348],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0014134826,0.000120476405,0.00009781417,0.00013959156,0.0004715491,0.00014956416,0.0013261213,0.000024234554,0.0030667358],"category_scores_gemma":[0.00003819999,0.00011456473,0.00001813741,0.0007335401,0.00014270375,0.00055965333,0.0008017553,0.00026552795,0.0003158326],"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":[0.00042816668,0.0025388652,0.07827003,0.000060774462,0.000018554947,0.00030935672,0.001764923,0.78746766,0.053534146,0.0028432007,0.050502688,0.022261616],"study_design_scores_gemma":[0.00045653337,0.000058678663,0.006704668,0.000015104705,0.000009708323,0.0000043541804,0.00005309834,0.91284746,0.00010617018,0.00014394056,0.07938725,0.00021301213],"about_ca_topic_score_codex":0.0005327426,"about_ca_topic_score_gemma":0.002583339,"teacher_disagreement_score":0.12537982,"about_ca_system_score_codex":0.00017554118,"about_ca_system_score_gemma":0.000050386727,"threshold_uncertainty_score":0.9978446},"labels":[],"label_agreement":null},{"id":"W4283206600","doi":"10.1038/s41597-022-01383-6","title":"COVIDiSTRESS diverse dataset on psychological and behavioural outcomes one year into the COVID-19 pandemic","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"COVID-19 and Mental Health","field":"Psychology","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Texas A and M University","keywords":"Pandemic; Coronavirus disease 2019 (COVID-19); 2019-20 coronavirus outbreak; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Psychology; Data science; Geography; Biology; Virology; Medicine; Computer science; Pathology; Outbreak; Infectious disease (medical specialty)","score_opus":0.4563412743949642,"score_gpt":0.5145741972217943,"score_spread":0.058232922826830125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283206600","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":[0.8288701,0.00022452536,0.000047588645,0.008507442,0.00435778,0.0006646244,0.15689842,0.000100935344,0.00032855422],"genre_scores_gemma":[0.9303139,0.000015066192,0.00005345249,0.011387756,0.000045693156,0.00006839951,0.054955654,0.000012439805,0.0031476344],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99733794,0.00040639445,0.00023857366,0.0011360344,0.00051256735,0.00036847944],"domain_scores_gemma":[0.99649805,0.00034202373,0.00010046489,0.002761066,0.000009289823,0.00028912036],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0023344543,0.00014277975,0.0001697356,0.00010109068,0.0015572712,0.00013288156,0.0018877825,0.00004541576,0.0050344593],"category_scores_gemma":[0.00018115857,0.00010305402,0.000029574541,0.0003034491,0.00065773487,0.000112043585,0.0025018123,0.0003905259,0.00040325467],"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":[0.00019707988,0.0005753465,0.2560923,0.000015152281,0.000019939798,0.00003961489,0.002079192,0.0000015965386,0.000026728394,0.0014459391,0.73289335,0.0066137295],"study_design_scores_gemma":[0.0012297047,0.00018682747,0.122284025,0.0000024803155,0.00004120425,0.000025777754,0.0046911966,0.000012023476,8.723503e-7,0.0003722047,0.8709897,0.0001640289],"about_ca_topic_score_codex":0.0037041495,"about_ca_topic_score_gemma":0.001533047,"teacher_disagreement_score":0.13809629,"about_ca_system_score_codex":0.00025154903,"about_ca_system_score_gemma":0.00013920157,"threshold_uncertainty_score":0.99974257},"labels":[],"label_agreement":null},{"id":"W4283330995","doi":"10.1038/s41597-022-01425-z","title":"Global hydro-environmental lake characteristics at high spatial resolution","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Hydrology and Watershed Management Studies","field":"Environmental Science","cited_by":103,"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":"Australian Research Council; Natural Sciences and Engineering Research Council of Canada","keywords":"Structural basin; Land cover; Environmental science; Hydrology (agriculture); Grid; Range (aeronautics); Grid cell; Land use; Remote sensing; Geology; Ecology; Geomorphology","score_opus":0.016097980207951675,"score_gpt":0.21646955088171277,"score_spread":0.2003715706737611,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283330995","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":[0.97254896,0.000026221067,0.00038950477,0.0012020643,0.0032031026,0.0003048693,0.017065786,0.000080000784,0.005179481],"genre_scores_gemma":[0.9783872,0.0000058542087,0.00014506643,0.00026041782,0.000049060585,0.000021136999,0.011671041,0.0000070389465,0.009453184],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978515,0.00010722923,0.00019576712,0.00087386044,0.0005883955,0.0003832483],"domain_scores_gemma":[0.998607,0.000011549173,0.00009259546,0.0012177504,0.000001043206,0.00007011169],"candidate_categories":["sts","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0008506682,0.00012993412,0.00011830833,0.00002803262,0.0019830216,0.000057326677,0.0012251346,0.000026161546,0.017704839],"category_scores_gemma":[0.000021070042,0.00013133767,0.000026069125,0.00022281095,0.000706271,0.00027804123,0.012521838,0.00009649981,0.0022413463],"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":[0.00009207903,0.00029141424,0.323061,0.0000049976884,0.00003858233,0.00006350746,0.000207053,0.0014227786,0.0008110751,0.00009334631,0.66775507,0.0061590904],"study_design_scores_gemma":[0.00023804053,0.000040879942,0.28637952,8.527335e-7,0.000030037383,0.000009248912,0.000048235324,0.004845304,0.000015876027,0.0003218111,0.7079091,0.00016104917],"about_ca_topic_score_codex":0.00019883654,"about_ca_topic_score_gemma":0.0013523661,"teacher_disagreement_score":0.04015405,"about_ca_system_score_codex":0.00035737915,"about_ca_system_score_gemma":0.0000053759127,"threshold_uncertainty_score":0.9993163},"labels":[],"label_agreement":null},{"id":"W4283367256","doi":"10.1038/s41597-022-01467-3","title":"A multi-city urban atmospheric greenhouse gas measurement data synthesis","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Atmospheric and Environmental Gas Dynamics","field":"Environmental Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Environment and Climate Change Canada","funders":"Climate Program Office; U.S. Department of Commerce; Jet Propulsion Laboratory; National Aeronautics and Space Administration","keywords":"Greenhouse gas; Scope (computer science); Environmental science; Climate change; Baseline (sea); Environmental resource management; Methane; Environmental planning; Business; Natural resource economics; Environmental protection; Computer science; Political science; Ecology","score_opus":0.07164669648370428,"score_gpt":0.2414225334785098,"score_spread":0.16977583699480553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283367256","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":[0.8285055,0.0020464638,0.11844638,0.0025182918,0.010129634,0.003880301,0.023505531,0.0012770089,0.009690859],"genre_scores_gemma":[0.74249643,0.000080632104,0.23458712,0.00051891233,0.000112837515,0.00016541258,0.0039059166,0.00013947702,0.017993243],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9945328,0.00020275575,0.00038247084,0.0021243938,0.0021048593,0.00065272074],"domain_scores_gemma":[0.9921882,0.000040484138,0.00018134796,0.0073273224,0.0000064103356,0.00025624613],"candidate_categories":["metaepi_narrow","sts","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.0034165655,0.00028223477,0.00023436744,0.000005865018,0.0015156516,0.0002011696,0.007399784,0.00004256001,0.012560623],"category_scores_gemma":[0.00022467767,0.0002805623,0.00005044804,0.0007901921,0.00082286604,0.0009727386,0.0228108,0.00029124977,0.00082525983],"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":[0.00007514375,0.002699207,0.075231224,0.000022889815,0.000115383016,0.00009300858,0.000822317,0.030874737,0.004645464,0.000013521341,0.7468995,0.13850759],"study_design_scores_gemma":[0.00027725304,0.000033698732,0.010945655,0.0000054114603,0.000067349894,0.000017075643,0.0005329675,0.35954377,0.000023904951,0.000026050799,0.62814635,0.0003805348],"about_ca_topic_score_codex":0.001225481,"about_ca_topic_score_gemma":0.00068010646,"teacher_disagreement_score":0.32866904,"about_ca_system_score_codex":0.0008097882,"about_ca_system_score_gemma":0.00005586432,"threshold_uncertainty_score":0.99996465},"labels":[],"label_agreement":null},{"id":"W4283377869","doi":"10.1038/s41597-022-01459-3","title":"A global ensemble of ocean wave climate statistics from contemporary wave reanalysis and hindcasts","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Ocean Waves and Remote Sensing","field":"Earth and Planetary Sciences","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Environment and Climate Change Canada","funders":"","keywords":"Downscaling; Hindcast; Metadata; Climatology; Significant wave height; Environmental science; Scale (ratio); Sea state; Meteorology; Wind wave; Computer science; Geography; Remote sensing; Geology; Precipitation; Cartography; Oceanography","score_opus":0.061396723068705084,"score_gpt":0.2422891398862953,"score_spread":0.18089241681759022,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283377869","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":[0.7846856,0.0010969703,0.0003039712,0.00012195922,0.0013147213,0.00013607327,0.20906822,0.000023517528,0.0032489619],"genre_scores_gemma":[0.95972997,0.000024067527,0.008211462,0.000051317875,0.00003832612,3.397537e-9,0.03163435,0.000003137947,0.00030734035],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980755,0.00013669442,0.00031498246,0.0006539478,0.0005460613,0.00027283456],"domain_scores_gemma":[0.9985441,0.000110918336,0.00018499956,0.0009830125,0.000043037966,0.00013395649],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010284598,0.000117000316,0.00022798889,0.00008436335,0.00056306866,0.00020292966,0.00039292432,0.000024296238,0.0007596998],"category_scores_gemma":[0.000061747356,0.00010097962,0.000030779862,0.00048550725,0.0002904311,0.000238988,0.00047183575,0.00009726736,0.000014345223],"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":[0.00030965242,0.00015418652,0.1469122,0.00012409413,0.0003722772,0.0009073936,0.002205667,0.0015885279,0.00024972874,0.00034594233,0.3738002,0.47303015],"study_design_scores_gemma":[0.00057751813,0.00012497135,0.10135962,0.00003135223,0.0001523552,0.00008221704,0.003528002,0.8561514,0.00004551296,0.0050194245,0.03255002,0.00037760392],"about_ca_topic_score_codex":0.0034662664,"about_ca_topic_score_gemma":0.0015234632,"teacher_disagreement_score":0.8545629,"about_ca_system_score_codex":0.0000070259307,"about_ca_system_score_gemma":0.00011700606,"threshold_uncertainty_score":0.831818},"labels":[],"label_agreement":null},{"id":"W4283696359","doi":"10.1038/s41597-022-01475-3","title":"A Global Building Occupant Behavior Database","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Building Energy and Comfort Optimization","field":"Engineering","cited_by":89,"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; Carleton University","funders":"Dr B R Ambedkar National Institute of Technology Jalandhar; Università degli Studi di Perugia; Indian Institute of Technology Bombay; Università della Calabria; U.S. Department of Energy; Tongji University; Silesian University of Technology; Colorado School of Mines; RMIT University; Tsinghua University; Universidade de São Paulo; Technische Universität Wien; Aalborg Universitet; Universidade Federal de Santa Catarina; Center for the Built Environment; Swinburne University of Technology; University of Toronto; University of New South Wales; Khalifa University of Science, Technology and Research; Western Kentucky University; American Society of Heating, Refrigerating and Air-Conditioning Engineers; Beijing University of Technology; University of Texas at Austin; University of Texas at Arlington; Syddansk Universitet; National Science Foundation","keywords":"Database; Computer science; World Wide Web","score_opus":0.03695447322705658,"score_gpt":0.2720786608106723,"score_spread":0.2351241875836157,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283696359","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":[0.702877,0.0014755101,0.20269498,0.00010948235,0.023972288,0.00058524875,0.062251803,0.002260923,0.0037727524],"genre_scores_gemma":[0.9713627,0.000005066748,0.014342837,0.00003580967,0.000060410108,0.000056868306,0.013650971,0.000019260864,0.00046605463],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989998,0.00001751155,0.00012336895,0.00036920435,0.00028335242,0.00020677944],"domain_scores_gemma":[0.9985515,0.0000067199126,0.000018325536,0.001357647,0.0000115188905,0.000054311455],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045067602,0.00007916468,0.00006488365,0.00006407691,0.0004344901,0.0001491997,0.0011111812,0.000014487139,0.00040785296],"category_scores_gemma":[0.000014094117,0.00008858818,0.000016034886,0.0006391965,0.00003970299,0.00035959558,0.0011733372,0.00008799628,0.0000069088996],"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":[0.0000046965883,0.0000670886,0.0009948158,0.000013204617,0.000014931133,0.000026129619,0.000024931715,0.7211222,0.00189916,0.0029986752,0.2632975,0.009536622],"study_design_scores_gemma":[0.00017182145,0.000007878924,0.00035714498,0.0000066184116,0.000033800934,0.000037101676,0.000056095007,0.66660523,0.00027344775,0.00011040355,0.33212176,0.00021869218],"about_ca_topic_score_codex":0.000024966703,"about_ca_topic_score_gemma":0.000027205724,"teacher_disagreement_score":0.26848572,"about_ca_system_score_codex":0.00007897307,"about_ca_system_score_gemma":0.000034869405,"threshold_uncertainty_score":0.4465704},"labels":[],"label_agreement":null},{"id":"W4283792177","doi":"10.1038/s41597-022-01434-y","title":"An 8-year record of phytoplankton productivity and nutrient distributions from surface waters of Saanich Inlet","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Water Quality and Pollution Assessment","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Canada; University of Victoria","keywords":"Phytoplankton; Inlet; Nutrient; Productivity; Environmental science; Oceanography; Primary productivity; Ecology; Biology; Geology","score_opus":0.04037195568643193,"score_gpt":0.2811424661554095,"score_spread":0.24077051046897757,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283792177","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":[0.9672692,0.00001297941,0.0006523973,0.00039769395,0.0005041352,0.00016664613,0.030901184,0.000011749414,0.00008405876],"genre_scores_gemma":[0.993473,0.0000021047028,0.001447554,0.000007714991,0.000009460403,0.000003464331,0.004808794,0.0000034144782,0.00024450044],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984297,0.0002256259,0.00021892243,0.00055313087,0.00042162358,0.00015095528],"domain_scores_gemma":[0.9985009,0.000024116189,0.00012890695,0.0012685249,0.000008888613,0.00006867748],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0014477022,0.00006953877,0.00012169282,0.000021214973,0.00029039217,0.00003884855,0.0006742335,0.000015410733,0.0012349439],"category_scores_gemma":[0.000025452302,0.000065437875,0.00001543949,0.0003239866,0.00046413188,0.00037514078,0.0013313362,0.00008804259,0.000017353279],"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":[0.00017055692,0.0018004844,0.35085726,0.000053079497,0.00004757299,0.000003032667,0.004756714,0.0011804698,0.5314125,0.001026669,0.1032262,0.005465451],"study_design_scores_gemma":[0.00090889377,0.00031383484,0.2754767,0.000021566148,0.000069754235,0.0000041740764,0.002149838,0.0022762374,0.21090424,0.0044845175,0.5029461,0.00044418898],"about_ca_topic_score_codex":0.0012329264,"about_ca_topic_score_gemma":0.00023688246,"teacher_disagreement_score":0.39971986,"about_ca_system_score_codex":0.00006716514,"about_ca_system_score_gemma":0.000026326754,"threshold_uncertainty_score":0.9996781},"labels":[],"label_agreement":null},{"id":"W4284673623","doi":"10.1038/s41597-022-01503-2","title":"Fisheries dataset on moulting patterns and shell quality of American lobsters H. americanus in Atlantic Canada","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Crustacean biology and ecology","field":"Environmental Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Canadian Council on Animal Care; University of Prince Edward Island","funders":"Fisheries and Oceans Canada; Atlantic Canada Opportunities Agency; Government of Canada","keywords":"American lobster; Homarus; Fishery; Biology; Moulting; Carapace; Fishing; Crustacean; Ecology; Decapoda; Geography; Larva","score_opus":0.04093232918795222,"score_gpt":0.2710283560594465,"score_spread":0.23009602687149425,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4284673623","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":[0.9736107,0.000004574726,0.0000037584891,0.0003411953,0.00028022338,0.000084387335,0.025533855,0.000004172819,0.00013714933],"genre_scores_gemma":[0.98858386,0.0000025653114,0.00005818758,0.00036619775,0.0000035306712,0.000004224141,0.010846674,0.0000033020883,0.00013146871],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99856824,0.00018686487,0.0002185733,0.00056568993,0.00021814868,0.00024249981],"domain_scores_gemma":[0.99882203,0.0001444816,0.00014161709,0.0008394581,0.0000017806192,0.00005062499],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00087322673,0.00007543587,0.00015969944,0.00003362958,0.00022328775,0.000018538707,0.00073595316,0.000009798337,0.0013761595],"category_scores_gemma":[0.00011843428,0.00007362166,0.00000684813,0.00029739493,0.00082575047,0.00010190142,0.001919362,0.00012350568,0.00000939983],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002833693,0.000043276752,0.8859834,0.0000061962023,0.000003507231,0.000013028761,0.00015420018,0.00019600023,0.00044793775,0.0000036552085,0.11099115,0.0021293103],"study_design_scores_gemma":[0.00017619871,0.000056080586,0.9042779,0.000002241126,0.0000036281047,0.0000041989797,0.0026622054,0.0006882288,0.00003653643,0.000008191586,0.09196486,0.000119715165],"about_ca_topic_score_codex":0.78804815,"about_ca_topic_score_gemma":0.91577154,"teacher_disagreement_score":0.1277234,"about_ca_system_score_codex":0.00016400615,"about_ca_system_score_gemma":0.000055086544,"threshold_uncertainty_score":0.9995367},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"observational","genre":"dataset","about_ca_system":false,"about_ca_topic":true,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":true,"confidence":"high"}],"label_agreement":"split"},{"id":"W4284958904","doi":"10.1038/s41597-022-01519-8","title":"Author Correction: A global ensemble of ocean wave climate statistics from contemporary wave reanalysis and hindcasts","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Ocean Waves and Remote Sensing","field":"Earth and Planetary Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Environment and Climate Change Canada","funders":"","keywords":"Climatology; Statistics; Environmental science; Geology; Mathematics","score_opus":0.06996294645536501,"score_gpt":0.25679683253715496,"score_spread":0.18683388608178997,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4284958904","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":[0.7874471,0.0013238334,0.0009692026,0.00035131146,0.008957788,0.0002522435,0.19564795,0.00005494713,0.004995624],"genre_scores_gemma":[0.9662121,0.0000123005,0.0061466447,0.00004381197,0.00006335948,6.0206378e-9,0.026002059,0.000003544386,0.0015161776],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99802285,0.00016081688,0.00033239572,0.00067373976,0.00054877147,0.00026142917],"domain_scores_gemma":[0.998564,0.00012955864,0.00020717122,0.0009019645,0.000055066525,0.00014221451],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0011112588,0.00012209863,0.00023055449,0.00008753451,0.00072932226,0.00022536263,0.00032840556,0.000029485162,0.0009200079],"category_scores_gemma":[0.000086698245,0.0001075909,0.000033542317,0.00055563997,0.0002751744,0.00025168227,0.00037573182,0.0001343155,0.000018208859],"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":[0.00019756003,0.00008149025,0.045926813,0.00004805232,0.00017886251,0.00035158085,0.0012976655,0.00092644856,0.00009879918,0.00008336909,0.61413467,0.33667472],"study_design_scores_gemma":[0.0003168193,0.00010401866,0.050376583,0.000025148633,0.000111678455,0.000102785925,0.003377682,0.9041222,0.000043213597,0.0015046289,0.039663725,0.0002515578],"about_ca_topic_score_codex":0.0032802525,"about_ca_topic_score_gemma":0.0014731154,"teacher_disagreement_score":0.90319574,"about_ca_system_score_codex":0.000010009417,"about_ca_system_score_gemma":0.0001339464,"threshold_uncertainty_score":0.99999326},"labels":[],"label_agreement":null},{"id":"W4285030286","doi":"10.1038/s41597-022-01495-z","title":"The Toronto older adults gait archive: video and 3D inertial motion capture data of older adults’ walking","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Balance, Gait, and Falls Prevention","field":"Health Professions","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Vector Institute; University of Toronto; Toronto Rehabilitation Institute; University Health Network","funders":"Government of Canada; CIHR Skin Research Training Centre; AGE-WELL","keywords":"Gait; Motion capture; Physical medicine and rehabilitation; Motion (physics); Computer science; Medicine; Artificial intelligence","score_opus":0.029035931952375513,"score_gpt":0.3376554024780065,"score_spread":0.308619470525631,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285030286","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":[0.84035856,0.015266124,0.0043263547,0.0030098644,0.030773854,0.0070854397,0.09236861,0.00035232864,0.006458889],"genre_scores_gemma":[0.95799875,0.0001899199,0.00069637346,0.000204044,0.00037674312,0.000098994584,0.036064275,0.00003060427,0.0043402724],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9965203,0.00072929094,0.000572004,0.001065324,0.0006289413,0.00048413224],"domain_scores_gemma":[0.99562,0.00026492932,0.00037507867,0.0035258348,0.00010731787,0.00010683727],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0037128688,0.00015516115,0.00020316595,0.000055692173,0.0026258973,0.00007641789,0.0022415312,0.00007485929,0.00030699297],"category_scores_gemma":[0.00031902894,0.0001182577,0.000029154815,0.00023642535,0.0002352714,0.0008077252,0.0053248084,0.0005013458,0.000025137688],"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":[0.00037352496,0.0006099931,0.0045209615,0.00068697176,0.000060414914,0.0000048884567,0.020681383,0.0000010791017,0.0025250828,0.0005365467,0.8020335,0.16796567],"study_design_scores_gemma":[0.00517275,0.00006310163,0.5312619,0.001392574,0.00014410836,0.0000112818625,0.044254724,0.038175285,0.0000064865244,0.000457837,0.3785366,0.0005233365],"about_ca_topic_score_codex":0.0026911267,"about_ca_topic_score_gemma":0.0126523245,"teacher_disagreement_score":0.5267409,"about_ca_system_score_codex":0.00007374726,"about_ca_system_score_gemma":0.00017691636,"threshold_uncertainty_score":0.99867254},"labels":[],"label_agreement":null},{"id":"W4285730943","doi":"10.1038/s41597-022-01531-y","title":"Author Correction: Long-term ice phenology records spanning up to 578 years for 78 lakes around the Northern Hemisphere","year":2022,"lang":"en","type":"erratum","venue":"Scientific Data","topic":"Cryospheric studies and observations","field":"Earth and Planetary Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ministry of Environment; York University","funders":"","keywords":"Phenology; Term (time); Northern Hemisphere; Environmental science; Southern Hemisphere; Climatology; Physical geography; Oceanography; Geography; Geology; Ecology; Biology; Physics; Astronomy","score_opus":0.0749726229622267,"score_gpt":0.29066089205426177,"score_spread":0.21568826909203506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285730943","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02086192,0.0108342655,0.0013855227,0.0069064302,0.89658225,0.0023427254,0.047451388,0.0002703292,0.013365169],"genre_scores_gemma":[0.0005952749,0.00009652384,0.00036185668,0.0004266459,0.0031015906,0.000042818167,0.06381212,0.00002444412,0.9315387],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99687576,0.000093113624,0.00041714203,0.001380502,0.00060140685,0.00063207047],"domain_scores_gemma":[0.9967696,0.00038733173,0.00027773227,0.0022677307,0.00015135318,0.00014622214],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001288489,0.0002978018,0.0003657593,0.00006256464,0.0023771457,0.00076244277,0.002914075,0.00016017008,0.008861114],"category_scores_gemma":[0.000557492,0.00023921549,0.00011213164,0.0010749865,0.00030145398,0.00026491247,0.00060905644,0.00061988656,0.00036989595],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002448669,0.000010676959,0.016151896,0.000033874952,0.000067938265,0.000007679408,0.0006027462,0.0003331631,4.708612e-7,0.000002743373,0.9203244,0.06243993],"study_design_scores_gemma":[0.00009898366,0.00007067744,0.06377115,0.000045379256,0.00009036101,0.000013512063,0.0028139716,0.0033423507,1.8127409e-7,0.00004195216,0.9294155,0.00029598],"about_ca_topic_score_codex":0.0024185062,"about_ca_topic_score_gemma":0.2000009,"teacher_disagreement_score":0.91817355,"about_ca_system_score_codex":0.00003518926,"about_ca_system_score_gemma":0.00046514688,"threshold_uncertainty_score":0.99892163},"labels":[],"label_agreement":null},{"id":"W4286494955","doi":"10.1038/s41597-022-01552-7","title":"The Multilingual Picture Database","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Categorization, perception, and language","field":"Psychology","cited_by":31,"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 for Research on Brain Language and Music","funders":"Department of Education and Training; Saint Petersburg State University; Israel Science Foundation; Academy of Finland; Narodowe Centrum Nauki; National Research Foundation of Korea; Comunidad de Madrid","keywords":"Multilingualism; Computer science; Psycholinguistics; Variety (cybernetics); Field (mathematics); Value (mathematics); Linguistics; Natural language processing; Artificial intelligence; Psychology; Mathematics; Cognition","score_opus":0.06283960389950143,"score_gpt":0.36443300166592907,"score_spread":0.30159339776642763,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4286494955","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":[0.7651758,0.0052048163,0.0031253141,0.0028987434,0.08926574,0.001653808,0.08929615,0.0006881805,0.042691424],"genre_scores_gemma":[0.7606432,0.0000074879567,0.00015598653,0.00034816403,0.00055555615,0.00004815872,0.057837613,0.000026088912,0.18037775],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984283,0.00016831266,0.00016226164,0.0006328144,0.00035460637,0.00025369582],"domain_scores_gemma":[0.9965824,0.00007730584,0.000058181708,0.0031906837,0.000037707345,0.000053741558],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0016833381,0.00007793624,0.000058850135,0.00006311766,0.0021398421,0.00023869872,0.0018108882,0.00001939085,0.016699707],"category_scores_gemma":[0.00011376163,0.000057951253,0.000022838483,0.00044362733,0.00022618037,0.00014845129,0.0010693757,0.00019000079,0.0005577479],"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":[0.000025584735,0.00011028507,0.00046875418,0.0000027895785,0.000017298384,0.000015683217,0.009018926,0.000011940107,0.0011565085,0.0034395515,0.966107,0.01962567],"study_design_scores_gemma":[0.00021496532,0.000009543472,0.0027429748,7.122506e-7,0.000012620631,0.000020799987,0.011807036,0.00034549803,0.000017921442,0.00011251487,0.9846308,0.000084580555],"about_ca_topic_score_codex":0.00016349881,"about_ca_topic_score_gemma":0.00060201,"teacher_disagreement_score":0.13768633,"about_ca_system_score_codex":0.000023843448,"about_ca_system_score_gemma":0.000089293455,"threshold_uncertainty_score":0.9991592},"labels":[],"label_agreement":null},{"id":"W4286750103","doi":"10.1038/s41597-022-01544-7","title":"Single-cell RNA-seq of primary bone marrow neutrophils from female and male adult mice","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":26,"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; Rose Hills Foundation; Buck Institute for Research on Aging; Echo Foundation; McGill University; National Institutes of Health; Pew Charitable Trusts; U.S. Department of Health and Human Services","keywords":"Biology; Transcriptome; Innate immune system; Immune system; Sexual dimorphism; Bone marrow; Immunology; Cell; Cell type; RNA; Phenotype; Cell biology; Gene expression; Gene; Genetics; Endocrinology","score_opus":0.029329118770350472,"score_gpt":0.21773767739736172,"score_spread":0.18840855862701125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4286750103","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":[0.98698056,0.0017681766,0.00018749751,0.000101644044,0.0009660731,0.00014778993,0.00795722,0.000009617473,0.0018814268],"genre_scores_gemma":[0.9782804,0.00005187257,0.0022428134,0.00022550422,0.000116615054,0.0000070216756,0.013699168,0.000022859667,0.0053536925],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9984071,0.00007184954,0.0002492295,0.0007906058,0.00025623047,0.00022494164],"domain_scores_gemma":[0.9984704,0.000015775044,0.00011525181,0.0012500101,0.00006651827,0.000082043356],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034346787,0.00012889621,0.00017313141,0.000053969972,0.00024241219,0.00007868318,0.00079380855,0.00005672378,0.00019519839],"category_scores_gemma":[0.00003378589,0.00014019405,0.00004560912,0.00015559174,0.00025666054,0.000013886696,0.0010848226,0.00011113556,0.000006115695],"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":[0.00009289979,0.00024409879,0.0010413307,0.000037026955,0.00001580963,0.000007141624,0.0000764063,0.00001128002,0.97860926,0.0000066845882,0.017969415,0.0018886367],"study_design_scores_gemma":[0.0014878269,0.0003120075,0.0008667578,0.000018957739,0.0000762274,0.000030715844,0.00040162157,0.00040966945,0.85739666,0.000085353764,0.13851285,0.00040133114],"about_ca_topic_score_codex":0.00015279758,"about_ca_topic_score_gemma":0.000071511895,"teacher_disagreement_score":0.12121259,"about_ca_system_score_codex":0.000014837223,"about_ca_system_score_gemma":0.0000947009,"threshold_uncertainty_score":0.5716948},"labels":[],"label_agreement":null},{"id":"W4288068880","doi":"10.1038/s41597-022-01515-y","title":"Community established best practice recommendations for tephra studies—from collection through analysis","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Geology and Paleoclimatology Research","field":"Earth and Planetary Sciences","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 Alberta","funders":"Natural Environment Research Council; Research Councils UK; Sight Research UK","keywords":"Tephra; Metadata; Discoverability; Documentation; Standardization; Data science; Earth science; Interoperability; Computer science; Geography; Volcano; World Wide Web; Geology; Paleontology","score_opus":0.24386890989179388,"score_gpt":0.40820881212516447,"score_spread":0.16433990223337058,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4288068880","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":[0.6830758,0.0054146433,0.0030381419,0.07834358,0.01653136,0.002539229,0.18514012,0.00026283768,0.025654325],"genre_scores_gemma":[0.69146955,0.00016531805,0.018153358,0.000819954,0.00007369495,0.000052639487,0.28130692,0.000005141594,0.007953384],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9970852,0.0014879993,0.0002483749,0.0005399948,0.0003112382,0.00032720415],"domain_scores_gemma":[0.9951273,0.0029091577,0.00014382452,0.0015518282,0.00020742725,0.000060428545],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004651516,0.00009344485,0.00021641789,0.0002486492,0.006474424,0.00018735694,0.001514009,0.000042030326,0.005440634],"category_scores_gemma":[0.002115346,0.00008941074,0.000052268384,0.0026797506,0.00042645365,0.0010318443,0.00050532457,0.0005052476,0.00015441628],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001719577,0.0002668318,0.47614384,0.000012024766,0.00092602865,0.000005315277,0.0031544482,0.00092415797,0.0000027688109,0.00006194899,0.51613235,0.002198292],"study_design_scores_gemma":[0.000466499,0.0002114672,0.022194885,0.000003593912,0.00083830254,0.000018885732,0.042980015,0.015886422,0.000011268724,0.0037967672,0.91339844,0.00019346125],"about_ca_topic_score_codex":0.006090427,"about_ca_topic_score_gemma":0.077231415,"teacher_disagreement_score":0.45394897,"about_ca_system_score_codex":0.0000065804593,"about_ca_system_score_gemma":0.00016144829,"threshold_uncertainty_score":0.99546856},"labels":[],"label_agreement":null},{"id":"W4288439585","doi":"10.1038/s41597-022-01559-0","title":"The role of plant functional groups mediating climate impacts on carbon and biodiversity of alpine grasslands","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Peatlands and Wetlands Ecology","field":"Environmental Science","cited_by":23,"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":"Senter for Internasjonalisering av Utdanning; Norges Forskningsråd; Universitetet i Bergen","keywords":"Environmental science; Ecosystem; Plant community; Biomass (ecology); Ecology; Forb; Species richness; Graminoid; Biodiversity; Climate change; Growing season; Biology; Grassland","score_opus":0.015555839301691065,"score_gpt":0.20310089661832093,"score_spread":0.18754505731662985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4288439585","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":[0.9914494,0.000059612063,8.993925e-7,0.00014246388,0.0003686265,0.000065736276,0.0066638854,0.0000052826485,0.0012440982],"genre_scores_gemma":[0.9976887,0.000019604482,0.000015429352,0.000014818787,0.000010388769,0.0000018477014,0.0022169263,0.0000014772381,0.000030795378],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99903667,0.00004964952,0.00012787763,0.00027208455,0.00034101488,0.00017271689],"domain_scores_gemma":[0.9993099,0.00009446754,0.000115407005,0.0004321855,0.0000041417197,0.000043876196],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012632748,0.000051931307,0.000082750244,0.000033204553,0.00052765076,0.000020093947,0.00043549342,0.000013558901,0.00019909666],"category_scores_gemma":[0.000047994487,0.000035893154,0.000013256576,0.00016953412,0.00029258907,0.00006614381,0.0017103689,0.00007186651,0.0000047201825],"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":[0.00011624567,0.000092823626,0.9577102,0.0000064788073,0.000015135318,0.000002944927,0.00028765138,0.0001383773,0.020009026,0.00012171892,0.018634269,0.0028651087],"study_design_scores_gemma":[0.00065722095,0.00035640993,0.9341619,0.000005064752,0.000029280756,0.000014775262,0.00090963533,0.011798339,0.0019926433,0.00053591304,0.04940665,0.00013217016],"about_ca_topic_score_codex":0.00022224456,"about_ca_topic_score_gemma":0.00041107842,"teacher_disagreement_score":0.030772382,"about_ca_system_score_codex":0.000026032621,"about_ca_system_score_gemma":0.000011782198,"threshold_uncertainty_score":0.40583166},"labels":[],"label_agreement":null},{"id":"W4288684979","doi":"10.1038/s41597-022-01534-9","title":"ISARIC-COVID-19 dataset: A Prospective, Standardized, Global Dataset of Patients Hospitalized with COVID-19","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"COVID-19 Clinical Research Studies","field":"Medicine","cited_by":72,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Grand River Hospital; Misericordia Community Hospital; BC Children's Hospital; University of British Columbia; Sinai Health System; Sturgeon Community Hospital; London Health Sciences Centre; Mount Sinai Hospital; Royal Columbian Hospital; Kingston Health Sciences Centre; Joseph Brant Hospital; University of Alberta; University Health Network; St. Joseph’s Healthcare Hamilton; Alberta Children's Hospital; Red Deer Regional Hospital; Grey Nuns Community Hospital; SickKids Foundation; University of Manitoba; University of Northern British Columbia; Children's Hospital of Eastern Ontario; Vancouver General Hospital; North York General Hospital; St Joseph's Health Centre; Centre Hospitalier Universitaire de Sherbrooke; Toronto East General Hospital; Foothills Medical Centre; McMaster University; Mills Memorial Hospital; Lions Gate Hospital; Centre Hospitalier Universitaire Sainte-Justine; Ottawa Hospital; Royal Alexandra Hospital; Hôpital du Sacré-Cœur de Montréal; Centre intégré de santé et de services sociaux de Chaudière-Appalaches; Health Sciences Centre; McGill University Health Centre; Etobicoke General Hospital; Montreal Children's Hospital; Hôpital de l'Enfant-Jésus; Brantford Energy (Canada); Island Health; Sunnybrook Health Science Centre; Humber River Regional Hospital; St. Boniface Hospital; Institut universitaire de cardiologie et de pneumologie de Québec; Centre Hospitalier de l’Université de Montréal","funders":"Foreign, Commonwealth and Development Office; Medical Research Council; Kementerian Pendidikan Nasional; Public Health England; Minderoo Foundation; University of Oxford; Imperial College London; Canadian Institutes of Health Research; National Institute of General Medical Sciences; National Institute for Health and Care Research; National Heart, Lung, and Blood Institute; National Institute for Health Research Health Protection Research Unit; Wellcome Trust; Bill and Melinda Gates Foundation","keywords":"Coronavirus disease 2019 (COVID-19); Medicine; Pandemic; Emergency medicine; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); MEDLINE; Intensive care medicine; 2019-20 coronavirus outbreak; Medical emergency; Internal medicine; Outbreak; Pathology; Disease; Infectious disease (medical specialty)","score_opus":0.0842770208689757,"score_gpt":0.45181960599310755,"score_spread":0.36754258512413185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4288684979","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0110041285,0.00012717325,0.002977398,0.005648083,0.00054913916,0.0025866139,0.9768939,0.00009751585,0.00011606261],"genre_scores_gemma":[0.16342244,0.000049936094,0.0023137112,0.0074618515,0.000071976334,0.00025925436,0.8257862,0.00004209696,0.00059255894],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9916327,0.0004002783,0.00087191124,0.0023745939,0.0039121723,0.00080834754],"domain_scores_gemma":[0.9890535,0.0013912728,0.00050912425,0.0071054236,0.0004010521,0.0015396444],"candidate_categories":["metaresearch","metaepi_narrow","sts","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0059665306,0.0003474607,0.00082081254,0.0002755149,0.0013433992,0.00018626056,0.0029013532,0.000057686037,0.002731781],"category_scores_gemma":[0.064882055,0.00027178595,0.00009029872,0.0025647322,0.0021111898,0.0005215695,0.009999564,0.00048415965,0.00006460258],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0037525287,0.0013210035,0.15482548,0.000654663,0.0002839247,0.00017603015,0.00018496938,0.00006924733,0.00001902945,0.00012997646,0.8380403,0.0005428782],"study_design_scores_gemma":[0.010451019,0.0010662872,0.018597616,0.000024641966,0.0002658663,0.0000059953077,0.00024521363,0.0002964761,0.000011149722,0.0004756356,0.9682601,0.0003000058],"about_ca_topic_score_codex":0.0015270524,"about_ca_topic_score_gemma":0.00024475556,"teacher_disagreement_score":0.1524183,"about_ca_system_score_codex":0.0017851685,"about_ca_system_score_gemma":0.006935909,"threshold_uncertainty_score":0.9999734},"labels":[],"label_agreement":null},{"id":"W4289261700","doi":"10.1038/s41597-022-01517-w","title":"The United States COVID-19 Forecast Hub dataset","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"COVID-19 epidemiological studies","field":"Mathematics","cited_by":129,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University; University of British Columbia; University of Victoria; TRIUMF","funders":"Oak Ridge National Laboratory; Natural Sciences and Engineering Research Council of Canada; Quest for Intelligence, Massachusetts Institute of Technology; Plant Sciences Institute, Iowa State University; National Institutes of Health; Centers for Disease Control and Prevention; Klaus Tschira Stiftung; Center for Emerging Infectious Diseases, University of Iowa; Iowa State University; North Carolina State University; Bundesministerium für Bildung und Forschung; Council of State and Territorial Epidemiologists; Institute for Health Metrics and Evaluation; National Institute of General Medical Sciences; University of Massachusetts Amherst; Johns Hopkins Bloomberg School of Public Health; Wellcome Trust; U.S. Department of Energy; National Institute of Diabetes and Digestive and Kidney Diseases; California Institute of Technology; Eunice Kennedy Shriver National Institute of Child Health and Human Development; Bill and Melinda Gates Foundation; Los Alamos National Laboratory; Johns Hopkins University; Gordon and Betty Moore Foundation; Indiana University-Purdue University Indianapolis; U.S. Department of Homeland Security; National Nuclear Security Administration; Laboratory Directed Research and Development; National Science Foundation","keywords":"Leverage (statistics); Download; Coronavirus disease 2019 (COVID-19); Government (linguistics); Pandemic; Scale (ratio); Disease control; Computer science; Data science; Econometrics; Business; Geography; Infectious disease (medical specialty); Economics; World Wide Web; Environmental health; Medicine; Machine learning","score_opus":0.5946829767412236,"score_gpt":0.495350206423102,"score_spread":0.0993327703181216,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4289261700","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019503022,0.0010240145,0.01109891,0.09087831,0.0045437785,0.0018726126,0.8699026,0.0006387659,0.0005379612],"genre_scores_gemma":[0.033339754,0.00028511134,0.0071762153,0.02870728,0.0002990096,0.0005093457,0.9138445,0.0000926816,0.015746092],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99691355,0.0005931893,0.00043236875,0.00090096344,0.0006515099,0.00050843786],"domain_scores_gemma":[0.98748386,0.008052909,0.00021821201,0.0040015304,0.00005063444,0.00019284396],"candidate_categories":["metaresearch","sts","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.010946492,0.00015925936,0.00022280258,0.00010679516,0.004642439,0.00030842278,0.0039973757,0.00002302092,0.0010356146],"category_scores_gemma":[0.025909292,0.00009970433,0.00003956913,0.0011802487,0.00081604114,0.00015063673,0.010523753,0.00027985623,0.00011581786],"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":[0.000019084337,0.0000669891,0.00024022549,0.000028675437,0.000032470518,0.000011138184,0.00022404367,0.00018838632,0.0000072447856,0.008520539,0.99001455,0.00064663246],"study_design_scores_gemma":[0.00016219825,0.000023496736,0.000043596916,0.0000020751,0.000025861566,0.0000048611378,0.0013001809,0.0077926917,0.0000027659983,0.114737585,0.87578154,0.00012314152],"about_ca_topic_score_codex":0.00063224585,"about_ca_topic_score_gemma":0.00093126367,"teacher_disagreement_score":0.114233024,"about_ca_system_score_codex":0.00019404048,"about_ca_system_score_gemma":0.00017142328,"threshold_uncertainty_score":0.9998776},"labels":[],"label_agreement":null},{"id":"W4289545216","doi":"10.1038/s41597-022-01568-z","title":"Developing a high-resolution gridded rainfall product for Bangladesh during 1901–2018","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Precipitation Measurement and Analysis","field":"Earth and Planetary Sciences","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 Calgary","funders":"National Research Foundation of Korea","keywords":"Product (mathematics); Environmental science; Climatology; Geology; Mathematics","score_opus":0.08742541192371227,"score_gpt":0.2588237999639356,"score_spread":0.17139838804022334,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4289545216","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":[0.9495814,0.0012875462,0.007670469,0.004839918,0.010120751,0.0014600918,0.023273952,0.0002891809,0.0014767249],"genre_scores_gemma":[0.9530787,0.000004665424,0.009408888,0.000091717826,0.00023361828,0.000013091924,0.034871563,0.00000462556,0.0022931208],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979914,0.0001014843,0.0002358634,0.000731801,0.0006058002,0.0003336615],"domain_scores_gemma":[0.9989011,0.00004892341,0.000112105554,0.0008010575,0.000070161754,0.0000666248],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0024759555,0.000098750555,0.00011939009,0.00022257098,0.0016975304,0.00029692875,0.00089028367,0.000012874152,0.0018006432],"category_scores_gemma":[0.00023305672,0.0000938275,0.000040831343,0.0008180223,0.00008070565,0.00058576756,0.00018919683,0.00008366945,0.00010625431],"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":[0.00054557313,0.00023208337,0.109468505,0.0005195752,0.0005289635,0.000033098753,0.0034175466,0.03573138,0.01911245,0.0015325468,0.6883626,0.1405157],"study_design_scores_gemma":[0.0018574898,0.00009366769,0.3725726,0.000045842597,0.00018324296,0.000018922445,0.0013078849,0.100797735,0.0022059747,0.0038954383,0.5160423,0.0009788868],"about_ca_topic_score_codex":0.0002523438,"about_ca_topic_score_gemma":0.001295229,"teacher_disagreement_score":0.2631041,"about_ca_system_score_codex":0.000022917624,"about_ca_system_score_gemma":0.00015563125,"threshold_uncertainty_score":0.99960214},"labels":[],"label_agreement":null},{"id":"W4290065549","doi":"10.1038/s41597-022-01554-5","title":"A global dataset of seaweed net primary productivity","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Marine and fisheries research","field":"Environmental Science","cited_by":69,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bedford Institute of Oceanography; Fisheries and Oceans Canada","funders":"","keywords":"Primary productivity; Primary production; Productivity; Algae; Net (polyhedron); Primary (astronomy); Primary producers; Environmental science; Ecology; Biology; Mathematics; Phytoplankton; Ecosystem; Nutrient; Economics","score_opus":0.044058248072791545,"score_gpt":0.28634018294948155,"score_spread":0.24228193487669,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4290065549","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16379078,0.000035981942,0.00024879305,0.0014301983,0.0018480795,0.0010474066,0.42583436,0.000069004345,0.4056954],"genre_scores_gemma":[0.371577,0.000008342855,0.006947833,0.00055103394,0.00018016025,0.00011446259,0.5277684,0.000038632934,0.092814155],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99775827,0.000113385635,0.00016032135,0.00075520563,0.00094917207,0.0002636409],"domain_scores_gemma":[0.99719316,0.00001434693,0.00006186373,0.0026473782,0.000006492903,0.00007673707],"candidate_categories":["open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0020802035,0.00006719203,0.00009926149,0.00002399873,0.0003638918,0.000079619895,0.0024215837,0.000010885045,0.024322486],"category_scores_gemma":[0.00010132827,0.00006416772,0.000014398773,0.0010255338,0.0006076962,0.0005336819,0.015731856,0.00010419314,0.0001109454],"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":[0.00002539079,0.00016932919,0.0444164,0.000011427667,0.000004709915,0.0000064229666,0.000026064066,0.00003404177,0.0009156416,0.000022272596,0.89730185,0.05706644],"study_design_scores_gemma":[0.00010122634,0.000029117218,0.018386062,3.401764e-7,0.000004215404,0.000007736316,0.00004217692,0.0007035787,0.00003529807,0.00013485576,0.98048335,0.00007205482],"about_ca_topic_score_codex":0.0019543762,"about_ca_topic_score_gemma":0.00045092966,"teacher_disagreement_score":0.31288123,"about_ca_system_score_codex":0.00012433961,"about_ca_system_score_gemma":0.00007027656,"threshold_uncertainty_score":0.99222875},"labels":[],"label_agreement":null},{"id":"W4291020824","doi":"10.1038/s41597-022-01604-y","title":"Global dataset of species-specific inland recreational fisheries harvest for consumption","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Fish Ecology and Management Studies","field":"Environmental Science","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":"Carleton University","funders":"U.S. Geological Survey; University of Missouri","keywords":"Recreation; Fishing; Fishery; Recreational fishing; Fisheries management; Livelihood; Food security; Consumption (sociology); Ecosystem; Geography; Landlocked country; Ecosystem services; Environmental resource management; Natural resource economics; Agriculture; Environmental science; Ecology; Biology; Economics","score_opus":0.08465527016480735,"score_gpt":0.27953319603743176,"score_spread":0.19487792587262442,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4291020824","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21483788,0.0001662187,0.0046152016,0.0028995452,0.0050686295,0.0015961967,0.74887544,0.00007133085,0.02186953],"genre_scores_gemma":[0.30835554,0.00016784342,0.015714614,0.0010268376,0.00014950713,0.00039972004,0.6329897,0.000024282803,0.041171964],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99881274,0.00004504705,0.00018501913,0.0005043016,0.00028758426,0.00016529497],"domain_scores_gemma":[0.9990156,0.000058856745,0.00010116745,0.00079039135,0.0000071725494,0.00002677098],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009921759,0.000069156384,0.00009579673,0.000025677407,0.0008128463,0.00005849688,0.00088335783,0.000013442918,0.010239585],"category_scores_gemma":[0.00006848949,0.000069569855,0.000015990781,0.00023946403,0.00073681877,0.00042971794,0.0027520605,0.000036552927,0.00011564924],"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":[0.000026682459,0.00006135853,0.20195274,0.0000075524827,0.000010990501,7.3286805e-7,0.000022606275,0.00006504236,0.000034625766,0.0006617976,0.7967606,0.00039525452],"study_design_scores_gemma":[0.00015581005,0.000020724992,0.35620987,0.0000010138912,0.000009241486,0.0000010923051,0.00008570772,0.00014438387,0.0000068599993,0.0004688025,0.6428467,0.000049765695],"about_ca_topic_score_codex":0.000028104201,"about_ca_topic_score_gemma":0.0007856369,"teacher_disagreement_score":0.15425713,"about_ca_system_score_codex":0.00008413169,"about_ca_system_score_gemma":0.000011204228,"threshold_uncertainty_score":0.9906652},"labels":[],"label_agreement":null},{"id":"W4291021452","doi":"10.1038/s41597-022-01608-8","title":"BRAX, Brazilian labeled chest x-ray dataset","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":43,"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","funders":"National Institutes of Health; Sociedade Beneficente Israelita Brasileira Albert Einstein; National Institute of Biomedical Imaging and Bioengineering; U.S. Department of Health and Human Services","keywords":"Computer science; Radiology; Radiography; Medical physics; Artificial intelligence; Medicine","score_opus":0.08167703993095068,"score_gpt":0.361811452426393,"score_spread":0.28013441249544235,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4291021452","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.103811264,0.0011634959,0.0001976864,0.20366064,0.013936907,0.0024153525,0.6728041,0.00082801626,0.0011825276],"genre_scores_gemma":[0.1775566,0.000013515593,0.0031405531,0.039416645,0.00041561658,0.00009375643,0.7617348,0.00008596313,0.017542576],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99693334,0.00010773369,0.0002865516,0.001293954,0.00095651374,0.00042189087],"domain_scores_gemma":[0.9938339,0.00016558958,0.00009523114,0.0056181084,0.000055454337,0.00023169146],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002390236,0.00015284074,0.00023772837,0.00026379828,0.00082826614,0.00025934732,0.0019277219,0.000031238178,0.007163635],"category_scores_gemma":[0.0008508727,0.00015345473,0.000037568683,0.0012154661,0.00030139,0.00034268814,0.003667048,0.0003355273,0.0009106054],"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":[0.000027918673,0.00038021893,0.00070359313,0.000055109595,0.000025682424,0.000097889446,0.00011173683,0.000020541407,0.0062897205,0.000031537606,0.9881604,0.0040956964],"study_design_scores_gemma":[0.0008569492,0.000060595456,0.0025724103,0.000027706414,0.00009072221,0.000028966717,0.00014786368,0.00166547,0.00045751643,0.000029353036,0.99389905,0.00016337667],"about_ca_topic_score_codex":0.00019927285,"about_ca_topic_score_gemma":0.00013403736,"teacher_disagreement_score":0.164244,"about_ca_system_score_codex":0.00013678438,"about_ca_system_score_gemma":0.0006017714,"threshold_uncertainty_score":0.9998673},"labels":[],"label_agreement":null},{"id":"W4292182021","doi":"10.1038/s41597-022-01579-w","title":"Fundamental social motives measured across forty-two cultures in two waves","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Cultural Differences and Values","field":"Psychology","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; University of Waterloo","funders":"Akademie Věd České Republiky; Universidad de La Frontera; Grantová Agentura České Republiky; Fundação de Amparo à Pesquisa do Estado de São Paulo; Aberystwyth University; National Science Foundation","keywords":"Feminism; Sociology; Geography; Gender studies","score_opus":0.2643450644218393,"score_gpt":0.49003977297467755,"score_spread":0.22569470855283824,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4292182021","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":[0.98129135,0.00034941477,0.0000057848592,0.00037901266,0.0040433654,0.00024067213,0.010675875,0.00005379297,0.002960706],"genre_scores_gemma":[0.97759354,0.0000010980219,0.000052635285,0.00009288402,0.0001712169,0.000038869894,0.0050279517,0.000010312352,0.017011516],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9976151,0.00023994547,0.00025143372,0.00089225365,0.0005026341,0.00049861363],"domain_scores_gemma":[0.9990067,0.00002632371,0.00009434443,0.00078204065,0.000031013984,0.000059563994],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0011352262,0.00014753013,0.00019194045,0.000063158535,0.0012587862,0.00040400453,0.00149713,0.000023340655,0.00413744],"category_scores_gemma":[0.00003528988,0.00011928986,0.00006387334,0.00047941785,0.00037420337,0.00031392468,0.0016015999,0.0002529708,0.0001449062],"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":[0.0002084051,0.0010164423,0.06838476,0.000020020962,0.00015159852,0.000060869555,0.11285589,0.0000202692,0.012613477,0.0070731007,0.7643733,0.03322184],"study_design_scores_gemma":[0.0028801507,0.00008015638,0.64930624,0.000013489431,0.00003111096,0.000030038125,0.11331947,0.00037619623,0.00016889027,0.0035969608,0.22965677,0.00054053677],"about_ca_topic_score_codex":0.0009130685,"about_ca_topic_score_gemma":0.0034230852,"teacher_disagreement_score":0.5809215,"about_ca_system_score_codex":0.000068240675,"about_ca_system_score_gemma":0.000030598752,"threshold_uncertainty_score":0.9967729},"labels":[],"label_agreement":null},{"id":"W4293090388","doi":"10.1038/s41597-022-01624-8","title":"A multi-scale probabilistic atlas of the human connectome","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":25,"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 Sherbrooke","funders":"Centre d'Imagerie BioMédicale; Université de Lausanne; Centre Hospitalier Universitaire Vaudois; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"Atlas (anatomy); Connectome; Scale (ratio); Computer science; Probabilistic logic; Data science; Biology; Artificial intelligence; Geography; Neuroscience; Cartography; Functional connectivity; Paleontology","score_opus":0.14059844892235812,"score_gpt":0.31754636454830976,"score_spread":0.17694791562595164,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293090388","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":[0.9772857,0.00004832127,0.00007288265,0.003918598,0.005333187,0.00083790853,0.010802997,0.00009858799,0.0016018247],"genre_scores_gemma":[0.9918004,2.070385e-7,0.00013974494,0.00035616214,0.000025954894,0.000045894725,0.00009081453,0.000009990965,0.0075307772],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99761003,0.00028106698,0.0001971101,0.0009592193,0.00073229545,0.00022026536],"domain_scores_gemma":[0.9961995,0.0011963935,0.00012949006,0.0023935128,0.000047627283,0.000033482505],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0012335735,0.00009256873,0.00012641455,0.000079381774,0.0019679954,0.00008412844,0.0025015716,0.000011397099,0.00035631616],"category_scores_gemma":[0.00802063,0.00007015269,0.00004831352,0.0010197038,0.0009739165,0.0001896364,0.0055884086,0.0001813309,0.000041389398],"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":[0.000009243863,0.00038433966,0.0017054904,0.000030802785,0.000006725559,0.0000029497633,0.00051923824,0.00029156727,0.83706445,0.0020765746,0.1577328,0.0001758337],"study_design_scores_gemma":[0.0017359979,0.00020064139,0.03669498,0.00004055411,0.000072691626,0.00007847768,0.0014245227,0.02358744,0.13903248,0.007103627,0.7893819,0.0006466727],"about_ca_topic_score_codex":0.000040090286,"about_ca_topic_score_gemma":0.00022506455,"teacher_disagreement_score":0.69803196,"about_ca_system_score_codex":0.00005848652,"about_ca_system_score_gemma":0.00010383029,"threshold_uncertainty_score":0.9993313},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"bench_or_experimental","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W4293103396","doi":"10.1038/s41597-022-01571-4","title":"qMRI-BIDS: An extension to the brain imaging data structure for quantitative magnetic resonance imaging data","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Medical Imaging Techniques and Applications","field":"Medicine","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; Polytechnique Montréal; Montreal Heart Institute","funders":"Biotechnology and Biological Sciences Research Council; Canada First Research Excellence Fund; Fonds De La Recherche Scientifique - FNRS; Research Councils UK; International Society for Magnetic Resonance in Medicine; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Wellcome Trust; Directorate for Biological Sciences; Canadian Open Neuroscience Platform; Wellcome","keywords":"Extension (predicate logic); Magnetic resonance imaging; Functional magnetic resonance imaging; Nuclear magnetic resonance; Computer science; Information retrieval; Physics; Neuroscience; Psychology; Medicine; Radiology","score_opus":0.12701113299853875,"score_gpt":0.4141679176153345,"score_spread":0.2871567846167957,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293103396","genre_codex":"commentary","genre_gemma":"methods","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":[0.009456666,0.009697345,0.17255417,0.460907,0.0030870766,0.0066194213,0.33669445,0.0007153862,0.00026846692],"genre_scores_gemma":[0.08710071,0.000033353608,0.5294637,0.020229127,0.0006402773,0.00025447013,0.357829,0.00012823589,0.0043211114],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99616945,0.00012881418,0.0003543047,0.0021494091,0.0007648612,0.00043315435],"domain_scores_gemma":[0.98393023,0.00024910187,0.00010915324,0.015337952,0.00014532082,0.00022826139],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0043648994,0.00017150895,0.00021307559,0.00013799341,0.0012463725,0.0003438574,0.0072676083,0.000016385735,0.00042576148],"category_scores_gemma":[0.0021004507,0.00012916833,0.000020500946,0.00084693136,0.00039719374,0.00073769485,0.010882293,0.00036776075,0.000020322375],"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":[0.00003203951,0.00007088931,0.00012610083,0.000018332714,0.0000031161737,0.000010149691,0.00016970691,0.000001902076,0.012150505,0.00065909815,0.8846755,0.10208267],"study_design_scores_gemma":[0.0002555203,0.00003597995,0.0005022086,0.00004540534,0.000053861466,0.000056622855,0.0006958343,0.28330928,0.00007398036,0.0008217802,0.71402675,0.00012278977],"about_ca_topic_score_codex":0.00014161885,"about_ca_topic_score_gemma":0.00009422594,"teacher_disagreement_score":0.44067788,"about_ca_system_score_codex":0.00004340791,"about_ca_system_score_gemma":0.00027102517,"threshold_uncertainty_score":0.99810356},"labels":[],"label_agreement":null},{"id":"W4293321971","doi":"10.1038/s41597-022-01633-7","title":"Real-world behavioral dataset from two fully remote smartphone-based randomized clinical trials for depression","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Digital Mental Health Interventions","field":"Psychology","cited_by":20,"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; University of Toronto; Vector Institute; Centre for Addiction and Mental Health","funders":"National Institute of Mental Health; U.S. Department of Health and Human Services","keywords":"Mental health; Digital health; Anxiety; Mood; Randomized controlled trial; Health care; Phone; Depression (economics); Telemedicine; Computer science; Applied psychology; Psychology; Medicine; Psychiatry","score_opus":0.4865865810851913,"score_gpt":0.5961037204382227,"score_spread":0.10951713935303137,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293321971","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04714894,0.00027475052,0.0058289133,0.0013320795,0.045088448,0.004441677,0.8944496,0.0001748956,0.0012606933],"genre_scores_gemma":[0.19657125,0.0000014214611,0.009360853,0.00052083883,0.00049990497,0.0005431678,0.7772253,0.00006381021,0.015213425],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98882854,0.005476631,0.002573176,0.0018896708,0.00065435,0.000577605],"domain_scores_gemma":[0.98885113,0.004963248,0.0010056888,0.0047921804,0.00007047115,0.00031727605],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.04449496,0.00022976908,0.0010496766,0.00031535217,0.00082439074,0.00038384597,0.0026062808,0.00006347343,0.0074205357],"category_scores_gemma":[0.0022324459,0.0002077642,0.00046420543,0.0005330708,0.00052176486,0.00037818513,0.0018344481,0.00038228408,0.0005695643],"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":[0.033396576,0.0011234436,0.0002445633,0.000014145118,0.00007492338,0.000016166068,0.00003673074,0.00000438795,0.000043515807,0.00025779777,0.84599674,0.11879103],"study_design_scores_gemma":[0.17422612,0.00028333723,0.00058195414,0.00009788134,0.00053667516,0.000004299936,0.00016237005,0.005581606,0.0001696796,0.0047434657,0.8132116,0.00040098306],"about_ca_topic_score_codex":0.0043656514,"about_ca_topic_score_gemma":0.0023571788,"teacher_disagreement_score":0.1494223,"about_ca_system_score_codex":0.00011227388,"about_ca_system_score_gemma":0.00025777615,"threshold_uncertainty_score":0.9934868},"labels":[],"label_agreement":null},{"id":"W4293463483","doi":"10.1038/s41597-022-01625-7","title":"Le Petit Prince multilingual naturalistic fMRI corpus","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Neurobiology of Language and Bilingualism","field":"Neuroscience","cited_by":44,"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":"Office of Naval Research; National Institute on Aging; Multidisciplinary University Research Initiative; Jiangsu University; National Institutes of Health; National Science Foundation; Jiangsu Normal University; New York University Abu Dhabi; Agence Nationale de la Recherche","keywords":"Functional magnetic resonance imaging; Generalizability theory; Computer science; Psychology; Active listening; Functional neuroimaging; Neuroimaging; Cognitive neuroscience; Cognitive psychology; Cognition; Communication","score_opus":0.07188631091391356,"score_gpt":0.31624786866279,"score_spread":0.2443615577488764,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293463483","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":[0.9814145,0.0001962642,0.000015599997,0.001229075,0.0076754256,0.00033259392,0.0058820867,0.00024368516,0.0030107636],"genre_scores_gemma":[0.9801985,0.000002888573,0.00021730245,0.0009474398,0.00009863745,0.000010499299,0.001147527,0.000016430351,0.017360745],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99717027,0.00027772188,0.00023505995,0.0014241171,0.00048252093,0.00041030595],"domain_scores_gemma":[0.9973838,0.00025097176,0.000120057404,0.002125835,0.000031110678,0.00008825228],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0009556716,0.00013654941,0.00014118248,0.0001304153,0.0015230352,0.00021834177,0.0031436738,0.000028657423,0.0004980888],"category_scores_gemma":[0.0016708112,0.00013044696,0.00004087113,0.00056817493,0.0006378675,0.00026980805,0.003563897,0.00040575396,0.00019727909],"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":[0.00003609852,0.0002311523,0.00005196069,0.000014877807,0.0000035699125,0.0017099768,0.00057198183,0.000045390738,0.9615429,0.0020893943,0.028782759,0.0049199546],"study_design_scores_gemma":[0.0004951777,0.000057127803,0.000055451932,0.000006353642,0.000012885137,0.0010767131,0.00035285795,0.0010954431,0.16159405,0.00054099405,0.8343932,0.00031971344],"about_ca_topic_score_codex":0.00006343797,"about_ca_topic_score_gemma":0.00008151602,"teacher_disagreement_score":0.8056105,"about_ca_system_score_codex":0.000023083361,"about_ca_system_score_gemma":0.00031845047,"threshold_uncertainty_score":0.99977684},"labels":[],"label_agreement":null},{"id":"W4293463901","doi":"10.1038/s41597-022-01645-3","title":"Probabilistic atlas for the language network based on precision fMRI data from &gt;800 individuals","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Neurobiology of Language and Bilingualism","field":"Neuroscience","cited_by":149,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"National Institute on Deafness and Other Communication Disorders; Eunice Kennedy Shriver National Institute of Child Health and Human Development; Simons Foundation; U.S. Department of Health and Human Services","keywords":"Interpretability; Computer science; Probabilistic logic; Voxel; Artificial intelligence; Atlas (anatomy); Natural language processing; Machine learning","score_opus":0.12054851064406184,"score_gpt":0.3402758178060862,"score_spread":0.21972730716202432,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293463901","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":[0.59203345,0.0012859538,0.0017901991,0.0074237334,0.021064868,0.005578937,0.36916968,0.00049826485,0.0011549344],"genre_scores_gemma":[0.93043554,0.000006731306,0.0017776034,0.006265074,0.0010323772,0.00018291223,0.055470727,0.0000625001,0.004766524],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99581003,0.0005447887,0.0003229268,0.0020956288,0.0007260007,0.0005006321],"domain_scores_gemma":[0.987832,0.004535615,0.00018950363,0.0073419427,0.000025083902,0.00007585898],"candidate_categories":["sts","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0038123033,0.00019220111,0.00019354845,0.000085181935,0.0018892853,0.00042588738,0.008466874,0.000045913454,0.0010422767],"category_scores_gemma":[0.0046455734,0.00013000511,0.000049768587,0.0006678541,0.00044423848,0.00026817629,0.0054146037,0.0003387108,0.00012639583],"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":[0.00014574533,0.00030652745,0.00008470214,0.000014041565,0.000012535734,0.00012736727,0.00062445796,0.0028715613,0.03028375,0.00013733,0.9543848,0.011007199],"study_design_scores_gemma":[0.0008489689,0.00018834948,0.00016074828,0.00003112701,0.000095757685,0.000027819597,0.0003216905,0.12824899,0.004507177,0.0015029311,0.86371,0.00035644657],"about_ca_topic_score_codex":0.000042420783,"about_ca_topic_score_gemma":0.00009051144,"teacher_disagreement_score":0.33840212,"about_ca_system_score_codex":0.00002576551,"about_ca_system_score_gemma":0.00017862795,"threshold_uncertainty_score":0.9998709},"labels":[],"label_agreement":null},{"id":"W4295367167","doi":"10.1038/s41597-022-01665-z","title":"A georeferenced rRNA amplicon database of aquatic microbiomes from South America","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Microbial Community Ecology and Physiology","field":"Environmental Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"Agencia Santafesina de Ciencia, Tecnología e Innovación; Consejo Nacional de Investigaciones Científicas y Técnicas; Agencia Nacional de Promoción Científica y Tecnológica; Fundação de Amparo à Pesquisa do Estado de São Paulo","keywords":"Georeference; Ecology; Geography; Microbiome; Biology; Biodiversity; Database; Physical geography; Computer science; Bioinformatics","score_opus":0.0461665178413495,"score_gpt":0.25641245677011926,"score_spread":0.21024593892876975,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4295367167","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":[0.96893454,0.000044696997,0.0002919438,0.00018018467,0.00068124465,0.00018831297,0.028733505,0.000024781782,0.0009207954],"genre_scores_gemma":[0.9602986,0.0000026111434,0.0012392234,0.00024157228,0.000008778554,0.00000927595,0.037159037,0.0000072558846,0.0010336356],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99840945,0.00034199576,0.00022470889,0.00059967424,0.00017165385,0.00025252774],"domain_scores_gemma":[0.99703074,0.0001278431,0.00016990674,0.0026094522,0.0000043694945,0.000057723057],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0006144667,0.00010298844,0.00017928028,0.000060908867,0.00065927143,0.000030630225,0.0028518613,0.000025262978,0.044268154],"category_scores_gemma":[0.00007689375,0.000101774946,0.000028755989,0.0005248439,0.0010195742,0.0001937725,0.00762239,0.00023545927,0.0008527362],"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":[0.000039090402,0.00021356645,0.0026305853,0.0000049812515,0.000019674342,0.000002284722,0.0011872931,0.00007878734,0.7714317,0.000022269263,0.22189581,0.002473952],"study_design_scores_gemma":[0.0013370385,0.0003111773,0.029085726,0.0000248825,0.00013435657,0.000011978682,0.0037714986,0.0057719857,0.014665194,0.0056559616,0.93837744,0.000852782],"about_ca_topic_score_codex":0.0028777127,"about_ca_topic_score_gemma":0.0008632796,"teacher_disagreement_score":0.7567665,"about_ca_system_score_codex":0.00004351729,"about_ca_system_score_gemma":0.000042448395,"threshold_uncertainty_score":0.9999252},"labels":[],"label_agreement":null},{"id":"W4295426917","doi":"10.1038/s41597-022-01655-1","title":"Sharkipedia: a curated open access database of shark and ray life history traits and abundance time-series","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Ichthyology and Marine Biology","field":"Environmental Science","cited_by":29,"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; Dalhousie University","funders":"Save Our Seas Foundation; California Department of Fish and Wildlife; National Science Foundation","keywords":"Macroevolution; Biology; Macroecology; IUCN Red List; Database; Threatened species; Population; Ecology; Biodiversity; Phylogenetics; Computer science","score_opus":0.06562540695180588,"score_gpt":0.2972119327077994,"score_spread":0.2315865257559935,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4295426917","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":[0.96455914,0.0023230626,0.00005150167,0.0013223962,0.0018456399,0.0009703207,0.014908401,0.000058374753,0.013961156],"genre_scores_gemma":[0.90198845,0.00021488532,0.0038382555,0.0018216884,0.00009104724,0.00015035945,0.015025573,0.000042766962,0.07682699],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985761,0.00012720085,0.00017932156,0.00075781124,0.00016056,0.00019898474],"domain_scores_gemma":[0.9990878,0.000044649503,0.000100000085,0.0006594684,0.0000073992487,0.000100699064],"candidate_categories":["open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001247946,0.00009572115,0.00016286613,0.000046656736,0.00037062087,0.000099791934,0.0026648545,0.00002802723,0.015696898],"category_scores_gemma":[0.0001734695,0.00009043964,0.000007657572,0.00022616582,0.0013468453,0.0017775102,0.020691637,0.00012411147,0.00007767709],"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":[0.00014989593,0.0001073151,0.007892655,0.000023358027,0.000019296554,0.000011969232,0.00034601617,0.0000128038255,0.025461867,0.00017924981,0.9633172,0.0024783418],"study_design_scores_gemma":[0.00045500987,0.000073579475,0.0809698,0.0000055624537,0.000026901525,0.000025958725,0.0000838707,0.00086947443,0.00016419907,0.00013940438,0.91699594,0.00019026296],"about_ca_topic_score_codex":0.00040953775,"about_ca_topic_score_gemma":0.0003541167,"teacher_disagreement_score":0.07307715,"about_ca_system_score_codex":0.000046357076,"about_ca_system_score_gemma":0.00008954171,"threshold_uncertainty_score":0.9872288},"labels":[],"label_agreement":null},{"id":"W4296031138","doi":"10.1038/s41597-022-01682-y","title":"An Open MRI Dataset For Multiscale Neuroscience","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":111,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Queen's University; McGill University; Montreal Neurological Institute and Hospital","funders":"Centre Azrieli de recherche sur l'autisme, Institut et Hôpital Neurologiques de Montréal; Canadian Institutes of Health Research; National Institute of Biomedical Imaging and Bioengineering; Fonds de Recherche du Québec - Santé; Canadian Open Neuroscience Platform; Health Canada; Institute for Basic Science; National Institute of Mental Health; Hospital for Sick Children; National Research Foundation of Korea; Inha University; National Institutes of Health; Sick Kids Foundation; Canada First Research Excellence Fund; Canada Research Chairs; National Research Foundation; Natural Sciences and Engineering Research Council of Canada; Institute for Information and Communications Technology Promotion; Government of Canada; Savoy Foundation; China Scholarship Council; Ministry of Science and ICT, South Korea; Fondation Brain Canada; McGill University","keywords":"Open science; Neuroscience; Data science; Neuroinformatics; Computer science; Psychology; Physics","score_opus":0.24469456429015796,"score_gpt":0.3971177424460014,"score_spread":0.15242317815584344,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4296031138","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012997442,0.000033479813,0.0059024235,0.014517032,0.014195868,0.002652319,0.9487712,0.00017701942,0.0007532252],"genre_scores_gemma":[0.82765615,0.0000072389503,0.009357352,0.03639449,0.00040495596,0.0014960762,0.10494474,0.000113040616,0.019625932],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9959971,0.00023809215,0.000186795,0.0024458636,0.0007225192,0.00040966706],"domain_scores_gemma":[0.9946278,0.0012707075,0.00009835523,0.0038506845,0.00003439739,0.00011807091],"candidate_categories":["sts","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0027663042,0.00012740903,0.00013861431,0.00012315968,0.0041657193,0.0012125614,0.009397538,0.000011918339,0.00025345397],"category_scores_gemma":[0.0072413282,0.00012768866,0.000017549697,0.00092760916,0.0005817102,0.0023938527,0.012734539,0.00014768736,0.00005893571],"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":[0.000034180193,0.00024135885,0.00004734052,0.000004430385,8.122961e-7,0.0000061240685,0.000058644393,0.0003533827,0.1531971,0.00082223635,0.8438833,0.0013511174],"study_design_scores_gemma":[0.00033074906,0.00016588657,0.00027579616,0.0000013355315,0.000005869009,0.000020316422,0.00013138902,0.039863557,0.0061920388,0.0008087588,0.9520337,0.00017058162],"about_ca_topic_score_codex":0.000057209312,"about_ca_topic_score_gemma":0.00012456105,"teacher_disagreement_score":0.8438265,"about_ca_system_score_codex":0.00004631633,"about_ca_system_score_gemma":0.00016639351,"threshold_uncertainty_score":0.9998243},"labels":[],"label_agreement":null},{"id":"W4296407701","doi":"10.1038/s41597-022-01672-0","title":"Publisher Correction: Fundamental social motives measured across forty-two cultures in two waves","year":2022,"lang":"en","type":"erratum","venue":"Scientific Data","topic":"Cultural Differences and Values","field":"Psychology","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":"Toronto Metropolitan University; University of Waterloo","funders":"","keywords":"Geography; Sociology; Anthropology","score_opus":0.2000200098705693,"score_gpt":0.4606010152912551,"score_spread":0.26058100542068574,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4296407701","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012627619,0.0028125325,0.0000057505677,0.0007381755,0.8125677,0.00085098314,0.02076121,0.00022686447,0.14940916],"genre_scores_gemma":[0.020199807,0.000017621876,0.000018214194,0.00011471281,0.0026582226,0.00009409408,0.09647403,0.000047184203,0.8803761],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9945653,0.0004501097,0.0005980631,0.0022874922,0.0011557719,0.0009432381],"domain_scores_gemma":[0.99744725,0.000049321716,0.00038210617,0.0018502783,0.00014152688,0.00012951822],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0016925887,0.00049356365,0.00062488636,0.00021695967,0.0015790926,0.0027078001,0.003331627,0.00026352747,0.015819216],"category_scores_gemma":[0.00018337676,0.0004048789,0.00020644533,0.0010558933,0.00078471977,0.0010268736,0.002487575,0.0016101277,0.00025223987],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004741493,0.0002552026,0.0014524969,0.000024336136,0.00012814604,0.000024293411,0.011828934,7.891268e-7,0.00002201541,0.00014862686,0.97882926,0.007238504],"study_design_scores_gemma":[0.0008096948,0.000034820994,0.04737215,0.00004891094,0.00004963836,0.00002188586,0.02313023,0.000060696297,0.000001050992,0.0005631376,0.92740875,0.0004990252],"about_ca_topic_score_codex":0.0028928015,"about_ca_topic_score_gemma":0.02178527,"teacher_disagreement_score":0.80990946,"about_ca_system_score_codex":0.000246501,"about_ca_system_score_gemma":0.00019965251,"threshold_uncertainty_score":0.9998403},"labels":[],"label_agreement":null},{"id":"W4298394231","doi":"10.1038/s41597-022-01716-5","title":"Niche deconvolution of the glioblastoma proteome reveals a distinct infiltrative phenotype within the proneural transcriptomic subgroup","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Glioma Diagnosis and Treatment","field":"Medicine","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":"Princess Margaret Cancer Centre; University of Toronto; University Health Network","funders":"Canadian Institutes of Health Research; Terry Fox Foundation; Government of Canada; Princess Margaret Cancer Foundation","keywords":"Biology; Phenotype; Transcriptome; Glioblastoma; MYB; Cancer research; Glioma; Mesenchymal stem cell; Gene expression profiling; Gene; Transcription factor; Gene expression; Cell biology; Genetics","score_opus":0.04000432322437747,"score_gpt":0.280134834045855,"score_spread":0.24013051082147752,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4298394231","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":[0.99166363,0.00028530764,0.000015409796,0.002400652,0.0010601378,0.0019380397,0.0024513751,0.000025770876,0.00015964246],"genre_scores_gemma":[0.99824756,7.565279e-7,0.0000995929,0.000092263144,0.000035193054,0.00024691553,0.00055519014,0.00001292357,0.00070957764],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99803185,0.00024101142,0.0003397267,0.00052979914,0.00063900347,0.0002186336],"domain_scores_gemma":[0.9975929,0.000066350694,0.00023189496,0.001972593,0.00007796863,0.000058278034],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013324992,0.00013445302,0.00020150126,0.000071831615,0.000725302,0.000066527165,0.00095361256,0.0000217711,0.00021706951],"category_scores_gemma":[0.00022502031,0.000070264316,0.00008418189,0.00085840287,0.0004746692,0.00014968554,0.00053300936,0.00023324385,0.000016670376],"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":[0.001947081,0.004356734,0.12641114,0.00040990638,0.00070671266,0.00008072757,0.013819411,0.0001674855,0.6485596,0.004747644,0.19392462,0.0048689647],"study_design_scores_gemma":[0.0074176006,0.0021874334,0.8102284,0.00037849232,0.001490802,0.00047103467,0.0052139345,0.009731024,0.12522925,0.0033910142,0.033609327,0.0006516735],"about_ca_topic_score_codex":0.00009191412,"about_ca_topic_score_gemma":0.00041861227,"teacher_disagreement_score":0.68381727,"about_ca_system_score_codex":0.00010194732,"about_ca_system_score_gemma":0.00024325754,"threshold_uncertainty_score":0.55785096},"labels":[],"label_agreement":null},{"id":"W4301399201","doi":"10.1038/s41597-022-01704-9","title":"A comprehensive database of amphibian heat tolerance","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Species Distribution and Climate Change","field":"Environmental Science","cited_by":56,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"National Research, Development and Innovation Office; Agencia Nacional de Investigación y Desarrollo; Deutsches Zentrum für integrative Biodiversitätsforschung Halle-Jena-Leipzig; National Natural Science Foundation of China; University of Queensland; Australian Research Council; University of New South Wales; Department of Education and Training; Deutsche Forschungsgemeinschaft","keywords":"Ectotherm; Amphibian; Evolvability; Trait; Vulnerability (computing); Resource (disambiguation); Ecology; Biology; Environmental science; Environmental resource management; Computer science; Evolutionary biology","score_opus":0.08464849075418321,"score_gpt":0.2873495062304601,"score_spread":0.20270101547627692,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4301399201","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":[0.90869635,0.00023705154,0.0000748632,0.0006367736,0.001716102,0.00029303084,0.07061867,0.00005096143,0.017676199],"genre_scores_gemma":[0.9740172,0.000012470659,0.00021158256,0.00037685645,0.000016014812,0.00001923864,0.022697233,0.000008864484,0.002640534],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99845797,0.000051344625,0.0001652316,0.0005463091,0.00056757,0.00021155231],"domain_scores_gemma":[0.9981486,0.000019359755,0.000048308553,0.0016988169,0.000010547414,0.000074345015],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00040417985,0.000071990304,0.00009664837,0.000029600713,0.00045823108,0.000050937877,0.0013751036,0.000009211184,0.17303129],"category_scores_gemma":[0.000024496192,0.000073416995,0.000023882814,0.0006308745,0.0004623102,0.00028004675,0.0040707476,0.00008010461,0.0008265182],"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":[0.000015588772,0.00016761625,0.0033688496,0.000012739718,0.0000034329476,0.000007039945,0.00016251444,0.00012008126,0.06753386,0.00022143431,0.9275662,0.00082064426],"study_design_scores_gemma":[0.0002263215,0.000019378213,0.013495436,0.000003566164,0.0000058211403,0.000009007795,0.0019017613,0.0012855618,0.0015621556,0.000023867444,0.98135996,0.00010716513],"about_ca_topic_score_codex":0.00023688091,"about_ca_topic_score_gemma":0.00023498028,"teacher_disagreement_score":0.17220478,"about_ca_system_score_codex":0.00014465596,"about_ca_system_score_gemma":0.000014470866,"threshold_uncertainty_score":0.9999515},"labels":[],"label_agreement":null},{"id":"W4303984248","doi":"10.1038/s41597-022-01693-9","title":"Long-term annual soil nitrogen surplus across Europe (1850–2019)","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Soil and Water Nutrient Dynamics","field":"Environmental Science","cited_by":48,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Bundesministerium für Bildung und Forschung","keywords":"Agriculture; Water Framework Directive; Environmental science; Term (time); Eutrophication; Soil water; Scale (ratio); Equator; Water quality; Natural resource economics; Environmental resource management; Hydrology (agriculture); Geography; Nutrient; Economics; Ecology; Soil science; Latitude; Biology","score_opus":0.02268357152617,"score_gpt":0.2624966884403882,"score_spread":0.2398131169142182,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4303984248","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":[0.97513556,0.0000697611,0.00008664001,0.00023391366,0.0032390635,0.00019146314,0.019206533,0.00010526029,0.0017318001],"genre_scores_gemma":[0.9651227,0.000010298241,0.00016543762,0.00025326468,0.00010167301,0.000020807467,0.014746231,0.000041498297,0.019538097],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99669534,0.00012853292,0.00027546668,0.0012301807,0.0009902704,0.0006802055],"domain_scores_gemma":[0.997182,0.000025527408,0.00010472859,0.0024853996,0.000018177952,0.00018417019],"candidate_categories":["sts","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0016547268,0.00017911958,0.00014779842,0.000047245678,0.00144885,0.0003490068,0.003507895,0.000029557264,0.0013458269],"category_scores_gemma":[0.00005117005,0.00017023896,0.000045920446,0.0010339194,0.0006583905,0.00080096786,0.011415196,0.0002321589,0.0027577875],"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":[0.000027070924,0.0002226572,0.75626767,0.000006199639,0.000012453835,0.00009153781,0.00090237934,0.00058058393,0.00020526076,0.000011447956,0.2298257,0.011847031],"study_design_scores_gemma":[0.0012306367,0.00012817832,0.2644816,0.000010413491,0.000047028643,0.00016877128,0.0006646374,0.0078120874,0.0004377399,0.0017564112,0.722313,0.00094947673],"about_ca_topic_score_codex":0.00026007227,"about_ca_topic_score_gemma":0.00016165158,"teacher_disagreement_score":0.4924873,"about_ca_system_score_codex":0.00013081254,"about_ca_system_score_gemma":0.000037505357,"threshold_uncertainty_score":0.9998511},"labels":[],"label_agreement":null},{"id":"W4304783064","doi":"10.1038/s41597-022-01695-7","title":"An analysis-ready and quality controlled resource for pediatric brain white-matter research","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Advanced Neuroimaging Techniques and Applications","field":"Medicine","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Université de Montréal; Institut Universitaire en Santé Mentale de Québec; Western University; Polytechnique Montréal; Concordia University; University of Toronto","funders":"Child Mind Institute; University of Pennsylvania; National Institute of Biomedical Imaging and Bioengineering; National Institute of Mental Health; U.S. Department of Health and Human Services","keywords":"White matter; Quality (philosophy); Computer science; Medicine; Physics","score_opus":0.3514407486686759,"score_gpt":0.5218421750821093,"score_spread":0.17040142641343337,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4304783064","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":[0.7427654,0.0007960949,0.10033197,0.09260526,0.00038067202,0.010280312,0.047799427,0.00075975026,0.004281086],"genre_scores_gemma":[0.93415385,0.000005249098,0.014971694,0.0019507277,0.00018762647,0.00072258234,0.025438376,0.00003467873,0.022535209],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977356,0.00026311015,0.00026823365,0.00095171615,0.0005116879,0.0002696347],"domain_scores_gemma":[0.99635416,0.0005371943,0.000085391635,0.0027578701,0.00013487188,0.00013051661],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0068010213,0.000075651624,0.00026034765,0.00046618682,0.0009422806,0.00014729986,0.0006983605,0.000017593467,0.00021330753],"category_scores_gemma":[0.00050634466,0.000067594534,0.00004537871,0.0014859488,0.00019342893,0.0001315703,0.00073335913,0.0002372707,0.000008187257],"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":[0.00041197776,0.0004278301,0.100400604,0.000053904467,0.000051263905,0.0000033329477,0.00019476408,0.000048304497,0.0028537787,0.0016218,0.89296114,0.00097130885],"study_design_scores_gemma":[0.003110473,0.0002055519,0.057114314,0.0000029239582,0.0005216541,0.00000947438,0.0007056791,0.022281218,0.000071159026,0.0015833691,0.91419065,0.00020352232],"about_ca_topic_score_codex":0.000024427976,"about_ca_topic_score_gemma":0.000015056142,"teacher_disagreement_score":0.19138843,"about_ca_system_score_codex":0.000032119144,"about_ca_system_score_gemma":0.000069698486,"threshold_uncertainty_score":0.72473556},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"bench_or_experimental","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W4306173614","doi":"10.1038/s41597-022-01737-0","title":"OSeMOSYS Global, an open-source, open data global electricity system model generator","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Integrated Energy Systems Optimization","field":"Engineering","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":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; University College Cork; Loughborough University; Imperial College London; Science Foundation Ireland; Government of Canada; Government of the United Kingdom; Foreign, Commonwealth and Development Office; Colorado School of Mines","keywords":"Open source; Open data; Electricity; Open system (computing); Computer science; Generator (circuit theory); Electricity system; World Wide Web; Electricity generation; Operating system; Engineering; Electrical engineering; Software; Physics; Power (physics)","score_opus":0.06749732815584851,"score_gpt":0.2947616454382479,"score_spread":0.22726431728239938,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4306173614","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":[0.02792835,0.00097098347,0.6126099,0.000116354364,0.013533519,0.0033085654,0.27716127,0.0027482933,0.061622743],"genre_scores_gemma":[0.82503235,0.0000064486976,0.02810438,0.00011218913,0.00020691636,0.00015163545,0.14280875,0.00012256607,0.0034547646],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99621356,0.00026101153,0.0005397724,0.0016714974,0.0007339617,0.0005801865],"domain_scores_gemma":[0.991304,0.000009567349,0.0001249932,0.008201088,0.00013886506,0.00022150176],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.003053166,0.0002882858,0.00034664804,0.00008331478,0.0011165531,0.0037549138,0.023994824,0.00008365185,0.000118148215],"category_scores_gemma":[0.00007019165,0.00030562718,0.000017485732,0.0023284128,0.000058157962,0.0036840625,0.020599645,0.00021292552,0.00009365051],"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":[0.000010376852,0.00005285282,0.000027172358,0.000023942686,0.000037142632,0.0000067815836,0.000020576894,0.6354233,0.00034412486,0.002928745,0.35985625,0.0012687215],"study_design_scores_gemma":[0.00033311473,0.00001989666,0.00000611367,0.000018795316,0.000032047243,0.000046624693,0.00023299505,0.88091207,0.0000867734,0.000043944074,0.11795111,0.00031649473],"about_ca_topic_score_codex":0.0019684276,"about_ca_topic_score_gemma":0.0015401033,"teacher_disagreement_score":0.797104,"about_ca_system_score_codex":0.0011216154,"about_ca_system_score_gemma":0.0005116505,"threshold_uncertainty_score":0.99993956},"labels":[],"label_agreement":null},{"id":"W4306292496","doi":"10.1038/s41597-022-01723-6","title":"GABB: A global dataset of alpine breeding birds and their ecological traits","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Species Distribution and Climate Change","field":"Environmental Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Environment and Climate Change Canada; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Environment and Climate Change Canada","keywords":"Ecology; Geography; Biology","score_opus":0.07948226285215344,"score_gpt":0.2861313746013772,"score_spread":0.2066491117492238,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4306292496","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":[0.6513403,0.00006810106,0.000039009614,0.00046316974,0.00039642552,0.000122037585,0.34402272,0.000025484409,0.0035227118],"genre_scores_gemma":[0.961614,0.000008050111,0.00008335006,0.00017492591,0.000011144609,0.0000077650875,0.03792702,0.0000033009026,0.0001704118],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987692,0.000041542175,0.00015867931,0.000511849,0.0003073613,0.00021132214],"domain_scores_gemma":[0.9992373,0.000020021289,0.00006636197,0.0005878664,0.0000044099397,0.00008402344],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009169374,0.00007675926,0.000099512516,0.000016381498,0.00038429908,0.00007551585,0.0010170208,0.000017312748,0.06985907],"category_scores_gemma":[0.0000648679,0.000061580715,0.000015303696,0.000497827,0.000529207,0.00022016304,0.0043431413,0.00006359531,0.0001348987],"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":[0.00001071089,0.00018266501,0.0068393345,0.000005342745,0.0000052804926,0.0000039022107,0.00007460636,0.000006569433,0.011032083,0.000442818,0.9756937,0.0057030017],"study_design_scores_gemma":[0.00025955294,0.000071254624,0.12164364,0.0000016792276,0.0000078774565,0.000031544452,0.0022064364,0.0009851526,0.00018045788,0.00016839398,0.8743292,0.00011481466],"about_ca_topic_score_codex":0.0000667893,"about_ca_topic_score_gemma":0.00043181525,"teacher_disagreement_score":0.3102737,"about_ca_system_score_codex":0.0001478879,"about_ca_system_score_gemma":0.000011160513,"threshold_uncertainty_score":0.93099123},"labels":[],"label_agreement":null},{"id":"W4306292873","doi":"10.1038/s41597-022-01739-y","title":"Implementation of FAIR principles in the IPCC: the WGI AR6 Atlas repository","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Research Data Management Practices","field":"Computer Science","cited_by":132,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ouranos","funders":"Agencia Estatal de Investigación; Horizon 2020 Framework Programme; Universidad de Cantabria; European Commission; Engineering and Physical Sciences Research Council; U.S. Department of Energy","keywords":"Atlas (anatomy); Computer science; Scrutiny; Data science; Underpinning; Open source; World Wide Web; Information retrieval; Engineering; Software; Political science","score_opus":0.20529560955855886,"score_gpt":0.40425551406959226,"score_spread":0.1989599045110334,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4306292873","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":[0.66056275,0.0017671576,0.14361362,0.11091606,0.01487995,0.0094059175,0.0073525854,0.0003931157,0.051108826],"genre_scores_gemma":[0.99097496,0.000025982305,0.0031973606,0.00019953013,0.00004636464,0.00012341101,0.0011900376,0.0000063150733,0.004236021],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9964911,0.0008271927,0.00031190473,0.0006923985,0.0014215958,0.00025580838],"domain_scores_gemma":[0.99357283,0.00034010774,0.00023630602,0.0057864464,0.00004106186,0.000023270246],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.012349745,0.00006620706,0.000066526816,0.00018364168,0.00083416374,0.0027359803,0.017129073,0.000006644027,0.000057759145],"category_scores_gemma":[0.00023240618,0.000041223808,0.000020862348,0.0015936139,0.00019246175,0.010223483,0.012845567,0.00020621617,0.000014958775],"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":[0.000015633626,0.00043933213,0.012032673,0.00007654819,0.00006845448,0.00010209882,0.009574858,0.0004872331,0.0038951873,0.37979716,0.5527745,0.040736306],"study_design_scores_gemma":[0.00015861318,0.000034916164,0.030349212,0.0000038152953,0.0000058674013,0.0000111432755,0.008650947,0.008877522,0.00050823786,0.0005037805,0.95082164,0.00007428559],"about_ca_topic_score_codex":0.0005634693,"about_ca_topic_score_gemma":0.0005265749,"teacher_disagreement_score":0.39804715,"about_ca_system_score_codex":0.000041169067,"about_ca_system_score_gemma":0.00018807812,"threshold_uncertainty_score":0.9982993},"labels":[],"label_agreement":null},{"id":"W4306882708","doi":"10.1038/s41597-022-01714-7","title":"The Immune Signatures data resource, a compendium of systems vaccinology datasets","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"vaccines and immunoinformatics approaches","field":"Biochemistry, Genetics and Molecular Biology","cited_by":29,"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 Allergy and Infectious Diseases; Canadian Institutes of Health Research; National Institutes of Health; Division of Intramural Research, National Institute of Allergy and Infectious Diseases; U.S. Department of Health and Human Services","keywords":"Compendium; Reverse vaccinology; Data sharing; Systems biology; Immunogenicity; Computer science; Computational biology; Pooling; Data science; Immune system; Bioinformatics; Biology; Medicine; Immunology; Genome; Artificial intelligence; Geography; Gene","score_opus":0.035874715170587324,"score_gpt":0.2659537450915435,"score_spread":0.2300790299209562,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4306882708","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21271911,0.17256844,0.0018224686,0.002470244,0.01454944,0.0034226335,0.58658534,0.00010297204,0.005759316],"genre_scores_gemma":[0.64637613,0.00009095765,0.00021900599,0.0000399875,0.00008553387,0.00001901063,0.3515619,0.000017392475,0.0015900541],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99825716,0.00015277999,0.00042728157,0.0005768108,0.00030156402,0.00028440243],"domain_scores_gemma":[0.99166155,0.000038637427,0.00026566218,0.007959813,0.000038327256,0.000035992463],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.002451755,0.00011996969,0.00015725811,0.00005402419,0.0008945659,0.00019470479,0.0071455985,0.000046531804,0.000034549328],"category_scores_gemma":[0.0001723823,0.0000880503,0.000028053038,0.00022614487,0.00016867595,0.000021616326,0.015022908,0.00017641828,0.000008064283],"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":[0.00008675808,0.000084742445,0.000057732137,0.000038705883,0.0001136685,0.0000014557926,0.000042900196,0.00034151282,0.049168598,0.00066263287,0.9475616,0.001839689],"study_design_scores_gemma":[0.0002875784,0.00006887465,0.00021336366,0.0000042088845,0.000024094123,0.000030852247,0.00115135,0.009676687,0.0022838954,0.000015668693,0.98612946,0.000113991606],"about_ca_topic_score_codex":0.00005476376,"about_ca_topic_score_gemma":0.000023888577,"teacher_disagreement_score":0.43365705,"about_ca_system_score_codex":0.0000071123236,"about_ca_system_score_gemma":0.00012422788,"threshold_uncertainty_score":0.9982262},"labels":[],"label_agreement":null},{"id":"W4307565510","doi":"10.1038/s41597-022-01743-2","title":"Elaboration of a new framework for fine-grained epidemiological annotation","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Université de Sherbrooke","funders":"Horizon 2020 Framework Programme; Fonds De La Recherche Scientifique - FNRS; FOD Volksgezondheid, Veiligheid van de Voedselketen en Leefmilieu; Centre de Coopération Internationale en Recherche Agronomique pour le Développement; Agence Nationale de la Recherche; European Commission","keywords":"Annotation; Computer science; Variety (cybernetics); Context (archaeology); Data science; Process (computing); Information retrieval; World Wide Web; Artificial intelligence; Geography","score_opus":0.1471525771918431,"score_gpt":0.40116059898123296,"score_spread":0.25400802178938986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307565510","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":[0.28855252,0.0017704241,0.48256707,0.020839943,0.007059268,0.0048533664,0.19309892,0.0005172692,0.000741236],"genre_scores_gemma":[0.5582592,0.0000065725394,0.19808261,0.00083208893,0.00039085752,0.00012344844,0.23792899,0.00002942144,0.004346841],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983611,0.00011654335,0.00035195184,0.00060321373,0.00037791388,0.00018927226],"domain_scores_gemma":[0.9975324,0.000332198,0.00020449841,0.0016962027,0.000113734066,0.00012096348],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00231921,0.0000839874,0.00024436094,0.00010455226,0.00019992715,0.000030239318,0.00056266546,0.00003396393,0.0005227705],"category_scores_gemma":[0.0076557575,0.00007449171,0.000050940333,0.00076696085,0.00012242337,0.00017439079,0.00046252547,0.00012494683,0.000022418684],"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":[0.00039078965,0.00020086228,0.0040983493,0.000063978936,0.000033643035,0.000004654266,0.00014887193,0.00008806879,0.0026287641,0.006555359,0.9599775,0.02580914],"study_design_scores_gemma":[0.0014824708,0.00033475313,0.030647475,0.00005440825,0.00010262461,0.000007843216,0.00027631668,0.019587317,0.0003199586,0.02547435,0.9215236,0.00018889378],"about_ca_topic_score_codex":0.000014662625,"about_ca_topic_score_gemma":0.000015211734,"teacher_disagreement_score":0.28448445,"about_ca_system_score_codex":0.000037559603,"about_ca_system_score_gemma":0.00037256416,"threshold_uncertainty_score":0.916521},"labels":[],"label_agreement":null},{"id":"W4307891591","doi":"10.1038/s41597-022-01770-z","title":"Publisher Correction: An analysis-ready and quality controlled resource for pediatric brain white-matter research","year":2022,"lang":"en","type":"erratum","venue":"Scientific Data","topic":"Radiomics and Machine Learning in Medical Imaging","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":"McGill University; Université de Montréal; Institut Universitaire en Santé Mentale de Québec; Western University; Polytechnique Montréal; Concordia University; University of Toronto","funders":"","keywords":"White matter; Resource (disambiguation); Quality (philosophy); White paper; Computer science; Data science; Medicine; Political science; Physics","score_opus":0.10684226474260987,"score_gpt":0.43110366615052953,"score_spread":0.32426140140791965,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307891591","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0054038274,0.012528478,0.007504659,0.16756643,0.48491696,0.013663516,0.018792586,0.00086549396,0.28875807],"genre_scores_gemma":[0.00041307457,0.000029592144,0.00048122063,0.0015083478,0.0030222808,0.00013215162,0.15543292,0.00006938552,0.838911],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.992256,0.0013777466,0.0008602189,0.0025183316,0.0021993925,0.00078831596],"domain_scores_gemma":[0.99217296,0.0017718861,0.00041946615,0.0044926424,0.0005698627,0.00057317445],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.033612125,0.0003226309,0.0012888883,0.0021087916,0.0013694316,0.001946962,0.001753943,0.0003009458,0.0027758959],"category_scores_gemma":[0.014294455,0.00027322673,0.00021454283,0.0027908203,0.00063037477,0.0004683096,0.0015258021,0.0031309589,0.000029105724],"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":[0.00031235386,0.0001861759,0.015752716,0.00026094637,0.00033763843,0.000012824673,0.0002307278,0.000013189475,0.0000026550977,0.000022094617,0.9813814,0.0014872813],"study_design_scores_gemma":[0.0026195077,0.00012540637,0.010398758,0.000027660226,0.001475435,0.000015595693,0.00057580945,0.036285266,4.160761e-8,0.000059666076,0.94815,0.00026687636],"about_ca_topic_score_codex":0.000416779,"about_ca_topic_score_gemma":0.0002453346,"teacher_disagreement_score":0.55015296,"about_ca_system_score_codex":0.00016594729,"about_ca_system_score_gemma":0.0008716256,"threshold_uncertainty_score":0.999972},"labels":[],"label_agreement":null},{"id":"W4308252523","doi":"10.1038/s41597-022-01806-4","title":"Pre- and post-surgery brain tumor multimodal magnetic resonance imaging data optimized for large scale computational modelling","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Libin Cardiovascular Institute of Alberta; University of Calgary","funders":"Horizon 2020 Framework Programme; Universiteit Gent; Belgian Federal Science Policy Office; Deutsche Forschungsgemeinschaft; European Commission","keywords":"Magnetic resonance imaging; Voxel; Functional magnetic resonance imaging; Brain tumor; Diffusion MRI; Blood-oxygen-level dependent; Neuroimaging; Cerebral blood flow; Computer science; Scale (ratio); Medicine; Radiology; Artificial intelligence; Psychology; Neuroscience; Pathology; Internal medicine; Physics","score_opus":0.06762944165670765,"score_gpt":0.29375143796004594,"score_spread":0.2261219963033383,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308252523","genre_codex":"dataset","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":[0.2518218,0.0059603457,0.25772262,0.037301533,0.009254884,0.0035529756,0.43361375,0.00055519736,0.00021694128],"genre_scores_gemma":[0.82592344,0.000016286911,0.1254608,0.013413927,0.00036583055,0.0004260676,0.028659988,0.00013875436,0.0055949143],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960651,0.00023200267,0.0003144657,0.0021786187,0.0007428114,0.0004670218],"domain_scores_gemma":[0.98936373,0.008450528,0.00009584864,0.0019027487,0.000102363905,0.0000847934],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0036948288,0.00017226161,0.00023133721,0.00020149512,0.0023860072,0.00041958955,0.0016651342,0.000012040322,0.000094647025],"category_scores_gemma":[0.0077214767,0.00018844858,0.000038431266,0.00050957856,0.0003475999,0.0011139228,0.0059966743,0.000180503,0.000010138849],"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":[0.00082468113,0.0007267469,0.0014179603,0.00013010517,0.000013570848,0.000045196182,0.0011428229,0.11722567,0.018289318,0.0010052321,0.84382224,0.015356487],"study_design_scores_gemma":[0.0006690199,0.000019412655,0.00077559514,0.000012430375,0.000011614426,0.00004331182,0.00020284887,0.88729674,0.00010922608,0.00061844895,0.11004515,0.00019621338],"about_ca_topic_score_codex":0.000032363037,"about_ca_topic_score_gemma":0.000018290406,"teacher_disagreement_score":0.7700711,"about_ca_system_score_codex":0.00004421149,"about_ca_system_score_gemma":0.0002323777,"threshold_uncertainty_score":0.99891275},"labels":[],"label_agreement":null},{"id":"W4308509762","doi":"10.1038/s41597-022-01558-1","title":"A curated collection of human vaccination response signatures","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"vaccines and immunoinformatics approaches","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","funders":"National Institute of Allergy and Infectious Diseases; Canadian Institutes of Health Research; National Institutes of Health; Government of Canada; U.S. Department of Health and Human Services","keywords":"Ontology; Metadata; Computer science; Context (archaeology); Profiling (computer programming); UniProt; Dashboard; Computational biology; Data science; World Wide Web; Biology; Gene","score_opus":0.03444902112042952,"score_gpt":0.28963945436500976,"score_spread":0.25519043324458024,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308509762","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":[0.99732757,0.00029782936,0.0003043229,0.00009107992,0.0004177818,0.00018306452,0.00091565115,0.00000888541,0.00045383323],"genre_scores_gemma":[0.9862791,0.0000032848043,0.0001947195,0.000017757631,0.000015896758,0.0000119345805,0.009927915,0.000006187738,0.0035432195],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999207,0.000096578224,0.00018054625,0.00024637108,0.00017103745,0.0000984213],"domain_scores_gemma":[0.9988593,0.000006797079,0.0001529279,0.0008908266,0.00007231722,0.00001786505],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012526393,0.00005718194,0.00006253946,0.00009574752,0.00044828444,0.000047617334,0.0006054331,0.000027781001,0.00014276504],"category_scores_gemma":[0.00015851083,0.00005625998,0.00002279875,0.00036139294,0.000024677132,0.000011976688,0.0008508364,0.00006366036,0.0000019727381],"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":[0.00019260783,0.00006718364,0.0000848709,0.000010258596,0.000016649925,1.9794953e-7,0.00011725657,0.00014805386,0.85877067,0.00005170242,0.1397399,0.0008006524],"study_design_scores_gemma":[0.0016576578,0.001077145,0.017759198,0.0000088874485,0.00004430386,0.000022653396,0.002130959,0.01594202,0.49116758,0.0002628943,0.46953467,0.00039201736],"about_ca_topic_score_codex":0.000010883108,"about_ca_topic_score_gemma":0.0000112642165,"teacher_disagreement_score":0.36760306,"about_ca_system_score_codex":0.000013025581,"about_ca_system_score_gemma":0.00009182462,"threshold_uncertainty_score":0.34478867},"labels":[],"label_agreement":null},{"id":"W4308886066","doi":"10.1038/s41597-022-01796-3","title":"Near-real-time daily estimates of fossil fuel CO2 emissions from major high-emission cities in China","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Atmospheric and Environmental Gas Dynamics","field":"Environmental Science","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":"Queen's University; Hudbay Minerals (Canada); University of Toronto","funders":"National Natural Science Foundation of China","keywords":"China; Environmental science; Fossil fuel; Natural resource economics; Geography; Ecology; Economics; Biology; Archaeology","score_opus":0.010204367170759936,"score_gpt":0.22089903088848123,"score_spread":0.2106946637177213,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308886066","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":[0.9940177,0.00010119616,0.00037312176,0.000180555,0.000424982,0.0001887154,0.0024986824,0.000042720672,0.0021722908],"genre_scores_gemma":[0.9351231,0.000025807647,0.047139943,0.000029149342,0.000016568974,0.000020889443,0.0036013692,0.000030925356,0.01401227],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9976232,0.00007473412,0.0003546919,0.0008529327,0.00073662377,0.00035782074],"domain_scores_gemma":[0.9980894,0.0000671052,0.00015671573,0.0015335121,0.0000020755951,0.00015122585],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006129953,0.00018163671,0.00022938548,0.000016324,0.0006130238,0.00009712192,0.001725267,0.000046027224,0.017800631],"category_scores_gemma":[0.000057878075,0.00016915309,0.000032586762,0.00051476434,0.000937893,0.00042437483,0.004700913,0.00018958106,0.000178909],"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":[0.00017339575,0.0013957003,0.3247656,0.000049370363,0.000048706403,0.000083761064,0.005870779,0.14129576,0.29923803,0.00008551537,0.2074912,0.019502189],"study_design_scores_gemma":[0.0012107819,0.00013260284,0.5106464,0.00006030715,0.00006909574,0.0000106837915,0.002292946,0.43577713,0.0010270078,0.008275242,0.039784946,0.0007128347],"about_ca_topic_score_codex":0.0070096427,"about_ca_topic_score_gemma":0.00008406731,"teacher_disagreement_score":0.29821104,"about_ca_system_score_codex":0.00022729166,"about_ca_system_score_gemma":0.000041858642,"threshold_uncertainty_score":0.9996028},"labels":[],"label_agreement":null},{"id":"W4309046817","doi":"10.1038/s41597-022-01815-3","title":"Modeling community standards for metadata as templates makes data FAIR","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Research Data Management Practices","field":"Computer Science","cited_by":46,"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":"Common Fund; U.S. National Library of Medicine; National Science Foundation; Wellcome; Canadian Institutes of Health Research; Austrian Science Fund; Wellcome Trust; National Institute of General Medical Sciences; National Cancer Institute; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Institutes of Health; U.S. Department of Health and Human Services; NIH Office of the Director","keywords":"Metadata; Template; Computer science; Geospatial metadata; Meta Data Services; Information retrieval; World Wide Web; Data science; Data element; Programming language","score_opus":0.4877564196382878,"score_gpt":0.4680528498693035,"score_spread":0.019703569768984297,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309046817","genre_codex":"methods","genre_gemma":"dataset","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":[0.0013625483,0.00037691215,0.8549292,0.0028557752,0.0015191954,0.0007873322,0.13689135,0.00020821876,0.0010694335],"genre_scores_gemma":[0.2878486,0.00021879435,0.30665267,0.00088763394,0.00019284135,0.00031917327,0.37943333,0.00008968855,0.024357274],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99338835,0.0009660429,0.00042389886,0.0019755715,0.002578682,0.0006674499],"domain_scores_gemma":[0.96730894,0.0007093287,0.00017470322,0.031364642,0.00027237125,0.00017002865],"candidate_categories":["metaresearch","sts","scholarly_communication","open_science"],"consensus_categories":["scholarly_communication","open_science"],"category_scores_codex":[0.04114348,0.00018891036,0.0002245314,0.00036960235,0.0044463146,0.018433115,0.067543514,0.000022131973,0.00013330841],"category_scores_gemma":[0.0052571706,0.00018436363,0.000032935273,0.001370461,0.00020407258,0.09434966,0.12832287,0.0006238261,0.000030139083],"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":[0.00007264615,0.00049768074,0.00002935288,0.0001751936,0.00021499289,0.00003237092,0.0005315779,0.0034620964,0.00047634484,0.07662398,0.89017946,0.027704287],"study_design_scores_gemma":[0.00018340099,0.000040319992,0.0000027063763,0.0000058818723,0.000018523944,0.0000068575196,0.00074832566,0.47942737,0.000036064583,0.002658882,0.51673746,0.00013421044],"about_ca_topic_score_codex":0.0014511165,"about_ca_topic_score_gemma":0.0008167194,"teacher_disagreement_score":0.54827654,"about_ca_system_score_codex":0.0001325495,"about_ca_system_score_gemma":0.0008475233,"threshold_uncertainty_score":0.9968498},"labels":[],"label_agreement":null},{"id":"W4309333099","doi":"10.1038/s41597-022-01817-1","title":"A biomechanics dataset of healthy human walking at various speeds, step lengths and step widths","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Balance, Gait, and Falls Prevention","field":"Health Professions","cited_by":44,"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 Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Biomechanics; Inverse dynamics; Ground reaction force; Motion capture; Gait; Computer science; Preferred walking speed; Treadmill; Simulation; Motion analysis; Gait analysis; Torque; Kinematics; Mathematics; Motion (physics); Physical medicine and rehabilitation; Artificial intelligence; Physics; Medicine; Anatomy; Physical therapy","score_opus":0.0758115345077446,"score_gpt":0.39332829701896466,"score_spread":0.3175167625112201,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309333099","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":[0.5372701,0.0025925152,0.0012511287,0.001106222,0.013247631,0.0032394354,0.43923664,0.00023419726,0.0018221046],"genre_scores_gemma":[0.62686574,0.00019621255,0.004081765,0.0010818412,0.00031275567,0.000117622636,0.35558346,0.0000801745,0.011680414],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99634516,0.0007022189,0.0007422433,0.0009805191,0.0006418009,0.0005880429],"domain_scores_gemma":[0.99648607,0.00015807664,0.0005391794,0.002576772,0.000069881,0.00017003901],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0055369386,0.00016112898,0.00030696712,0.00025661904,0.0036208213,0.00004705775,0.0013403604,0.00008473562,0.00048587096],"category_scores_gemma":[0.0000970857,0.00016227737,0.000029957835,0.00064501486,0.00018274592,0.00035517593,0.0057635214,0.00050767214,0.00011499978],"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":[0.0000818568,0.00048347184,0.00091474265,0.000546428,0.000037650738,0.000009608889,0.0010210781,1.4473646e-7,0.025980089,0.0019870792,0.9547523,0.014185499],"study_design_scores_gemma":[0.0014802247,0.00015142233,0.0034893337,0.00009439312,0.00005550837,0.000009625044,0.002282675,0.0030794502,0.000010405917,0.00087355886,0.9882495,0.00022389696],"about_ca_topic_score_codex":0.0006064345,"about_ca_topic_score_gemma":0.0016029944,"teacher_disagreement_score":0.08959561,"about_ca_system_score_codex":0.00016794373,"about_ca_system_score_gemma":0.00025999823,"threshold_uncertainty_score":0.9976763},"labels":[],"label_agreement":null},{"id":"W4309513471","doi":"10.1038/s41597-022-01816-2","title":"Author Correction: An analysis-ready and quality controlled resource for pediatric brain white-matter research","year":2022,"lang":"en","type":"erratum","venue":"Scientific Data","topic":"Neonatal and fetal brain pathology","field":"Medicine","cited_by":1,"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; Université de Montréal; Institut Universitaire en Santé Mentale de Québec; Western University; Polytechnique Montréal; Concordia University; University of Toronto","funders":"","keywords":"White matter; White paper; Quality (philosophy); Resource (disambiguation); White (mutation); Medicine; Computer science; Geography; Biology; Physics; Archaeology","score_opus":0.15712393059970867,"score_gpt":0.4317657935942526,"score_spread":0.27464186299454396,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309513471","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012425806,0.02255084,0.0034194866,0.103570126,0.36595958,0.024690554,0.30362678,0.0010268172,0.16273],"genre_scores_gemma":[0.000779934,0.000011114362,0.00021774876,0.0007622862,0.0019213458,0.00019255982,0.1947628,0.000045812754,0.8013064],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9925013,0.001424276,0.00086161477,0.002875121,0.001558475,0.0007791888],"domain_scores_gemma":[0.99226964,0.0017293491,0.00037185257,0.0047070365,0.0004925477,0.00042959605],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02064336,0.00035073928,0.0014191966,0.0019631074,0.0013047265,0.00044619374,0.0014938703,0.0004249632,0.0028360086],"category_scores_gemma":[0.005050318,0.00029657947,0.00023765204,0.002749033,0.00077313895,0.0002582838,0.0020082665,0.0018050417,0.00011066034],"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":[0.0010925384,0.00022565696,0.0027373387,0.00032933208,0.00025166306,0.000041735784,0.00033063954,0.0000014248794,0.000024639645,0.000041247436,0.993779,0.0011447959],"study_design_scores_gemma":[0.0024323969,0.00034999897,0.0119995745,0.000017206989,0.0014798328,0.000051654344,0.000922215,0.0025890237,9.325005e-7,0.00009078121,0.97976106,0.0003053213],"about_ca_topic_score_codex":0.00013199737,"about_ca_topic_score_gemma":0.0005022696,"teacher_disagreement_score":0.6385764,"about_ca_system_score_codex":0.00011825165,"about_ca_system_score_gemma":0.0006476938,"threshold_uncertainty_score":0.9999954},"labels":[],"label_agreement":null},{"id":"W4309625182","doi":"10.1038/s41597-022-01812-6","title":"An expert curated global legume checklist improves the accuracy of occurrence, biodiversity and taxonomic data","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Plant and Fungal Species Descriptions","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"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","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Université de Montréal; Royal Botanical Gardens, Kew","keywords":"Checklist; Taxon; Taxonomic rank; Biodiversity; Biology; Global biodiversity; Ecology","score_opus":0.06531958014189927,"score_gpt":0.29584527117678433,"score_spread":0.23052569103488507,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309625182","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":[0.728833,0.0011505601,0.00009816226,0.0002574045,0.0011124318,0.00019157965,0.26799288,0.000011511018,0.00035246107],"genre_scores_gemma":[0.8864,0.00008096365,0.00018160189,0.00009593127,0.000054112556,0.000003923587,0.11296686,0.0000018250154,0.00021480875],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988829,0.00007574085,0.00012387734,0.00062205567,0.00014181997,0.00015363768],"domain_scores_gemma":[0.99751216,0.000010626551,0.00009001853,0.0022997851,0.000032098535,0.000055290504],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058652734,0.00008079242,0.000075498916,0.000019985548,0.00069608085,0.00015607127,0.0026655304,0.000025499307,0.00008448383],"category_scores_gemma":[0.00011426384,0.00006536578,0.000015085361,0.00019290163,0.0004183022,0.000052196418,0.004198066,0.000079057485,0.0000061406768],"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":[0.000035167133,0.00007088405,0.0014801844,0.0000032717544,0.0000199204,9.351713e-7,0.000030044393,0.0000018118733,0.31422782,0.00003640319,0.6818301,0.0022634726],"study_design_scores_gemma":[0.00018189196,0.00005247239,0.0034377447,0.0000014314373,0.000018269971,0.000014553893,0.00082415895,0.0011848089,0.0024065345,0.000009145895,0.9917521,0.000116895004],"about_ca_topic_score_codex":0.00020244879,"about_ca_topic_score_gemma":0.00024196578,"teacher_disagreement_score":0.31182128,"about_ca_system_score_codex":0.000011993431,"about_ca_system_score_gemma":0.00011566685,"threshold_uncertainty_score":0.53537613},"labels":[],"label_agreement":null},{"id":"W4310060332","doi":"10.1038/s41597-022-01833-1","title":"TractoInferno - A large-scale, open-source, multi-site database for machine learning dMRI tractography","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Advanced Neuroimaging Techniques and Applications","field":"Medicine","cited_by":44,"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; Hôpital du Sacré-Cœur de Montréal; Université de Sherbrooke","funders":"Fonds de recherche du Québec – Nature et technologies; Compute Canada; Wellcome Trust","keywords":"Computer science; Tractography; Scale (ratio); Database; Artificial intelligence; Diffusion MRI; Cartography; Magnetic resonance imaging; Medicine; Geography","score_opus":0.17628452514973905,"score_gpt":0.40893639807620985,"score_spread":0.2326518729264708,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4310060332","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":[0.01682703,0.0005593973,0.8746315,0.0033587143,0.0005931184,0.0041834502,0.098179646,0.0009099359,0.0007571521],"genre_scores_gemma":[0.19899508,0.00007959909,0.5228777,0.0019345926,0.00015874063,0.0013042343,0.2406809,0.00019838789,0.03377079],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976888,0.000055906323,0.00029823306,0.0011956074,0.0003627712,0.00039873002],"domain_scores_gemma":[0.99683195,0.0000967507,0.00015959928,0.002671687,0.00007061695,0.00016940193],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0015749015,0.00016343473,0.00023958359,0.00024371297,0.0014995061,0.00024755165,0.0016127165,0.00002339076,0.00040143207],"category_scores_gemma":[0.00019818303,0.00015987012,0.0000808717,0.00089844014,0.00013354402,0.00050522387,0.0030408883,0.0005368907,0.000017772558],"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":[0.0007000723,0.007656968,0.036283653,0.00032090652,0.000119897595,0.00008722642,0.0013562719,0.0003173903,0.14746787,0.0014116329,0.71857524,0.085702844],"study_design_scores_gemma":[0.0014149433,0.000082460465,0.0011504653,0.000019449299,0.0000699386,0.000052824493,0.00015051823,0.07220827,0.0004291373,0.00007579253,0.92417866,0.00016753653],"about_ca_topic_score_codex":0.000050842744,"about_ca_topic_score_gemma":0.000058808182,"teacher_disagreement_score":0.3517539,"about_ca_system_score_codex":0.00002836081,"about_ca_system_score_gemma":0.0000832712,"threshold_uncertainty_score":0.9998004},"labels":[],"label_agreement":null},{"id":"W4310480951","doi":"10.1038/s41597-022-01842-0","title":"HeliantHOME, a public and centralized database of phenotypic sunflower data","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Sunflower and Safflower Cultivation","field":"Agricultural and Biological Sciences","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 Victoria; University of British Columbia","funders":"Leibniz-Rechenzentrum; Leibniz-Gemeinschaft; Bayerische Akademie der Wissenschaften; Genome British Columbia; Technische Universität München; Genome Canada; National Science Foundation","keywords":"Domestication; Biology; Genomics; Adaptation (eye); Helianthus annuus; Sunflower; Helianthus; Population; Ranking (information retrieval); Biotechnology; Genome; Genetics; Computer science; Information retrieval; Gene; Agronomy","score_opus":0.1199364605218563,"score_gpt":0.27427903573872975,"score_spread":0.15434257521687345,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4310480951","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":[0.92054373,0.0009200328,0.000044202607,0.0021650416,0.0017054551,0.0003546363,0.07380608,0.0000750615,0.00038575687],"genre_scores_gemma":[0.90926254,0.000034330416,0.00048561656,0.000109390305,0.00008129991,0.000008748575,0.089295626,0.0000015611485,0.00072086166],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976759,0.00015321554,0.00028220197,0.0010005689,0.0005716938,0.00031640154],"domain_scores_gemma":[0.9983268,0.000121173434,0.00011207834,0.0012509378,0.00006616898,0.000122876],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0020511972,0.00011508368,0.0001615755,0.000040081803,0.0007086318,0.00024656064,0.0028943191,0.000024419696,0.0034590226],"category_scores_gemma":[0.00033506766,0.000052904055,0.000021613938,0.0010572686,0.00024252979,0.0010311436,0.005668676,0.00012672466,0.000015717664],"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":[0.000139316,0.0009126268,0.015977427,0.00004664256,0.000062194245,0.000015860895,0.00033604202,0.0000027137191,0.4673564,0.0013052514,0.3513813,0.16246422],"study_design_scores_gemma":[0.0004101686,0.00006045064,0.023812512,0.000013676146,0.000028187045,0.000012120993,0.0011234928,0.0031524606,0.00058403437,0.00022396048,0.97032017,0.00025874612],"about_ca_topic_score_codex":0.00019848197,"about_ca_topic_score_gemma":0.00055581215,"teacher_disagreement_score":0.61893886,"about_ca_system_score_codex":0.000013354595,"about_ca_system_score_gemma":0.000038408034,"threshold_uncertainty_score":0.99745196},"labels":[],"label_agreement":null},{"id":"W4310699919","doi":"10.1038/s41597-022-01837-x","title":"Mechanical Unloading of Engineered Human Meniscus Models Under Simulated Microgravity: A Transcriptomic Study","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Spaceflight effects on biology","field":"Medicine","cited_by":28,"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 Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates; University of British Columbia; Canada Foundation for Innovation; Government of Canada; Canadian Institutes of Health Research; Alberta Cancer Foundation; Alberta Innovates - Health Solutions; Women and Children's Health Research Institute","keywords":"Meniscus; Transcriptome; Computer science; Computational biology; Biology; Physics; Optics; Gene expression","score_opus":0.10437387391574139,"score_gpt":0.3480758117944599,"score_spread":0.24370193787871852,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4310699919","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":[0.99456674,0.00016975772,0.0009539351,0.00033689753,0.0010450165,0.0012414204,0.0014679511,0.00012072956,0.000097536904],"genre_scores_gemma":[0.99573845,5.7835035e-7,0.00034776411,0.00006283936,0.000023854236,0.000017370961,0.0028831712,0.000028679191,0.00089727604],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974191,0.00024988057,0.00040044507,0.0009954141,0.0005606668,0.00037447963],"domain_scores_gemma":[0.99722576,0.000072204355,0.000097272685,0.0023874957,0.00008169921,0.00013558342],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002301421,0.00017725913,0.00045136662,0.00036898244,0.00034156904,0.000044855078,0.000991976,0.00005999356,0.00040932134],"category_scores_gemma":[0.000058489037,0.0001570841,0.00007791455,0.0008499883,0.00016375163,0.00013189939,0.0008479617,0.0003352987,0.000012612033],"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":[0.00016205867,0.0012445465,0.00013406767,0.000036400044,0.00017919565,0.000046772384,0.00068636617,0.0011725767,0.9898055,0.0005806488,0.0057175155,0.00023431951],"study_design_scores_gemma":[0.048926186,0.011811545,0.0026425822,0.00020967078,0.00473762,0.0007082334,0.020246793,0.5810039,0.27551818,0.010799867,0.040735964,0.0026594945],"about_ca_topic_score_codex":0.00009033364,"about_ca_topic_score_gemma":0.00006390874,"teacher_disagreement_score":0.71428734,"about_ca_system_score_codex":0.00010153231,"about_ca_system_score_gemma":0.00012668343,"threshold_uncertainty_score":0.64057034},"labels":[],"label_agreement":null},{"id":"W4311505052","doi":"10.1038/s41597-022-01888-0","title":"A data set of global river networks and corresponding water resources zones divisions v2","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Hydrology and Watershed Management Studies","field":"Environmental Science","cited_by":15,"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":"U.S. Geological Survey; Nature Conservancy; McGill University; Australian National University; World Wildlife Fund","keywords":"Data set; Set (abstract data type); Water resources; Geology; Water resource management; Environmental science; Computer science; Ecology; Biology","score_opus":0.0410215549892982,"score_gpt":0.27028991474207664,"score_spread":0.22926835975277843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4311505052","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":[0.98343164,0.00018421312,0.0013340799,0.0014268704,0.0013421245,0.00023633371,0.010249506,0.00004043167,0.0017548276],"genre_scores_gemma":[0.99387217,0.000010232714,0.00034063926,0.00009954473,0.000018972212,0.000004700079,0.0032624344,0.000004314407,0.0023869916],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.998352,0.00011973384,0.00015724836,0.00076591916,0.0003205784,0.00028454783],"domain_scores_gemma":[0.9981146,0.000037975256,0.000049840615,0.0017480697,0.0000027010046,0.000046854566],"candidate_categories":["open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0018147883,0.00008842893,0.00011512112,0.000031535277,0.0011228933,0.00006410351,0.0020898373,0.000017401198,0.0013775897],"category_scores_gemma":[0.000039448914,0.00006577323,0.000010975042,0.00030219703,0.0011349407,0.00044953558,0.032072384,0.00008571814,0.00007238293],"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":[0.00008174998,0.000104830826,0.22298785,0.000012987757,0.00007893662,0.000034567645,0.0025321802,0.008442493,0.0002486235,0.00013503495,0.7587411,0.006599677],"study_design_scores_gemma":[0.00025553704,0.000038736707,0.049568158,0.0000059363983,0.000066280016,0.0000075405155,0.0007470344,0.04596767,0.000010451788,0.00075276016,0.9024122,0.00016770649],"about_ca_topic_score_codex":0.00020726369,"about_ca_topic_score_gemma":0.00021445184,"teacher_disagreement_score":0.17341968,"about_ca_system_score_codex":0.000026684951,"about_ca_system_score_gemma":0.0000025833056,"threshold_uncertainty_score":0.99953526},"labels":[],"label_agreement":null},{"id":"W4311572563","doi":"10.1038/s41597-022-01774-9","title":"The global spectrum of plant form and function: enhanced species-level trait dataset","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Ecology and Vegetation Dynamics Studies","field":"Environmental Science","cited_by":118,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Algoma University; University of Waterloo; University of Saskatchewan; Université de Sherbrooke","funders":"Deutsches Zentrum für integrative Biodiversitätsforschung Halle-Jena-Leipzig; Russian Science Foundation; Natural Environment Research Council; Consejo Nacional de Investigaciones Científicas y Técnicas; Newton Fund; Fondo para la Investigación Científica y Tecnológica; Inter-American Institute for Global Change Research; Universidad Nacional de Córdoba","keywords":"Trait; Biology; Categorical variable; Vascular plant; Specific leaf area; Plant species; Taxonomic rank; Botany; Ecology; Statistics; Mathematics; Species richness; Computer science","score_opus":0.036174268526012715,"score_gpt":0.2472785866775703,"score_spread":0.21110431815155759,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4311572563","genre_codex":"dataset","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":[0.25500005,0.0003608713,0.0034864815,0.004106052,0.005747812,0.00071200763,0.7076818,0.0000454493,0.022859495],"genre_scores_gemma":[0.97501725,0.000022347156,0.00024205803,0.000111729365,0.00002029019,0.00001640162,0.020383555,0.0000033516528,0.004182992],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99900925,0.00003678493,0.00014463843,0.0003716059,0.00026641844,0.00017129743],"domain_scores_gemma":[0.99913436,0.000061178616,0.00007792571,0.0006931211,0.0000029418334,0.000030477075],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00091243355,0.00005960939,0.000070017064,0.0000115049315,0.001427975,0.000048986618,0.0007590026,0.0000109650155,0.0015063739],"category_scores_gemma":[0.00004142928,0.00004476224,0.000010871317,0.0002591069,0.0007473572,0.00019688005,0.0023196968,0.00007082834,0.000042741187],"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":[0.00010148075,0.0001333056,0.016498638,0.000009826663,0.00005950499,0.000004227202,0.00042496994,0.0003375839,0.0007353289,0.012919191,0.96331084,0.0054650903],"study_design_scores_gemma":[0.0002597067,0.000072733455,0.25577945,0.000001416539,0.000023825343,0.000012899905,0.00094625156,0.0032606618,0.00005860985,0.008472409,0.73100775,0.000104296916],"about_ca_topic_score_codex":0.00003872728,"about_ca_topic_score_gemma":0.00538628,"teacher_disagreement_score":0.7200172,"about_ca_system_score_codex":0.000058390164,"about_ca_system_score_gemma":0.000017282642,"threshold_uncertainty_score":0.999872},"labels":[],"label_agreement":null},{"id":"W4311582290","doi":"10.1038/s41597-022-01860-y","title":"Particle filtration efficiency measured using sodium chloride and polystyrene latex sphere test methods","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Infection Control and Ventilation","field":"Medicine","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"Public Health Agency; Public Health Agency of Canada","keywords":"Polystyrene; Dispersity; Filtration (mathematics); Materials science; Sodium; Equivalence (formal languages); Chloride; Particle size; Particle (ecology); Mathematics; Chemistry; Polymer chemistry; Statistics; Composite material; Metallurgy; Physical chemistry","score_opus":0.09924052525318396,"score_gpt":0.36494054651851177,"score_spread":0.2657000212653278,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4311582290","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":[0.9050436,0.00078273274,0.08679967,0.0009191135,0.0037845378,0.00071737095,0.00072030263,0.00016508122,0.0010675933],"genre_scores_gemma":[0.9938702,0.0000015479586,0.0030464837,0.00007007716,0.00010826191,0.0000083469,0.0006945428,0.000009538595,0.002191027],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986338,0.00010908942,0.00022501568,0.0004710637,0.00036219112,0.00019885287],"domain_scores_gemma":[0.99894434,0.00007066603,0.00009174426,0.0007212616,0.000087482185,0.0000844984],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025507165,0.00008124326,0.00013233897,0.00007271316,0.0008015647,0.00015005424,0.00016102192,0.00002311766,0.00065513066],"category_scores_gemma":[0.00048244244,0.00007630684,0.000026956346,0.00056423154,0.00009298466,0.0002895461,0.0002715101,0.0001221938,0.00001540048],"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":[0.00022556342,0.0005512738,0.028435025,0.00006449342,0.000046372108,0.000014040569,0.0004977977,0.00056823826,0.9249746,0.0002305163,0.004614975,0.039777104],"study_design_scores_gemma":[0.0017176144,0.0001814585,0.022846278,0.000023865608,0.00023156224,0.00015018515,0.00039813019,0.86408687,0.0605331,0.00015426286,0.04946462,0.00021203866],"about_ca_topic_score_codex":0.0000744372,"about_ca_topic_score_gemma":0.00002928657,"teacher_disagreement_score":0.8644415,"about_ca_system_score_codex":0.000055005214,"about_ca_system_score_gemma":0.0001496075,"threshold_uncertainty_score":0.7173221},"labels":[],"label_agreement":null},{"id":"W4311715174","doi":"10.1038/s41597-022-01887-1","title":"Comparative transcriptome profiles of four sexually size dimorphic fish","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Fish Ecology and Management Studies","field":"Environmental Science","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":"Ministry of Agriculture","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Sexual dimorphism; Transcriptome; Biology; Fish <Actinopterygii>; Zoology; Evolutionary biology; Fishery; Genetics; Gene expression; Gene","score_opus":0.06658906232373124,"score_gpt":0.27213229318616233,"score_spread":0.2055432308624311,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4311715174","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":[0.9482121,0.000028471146,0.00010918696,0.0033038307,0.0022768802,0.0007780115,0.0065483893,0.00007587004,0.038667243],"genre_scores_gemma":[0.9802189,0.0000022852046,0.00051473087,0.00039882606,0.000010465786,0.000049007645,0.0005787865,0.0000049306814,0.0182221],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99843794,0.00010600445,0.0001929061,0.00059518,0.0004331358,0.00023483344],"domain_scores_gemma":[0.99888474,0.00007412535,0.00009447947,0.0009039753,0.0000072984153,0.00003538218],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0010638032,0.00009284662,0.00017024268,0.000038458562,0.0007734285,0.000031909458,0.001484526,0.0000140587035,0.012696956],"category_scores_gemma":[0.000060347436,0.000089258705,0.00002284666,0.0004895965,0.00076760864,0.0003373485,0.0030743002,0.000113698705,0.00016695965],"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":[0.00001533599,0.00016373578,0.02013372,0.000012315583,0.000033329532,0.000004669159,0.0010063018,0.0002003118,0.0028146508,0.00009375365,0.975364,0.00015785256],"study_design_scores_gemma":[0.00043990987,0.00013069857,0.42774516,0.0000038987196,0.000052601776,0.000003871646,0.0026688857,0.0010520037,0.00038410327,0.00084431196,0.5664439,0.00023062597],"about_ca_topic_score_codex":0.000040626725,"about_ca_topic_score_gemma":0.0011275464,"teacher_disagreement_score":0.4089201,"about_ca_system_score_codex":0.000040208128,"about_ca_system_score_gemma":0.000015219926,"threshold_uncertainty_score":0.98820555},"labels":[],"label_agreement":null},{"id":"W4313439128","doi":"10.1038/s41597-022-01899-x","title":"MIMIC-IV, a freely accessible electronic health record dataset","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":2791,"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","funders":"National Institutes of Health; National Institute of Biomedical Imaging and Bioengineering; U.S. Department of Health and Human Services","keywords":"Electronic health record; Computer science; Health records; Information retrieval; World Wide Web; Health care; Political science","score_opus":0.10846043845443115,"score_gpt":0.39437885807324796,"score_spread":0.2859184196188168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313439128","genre_codex":"methods","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.039961334,0.005842596,0.34778765,0.33475274,0.05828557,0.0059681656,0.18860501,0.01430354,0.0044933837],"genre_scores_gemma":[0.19233604,0.0008353312,0.1521422,0.013727488,0.0015640856,0.00022051236,0.6028111,0.00025741672,0.03610581],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.995101,0.00033573623,0.00046769233,0.0020000832,0.00079012197,0.0013054197],"domain_scores_gemma":[0.99110603,0.00016155577,0.0002402856,0.00810606,0.00007451415,0.00031154777],"candidate_categories":["scholarly_communication","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0056004925,0.00019403476,0.00024514162,0.00047690622,0.0009377874,0.0014397579,0.011169721,0.000057711877,0.00014246374],"category_scores_gemma":[0.0004761938,0.00018592905,0.000031993164,0.003804527,0.00012953352,0.001850088,0.0062841307,0.0005169722,0.0030421927],"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":[0.0000021727856,0.000022138776,0.0009818457,0.00006472769,0.000006191384,0.000010216907,0.00014967078,0.000027213951,0.000031582458,0.003108268,0.9066598,0.08893617],"study_design_scores_gemma":[0.00013779949,0.000053662272,0.001847208,0.000035107387,0.0000020292034,0.000010285596,0.00002263191,0.19457194,0.000013235347,0.0024073597,0.8007212,0.00017748289],"about_ca_topic_score_codex":0.0017578178,"about_ca_topic_score_gemma":0.002827747,"teacher_disagreement_score":0.41420612,"about_ca_system_score_codex":0.00013064129,"about_ca_system_score_gemma":0.0014797066,"threshold_uncertainty_score":0.99959683},"labels":[],"label_agreement":null},{"id":"W4313528201","doi":"10.1038/s41597-022-01880-8","title":"Familydemic Cross Country and Gender Dataset on work and family outcomes during COVID-19 pandemic","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"Work-Family Balance Challenges","field":"Social Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Brock University; University of British Columbia","funders":"Forskningsrådet om Hälsa, Arbetsliv och Välfärd; Social Sciences and Humanities Research Council of Canada; Universität Hamburg; Università degli Studi di Firenze; Narodowe Centrum Nauki; Vetenskapsrådet; Government of Canada; Royal Swedish Academy of Sciences; Davidson College; Fordham University","keywords":"Pandemic; Work (physics); Welfare; Coronavirus disease 2019 (COVID-19); Demographic economics; Division of labour; Cross country; Geography; Political science; Economic growth; Economics; Medicine","score_opus":0.20641003253429405,"score_gpt":0.418678501366601,"score_spread":0.21226846883230696,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313528201","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":[0.970021,0.0010532745,0.000008830287,0.0005811531,0.0020001165,0.00033552173,0.024745159,0.00039794532,0.00085700507],"genre_scores_gemma":[0.97399014,0.0027577893,0.00008624912,0.0010806631,0.0002523639,0.000026865211,0.01545954,0.00004041237,0.006305978],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99634194,0.00021232919,0.00029754467,0.0014391479,0.0009272581,0.0007817653],"domain_scores_gemma":[0.996963,0.0006430022,0.000117107804,0.0017826915,0.000043614866,0.00045054514],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.004875077,0.00022570399,0.00027205845,0.00023073218,0.0021674163,0.0010662149,0.0015848245,0.00016806634,0.00006555345],"category_scores_gemma":[0.0015997702,0.00020770635,0.000021412858,0.0011394406,0.0019976096,0.00077471,0.0015345159,0.00028874018,0.00022696928],"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":[0.00002046252,0.000018737897,0.73641115,0.000055239187,0.000021952921,0.000017147953,0.0035177772,0.000013165784,0.00011394858,0.00021732182,0.2591893,0.00040380663],"study_design_scores_gemma":[0.0004646109,0.000004946064,0.7159502,0.000024001123,0.000016141868,0.0000018856311,0.005051414,0.000011951063,0.0000010761577,0.0008101407,0.27740976,0.0002538643],"about_ca_topic_score_codex":0.0003222669,"about_ca_topic_score_gemma":0.0014210021,"teacher_disagreement_score":0.02046093,"about_ca_system_score_codex":0.00014403777,"about_ca_system_score_gemma":0.00030413,"threshold_uncertainty_score":0.9999708},"labels":[],"label_agreement":null},{"id":"W4313544955","doi":"10.1038/s41597-022-01896-0","title":"Author Correction: COVIDiSTRESS diverse dataset on psychological and behavioural outcomes one year into the COVID-19 pandemic","year":2023,"lang":"en","type":"erratum","venue":"Scientific Data","topic":"COVID-19 and Mental Health","field":"Psychology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Pandemic; Coronavirus disease 2019 (COVID-19); 2019-20 coronavirus outbreak; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Psychology; Medicine; Virology; Outbreak; Infectious disease (medical specialty)","score_opus":0.4524044860773293,"score_gpt":0.5205371422595774,"score_spread":0.06813265618224806,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313544955","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007147658,0.00086351443,0.00009649965,0.018489705,0.49222428,0.0021212841,0.475853,0.0006739996,0.0025300642],"genre_scores_gemma":[0.0035606755,0.0001648226,0.000028075496,0.0052747144,0.0008066224,0.00009969207,0.39885885,0.0000603069,0.59114623],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9947757,0.0005258597,0.0005441815,0.0025749751,0.0008845824,0.0006947011],"domain_scores_gemma":[0.9929892,0.0007433884,0.00032683092,0.0053046006,0.000039623334,0.0005963558],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0031714172,0.00043864147,0.00052565715,0.0003061788,0.0014229836,0.00044525444,0.002997062,0.00055606675,0.002461585],"category_scores_gemma":[0.0009667273,0.0003124031,0.00008709054,0.0006529356,0.0013841115,0.00016237069,0.002366241,0.0015630755,0.003277944],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014229657,0.00031653116,0.016834205,0.000088897665,0.00005902409,0.00007385269,0.0011008623,2.5175655e-7,9.352154e-7,0.00013735244,0.9750048,0.0062409905],"study_design_scores_gemma":[0.00071052666,0.00015797385,0.041122206,0.00005574335,0.00015317598,0.000027066262,0.002018896,0.000017820414,1.1782965e-7,0.00014354862,0.9552559,0.00033698918],"about_ca_topic_score_codex":0.008359298,"about_ca_topic_score_gemma":0.013482341,"teacher_disagreement_score":0.5886162,"about_ca_system_score_codex":0.00049267174,"about_ca_system_score_gemma":0.0005863908,"threshold_uncertainty_score":0.9999328},"labels":[],"label_agreement":null},{"id":"W4315567907","doi":"10.1038/s41597-022-01915-0","title":"A 30-year dataset of CO2 in flowing freshwaters in the United States","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"Ocean Acidification Effects and Responses","field":"Earth and Planetary Sciences","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 Winnipeg","funders":"Louisiana Board of Regents","keywords":"Alkalinity; Environmental science; Water quality; Carbon dioxide; Range (aeronautics); Water chemistry; Limnology; Ecosystem; Dissolved organic carbon; Oceanography; Freshwater ecosystem; Ecology; Environmental chemistry; Hydrology (agriculture); Chemistry; Biology; Geology; Environmental engineering","score_opus":0.06029442004987093,"score_gpt":0.2847824655910135,"score_spread":0.22448804554114257,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4315567907","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":[0.9321644,0.00003513207,0.0000043357527,0.000422838,0.000303737,0.00013428864,0.06685757,0.000013672002,0.000064057414],"genre_scores_gemma":[0.77493435,0.000031764233,0.00007437388,0.00008246501,0.000011232595,4.2449523e-7,0.22477823,0.0000015921355,0.00008553017],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9987862,0.0002246799,0.00020095294,0.00030349786,0.00027989896,0.00020477166],"domain_scores_gemma":[0.99865746,0.00035590545,0.00002919604,0.0009151102,0.000011760461,0.00003057723],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035283684,0.0000577139,0.000079794714,0.0004234515,0.00009469387,0.00014759607,0.0011571354,0.000019395191,0.00047916957],"category_scores_gemma":[0.00021585313,0.00003462296,0.000009203215,0.0020080854,0.0002015262,0.0002406675,0.00007373569,0.00007795209,0.0005051442],"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":[0.00006768412,0.00005770492,0.1758957,0.00007143291,0.000010418416,0.000081449056,0.0027965857,0.0147302365,0.00058605813,0.000042064286,0.80084634,0.0048143268],"study_design_scores_gemma":[0.00032370075,0.000028082415,0.40915787,0.00004743573,0.0000055779296,0.0000018197851,0.004143141,0.18562916,0.00022534373,0.00017625252,0.40014037,0.00012124855],"about_ca_topic_score_codex":0.0020564676,"about_ca_topic_score_gemma":0.0038523634,"teacher_disagreement_score":0.40070596,"about_ca_system_score_codex":0.0000014219688,"about_ca_system_score_gemma":0.000036141428,"threshold_uncertainty_score":0.6492775},"labels":[],"label_agreement":null},{"id":"W4315782561","doi":"10.1038/s41597-023-01935-4","title":"Interbasin water transfers in the United States and Canada","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"Water resources management and optimization","field":"Engineering","cited_by":49,"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":"U.S. Geological Survey; U.S. Department of the Interior; National Science Foundation","keywords":"Geospatial analysis; Water transfer; Water use; Water resource management; Environmental science; Environmental resource management; Hydrology (agriculture); Geography; Remote sensing; Ecology; Engineering","score_opus":0.02280844734738341,"score_gpt":0.19856969990625967,"score_spread":0.17576125255887626,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4315782561","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":[0.9980584,0.0000080629,0.00031055967,0.0005570717,0.0003370198,0.0000904643,0.00028418822,0.00006363665,0.00029061316],"genre_scores_gemma":[0.9829136,0.000030438336,0.000026437789,0.00007339292,0.0000100142515,0.0000034177958,0.015887072,0.000008292563,0.0010473435],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99956197,0.000013952615,0.00006392101,0.00012453235,0.00010329097,0.0001323366],"domain_scores_gemma":[0.9996578,0.000010430995,0.0000019198364,0.00031242502,0.0000040935606,0.000013292576],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033963245,0.000040371116,0.000029406156,0.000121346646,0.000049713548,0.00018580166,0.0003689846,0.000006868219,0.000014542881],"category_scores_gemma":[0.000003469277,0.00002454739,0.0000025222764,0.0003330134,0.000028239476,0.00011062516,0.000084735046,0.00003532445,0.000012372063],"study_design_candidate":"not_applicable","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":[0.0000030095923,0.0000050618496,0.0006461532,0.00007986846,0.000014814905,0.000027219887,0.0053377636,0.22467287,0.00020529226,0.000031301068,0.7668041,0.0021725465],"study_design_scores_gemma":[0.00009113418,0.0000017971694,0.00044735425,0.0000073830183,0.000003647864,2.6982897e-7,0.0007917533,0.61040455,0.00023079813,0.000030732157,0.38793957,0.000050976752],"about_ca_topic_score_codex":0.06566956,"about_ca_topic_score_gemma":0.47343004,"teacher_disagreement_score":0.4077605,"about_ca_system_score_codex":0.000012827466,"about_ca_system_score_gemma":0.0000040512286,"threshold_uncertainty_score":0.94055223},"labels":[],"label_agreement":null},{"id":"W4316097136","doi":"10.1038/s41597-022-01889-z","title":"Satellite-derived multivariate world-wide lake physical variable timeseries for climate studies","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"Marine and coastal ecosystems","field":"Earth and Planetary Sciences","cited_by":59,"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":"Centre for Ecology and Hydrology; Nanjing Institute of Geography and Limnology, Chinese Academy of Sciences; Università degli Studi di Perugia; National Centre for Earth Observation; Eesti Maaülikool; Fisheries and Oceans Canada; European Space Agency; Uppsala Universitet; Universidad del Valle; Technion-Israel Institute of Technology; European Commission; National Institute for Environmental Studies; Latvijas Universitate; University of Wisconsin-Madison; Università degli Studi di Trento; Suomen Ympäristökeskus; Tartu Ülikool; Agri-Food and Biosciences Institute; Centre National d’Etudes Spatiales; Environmental Protection Agency; Environment and Climate Change Canada; University of Stirling; Sight Research UK; Irkutsk State University; Compute Canada; University of Queensland; Natural Environment Research Council; U.S. Environmental Protection Agency; Nipissing University; KU Leuven; Creighton University","keywords":"Environmental science; Satellite imagery; Satellite; Latitude; Limnology; Climate change; Climatology; Longitude; Remote sensing; Physical geography; Geography; Oceanography; Geology","score_opus":0.08653126989409696,"score_gpt":0.30584255371121843,"score_spread":0.21931128381712148,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4316097136","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":[0.66379595,0.0026825657,0.0009431954,0.0037991346,0.03120671,0.004744336,0.21428184,0.0026587157,0.075887546],"genre_scores_gemma":[0.79377747,0.00028627197,0.0059416583,0.0002865496,0.0010375433,0.00004523401,0.1094358,0.00003670927,0.0891528],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979304,0.00006556239,0.00026374203,0.00081142195,0.00031412873,0.0006147383],"domain_scores_gemma":[0.99802065,0.0005682376,0.000093253584,0.0011044306,0.000097788536,0.00011566119],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001646202,0.00016951891,0.0002843664,0.00017052548,0.00066016475,0.00047740922,0.00095866306,0.000026031943,0.000593546],"category_scores_gemma":[0.00041427376,0.0001315999,0.00004909893,0.0011870179,0.00020555874,0.00071087916,0.0004797305,0.00007902416,0.0020757983],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039621114,0.00017833315,0.07645137,0.0016400564,0.0005046336,0.00006545732,0.0039140205,0.0019348832,0.0019733727,0.0023869965,0.74038917,0.17016546],"study_design_scores_gemma":[0.00030579767,0.000046183854,0.015862823,0.00004976852,0.000038185084,0.0000015555012,0.00084215857,0.08384367,0.00016457423,0.004228245,0.8943493,0.0002677391],"about_ca_topic_score_codex":0.00035950635,"about_ca_topic_score_gemma":0.022003531,"teacher_disagreement_score":0.16989774,"about_ca_system_score_codex":0.000002661174,"about_ca_system_score_gemma":0.00006911326,"threshold_uncertainty_score":0.9987012},"labels":[],"label_agreement":null},{"id":"W4316499895","doi":"10.1038/s41597-023-01945-2","title":"Author Correction: MIMIC-IV, a freely accessible electronic health record dataset","year":2023,"lang":"en","type":"erratum","venue":"Scientific Data","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":166,"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","funders":"","keywords":"Computer science; Electronic health record; Information retrieval; Health records; Data science; World Wide Web; Political science; Health care","score_opus":0.10061696061468166,"score_gpt":0.3922536860077259,"score_spread":0.29163672539304425,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4316499895","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000053741624,0.0045323255,0.04484897,0.044539265,0.7945916,0.0017710394,0.10330551,0.0029698918,0.0034359915],"genre_scores_gemma":[0.000017276552,0.00023063402,0.0060255895,0.0009453981,0.0018098805,0.000063871405,0.37049887,0.000112217975,0.6202963],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9884793,0.00091417966,0.0012141898,0.0051799756,0.001972671,0.0022396639],"domain_scores_gemma":[0.9806623,0.00030299186,0.0012102529,0.016925476,0.00027028928,0.00062872755],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.008393578,0.00068157853,0.0008828353,0.0011697718,0.0019679498,0.0041054445,0.023080623,0.0005194693,0.00036044169],"category_scores_gemma":[0.001627732,0.0006899359,0.0001182696,0.0049224054,0.00027873996,0.0020910741,0.011927613,0.004208623,0.0036908675],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003683687,0.000044203854,0.000053632724,0.00035558076,0.0000307128,0.000024591405,0.0001349244,0.000011869489,6.380936e-7,0.0003374119,0.92904985,0.06995292],"study_design_scores_gemma":[0.00011703074,0.000120368924,0.00021959489,0.00040115387,0.000015045678,0.000031413107,0.000024881178,0.1603359,7.383119e-7,0.0006766887,0.8375406,0.00051656517],"about_ca_topic_score_codex":0.0070494167,"about_ca_topic_score_gemma":0.023004806,"teacher_disagreement_score":0.7927818,"about_ca_system_score_codex":0.00069836114,"about_ca_system_score_gemma":0.010013485,"threshold_uncertainty_score":0.99956274},"labels":[],"label_agreement":null},{"id":"W4317500295","doi":"10.1038/s41597-022-01919-w","title":"The global historical climate database HCLIM","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"Tree-ring climate responses","field":"Earth and Planetary Sciences","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":"McGill University","funders":"European Commission; Sight Research UK; University of Bern; Natural Environment Research Council; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Precipitation; Environmental science; Climatology; Database; Climate change; Data collection; Series (stratigraphy); Meteorology; Geography; Computer science; Statistics; Mathematics; Geology","score_opus":0.08066699518869384,"score_gpt":0.29728364273494867,"score_spread":0.21661664754625481,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317500295","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":[0.66738415,0.0059896884,0.000109120985,0.0124619715,0.045259744,0.0008934013,0.23551983,0.0022053577,0.03017673],"genre_scores_gemma":[0.84827864,0.002013098,0.0025027294,0.0003508907,0.0010366887,0.00000712737,0.11819549,0.000030597053,0.027584733],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975268,0.00012795499,0.0002396399,0.0007510296,0.0006452346,0.0007093181],"domain_scores_gemma":[0.99668807,0.00048888335,0.00006800984,0.0025360067,0.000031911568,0.00018710163],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0031991866,0.00012106528,0.000110570385,0.000073048024,0.0013701231,0.0007733113,0.0025311194,0.000033905846,0.000495174],"category_scores_gemma":[0.0007778742,0.00007870807,0.000033725566,0.0014372449,0.00030980777,0.0005375677,0.00061156024,0.00010576163,0.011908115],"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":[0.00007279477,0.000015005367,0.16595897,0.000021388316,0.000011653314,0.000088704524,0.000029276234,0.00006521342,0.000033990087,0.00032540777,0.75482523,0.07855238],"study_design_scores_gemma":[0.000088820925,0.000012880039,0.20321834,0.0000102399745,0.000010411418,0.000012952605,0.0000752669,0.009086891,0.0000061371784,0.00026735698,0.78709847,0.00011225302],"about_ca_topic_score_codex":0.00076241646,"about_ca_topic_score_gemma":0.011058581,"teacher_disagreement_score":0.18089448,"about_ca_system_score_codex":0.000030904936,"about_ca_system_score_gemma":0.00011994833,"threshold_uncertainty_score":0.99992996},"labels":[],"label_agreement":null},{"id":"W4318617212","doi":"10.1038/s41597-023-01949-y","title":"Quality control and removal of technical variation of NMR metabolic biomarker data in ~120,000 UK Biobank participants","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":177,"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":"NIHR Cambridge Biomedical Research Centre; Economic and Social Research Council; Engineering and Physical Sciences Research Council; Chief Scientist Office, Scottish Government Health and Social Care Directorate; Medical Research Council; Public Health Agency; University of Cambridge; Department of Health and Social Care; Canadian Institutes of Health Research; Health and Social Care Research and Development Division; National Institute for Health and Care Research; Science and Technology Facilities Council; British Heart Foundation; Scottish Government; Dell EMC; Wellcome Trust","keywords":"Biobank; Biomarker; Biomarker discovery; Computer science; Computational biology; Medicine; Bioinformatics; Chemistry; Biology; Proteomics; Biochemistry","score_opus":0.10249251048695286,"score_gpt":0.36813642298749344,"score_spread":0.2656439125005406,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318617212","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":[0.98160446,0.0026561737,0.00064184563,0.00022594098,0.00040408582,0.00024314362,0.013927117,0.000010520143,0.00028669726],"genre_scores_gemma":[0.9938854,0.0004694638,0.0011773923,0.000014321882,0.00002728546,0.0000047039443,0.0042616655,0.0000068636036,0.00015288423],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9981838,0.00013058604,0.00045994885,0.00073702796,0.0002318826,0.00025676435],"domain_scores_gemma":[0.99731094,0.00005343437,0.00018220459,0.0023331782,0.000070820424,0.00004940393],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0044995816,0.00010022982,0.00031169388,0.00016548968,0.00005519288,0.000029498413,0.0008714815,0.000075610275,0.000017841165],"category_scores_gemma":[0.0016584323,0.0000874779,0.000024418847,0.00066648197,0.00032432657,0.000015238978,0.0017155753,0.000047012967,0.0000030332615],"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":[0.000080824444,0.00006964961,0.0063557024,0.000029721663,0.000077138015,0.0000020244509,0.000019685196,0.0000014419508,0.98508877,0.00096254353,0.005243624,0.002068878],"study_design_scores_gemma":[0.0016427026,0.0000657178,0.89156556,0.000022171864,0.00012529021,0.000007285072,0.00010931842,0.0024179565,0.025558854,0.0008202599,0.07741288,0.00025201362],"about_ca_topic_score_codex":0.00014447287,"about_ca_topic_score_gemma":0.00040095614,"teacher_disagreement_score":0.95952994,"about_ca_system_score_codex":0.0000031914315,"about_ca_system_score_gemma":0.000066822366,"threshold_uncertainty_score":0.35672453},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":[],"domain":null,"study_design":"bench_or_experimental","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W4318766583","doi":"10.1038/s41597-023-01977-8","title":"Reaction profiles for quantum chemistry-computed [3 + 2] cycloaddition reactions","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"Click Chemistry and Applications","field":"Chemistry","cited_by":48,"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":"Vetenskapsrådet","keywords":"Cycloaddition; Workflow; Click chemistry; Reactivity (psychology); Computer science; Chemistry; Computational chemistry; Quantum chemistry; Benchmarking; Reaction mechanism; Combinatorial chemistry; Computational science; Biochemical engineering; Organic chemistry; Database; Catalysis","score_opus":0.08451263699742557,"score_gpt":0.32619986212294105,"score_spread":0.2416872251255155,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318766583","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":[0.78884876,0.00008422316,0.006752533,0.007730248,0.0028433767,0.0011707663,0.13042529,0.005286829,0.056858007],"genre_scores_gemma":[0.57117724,0.0000148870095,0.00087805564,0.000013412237,0.0009958362,0.00049796526,0.35858783,0.0000469088,0.06778784],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982745,0.0000047736244,0.0002900007,0.0008917754,0.00023643053,0.0003025361],"domain_scores_gemma":[0.99738264,0.00016254837,0.00015026524,0.0020822603,0.00012083005,0.000101450394],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035592786,0.00013447338,0.00011350549,0.0000424209,0.000704694,0.00022111482,0.00083812175,0.000111427646,0.00064475613],"category_scores_gemma":[0.00038462097,0.00014669579,0.000058737558,0.00066989276,0.00015520194,0.0003074675,0.0002831463,0.00014530357,0.00038468197],"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":[0.0000057660245,0.00005656572,0.000008029189,0.0001378087,0.000010504172,6.8823005e-7,0.0000135841165,0.0000053829663,0.69203365,0.00016980738,0.30561584,0.0019423901],"study_design_scores_gemma":[0.00014916556,0.0000010475071,0.000055458655,0.000035503414,0.000019512527,0.000008928383,0.00015252696,0.014688356,0.44793472,0.0012535382,0.5355776,0.0001236694],"about_ca_topic_score_codex":0.000019010433,"about_ca_topic_score_gemma":0.000005808513,"teacher_disagreement_score":0.2440989,"about_ca_system_score_codex":0.00005099546,"about_ca_system_score_gemma":0.00007559488,"threshold_uncertainty_score":0.7059628},"labels":[],"label_agreement":null},{"id":"W4320038879","doi":"10.1038/s41597-022-01811-7","title":"The Psychological Science Accelerator’s COVID-19 rapid-response dataset","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"COVID-19 and Mental Health","field":"Psychology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal; Wilfrid Laurier University","funders":"National Cancer Institute; National Institute of Mental Health; Fundação para a Ciência e a Tecnologia; Japan Society for the Promotion of Science; Morsani College of Medicine; National Institutes of Health; Universidad de los Andes; Agentúra na Podporu Výskumu a Vývoja; Agence Nationale de la Recherche; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; National Research University Higher School of Economics; UK Research and Innovation; Agencia Nacional de Investigación y Desarrollo; Uniwersytet Wrocławski; Univerzita Karlova v Praze; Kingston University; Economic and Social Research Council; European Commission; Narodowym Centrum Nauki; Amazon Web Services","keywords":"Framing (construction); Coronavirus disease 2019 (COVID-19); Pandemic; Autonomy; Psychology; Framing effect; Raw data; Cognition; Psychological science; Social psychology; Medicine; Geography; Statistics; Mathematics; Psychiatry","score_opus":0.3940632159279168,"score_gpt":0.5637136789219475,"score_spread":0.16965046299403064,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4320038879","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":[0.6935516,0.0011787887,0.0002873046,0.055420324,0.04760533,0.0023250703,0.19433394,0.0012344437,0.00406319],"genre_scores_gemma":[0.898633,0.0001618676,0.00020214179,0.019684417,0.00048714064,0.00019090198,0.0527516,0.000052778934,0.027836164],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99514735,0.00051477033,0.00038156597,0.0019732274,0.0008842336,0.0010988589],"domain_scores_gemma":[0.9909966,0.0013192525,0.00011502116,0.0067729093,0.000052383657,0.00074385805],"candidate_categories":["sts","open_science","insufficient_payload"],"consensus_categories":["sts","insufficient_payload"],"category_scores_codex":[0.02138471,0.00017489384,0.00015199548,0.00035613327,0.0035408556,0.00087878865,0.0064492607,0.00007573976,0.0030839907],"category_scores_gemma":[0.0029016703,0.000117656484,0.000033877528,0.0036921292,0.0032698691,0.00047555633,0.002676366,0.00026611052,0.011178453],"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":[0.0003967617,0.00011314504,0.00023303593,0.0000094480865,0.0000060129237,0.00006028875,0.0004840936,6.067885e-7,0.0015622593,0.0014091547,0.9689191,0.026806079],"study_design_scores_gemma":[0.0005151353,0.00008057685,0.016846912,0.0000038981016,0.0000069635566,0.000024974455,0.0011416285,0.00016289543,0.000035125133,0.00041243684,0.98061925,0.0001502183],"about_ca_topic_score_codex":0.00022956566,"about_ca_topic_score_gemma":0.00022270647,"teacher_disagreement_score":0.20508137,"about_ca_system_score_codex":0.0002603788,"about_ca_system_score_gemma":0.0017181888,"threshold_uncertainty_score":0.99944264},"labels":[],"label_agreement":null},{"id":"W4320857731","doi":"10.1038/s41597-023-01942-5","title":"A longitudinal microstructural MRI dataset in healthy C57Bl/6 mice at 9.4 Tesla","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"Advanced Neuroimaging Techniques and Applications","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Robarts Clinical Trials; Western University","funders":"Congressionally Directed Medical Research Programs; Canada First Research Excellence Fund; Natural Sciences and Engineering Research Council of Canada; Government of Canada; U.S. Department of Defense","keywords":"Diffusion MRI; Fractional anisotropy; Magnetic resonance imaging; Neuroimaging; Human Connectome Project; Computer science; Magnetization transfer; Nuclear magnetic resonance; Artificial intelligence; Pattern recognition (psychology); Neuroscience; Radiology; Physics; Medicine; Biology; Functional connectivity","score_opus":0.20877625383579276,"score_gpt":0.4405094157300159,"score_spread":0.23173316189422313,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4320857731","genre_codex":"empirical","genre_gemma":"dataset","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":[0.75852835,0.00045274917,0.0012141388,0.036333025,0.0015108158,0.002204025,0.1979658,0.0011745648,0.0006165447],"genre_scores_gemma":[0.33945045,0.00019357551,0.04102847,0.0024082104,0.00024777924,0.000105195075,0.6042326,0.000079507874,0.012254194],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982534,0.000016982385,0.00022863499,0.0009159878,0.00022897596,0.0003560198],"domain_scores_gemma":[0.9973794,0.000048662554,0.000059382404,0.0023649507,0.000029901106,0.000117702475],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046656516,0.00010745064,0.00015064387,0.00020891846,0.00023901198,0.000068620335,0.0007104283,0.00002963683,0.000096315365],"category_scores_gemma":[0.000109782304,0.00009710446,0.000019037006,0.00120692,0.00025285923,0.00021245607,0.0013171331,0.00017343655,0.000494422],"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":[0.00004871532,0.000034350327,0.005901056,0.00003784656,0.000002565953,0.000051427323,0.000023443927,0.0000020868665,0.020857979,0.000076595876,0.9716401,0.0013238515],"study_design_scores_gemma":[0.0005339215,0.000038715858,0.03874206,0.000049607654,0.000016889338,0.00015701563,0.00002718625,0.0024614234,0.0019614352,0.00040996616,0.9554651,0.0001366939],"about_ca_topic_score_codex":0.000055581473,"about_ca_topic_score_gemma":0.00010405322,"teacher_disagreement_score":0.4190779,"about_ca_system_score_codex":0.0000637766,"about_ca_system_score_gemma":0.00007779725,"threshold_uncertainty_score":0.6354959},"labels":[],"label_agreement":null},{"id":"W4321076624","doi":"10.1038/s41597-023-01973-y","title":"GLORIA - A globally representative hyperspectral in situ dataset for optical sensing of water quality","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"Marine and coastal ecosystems","field":"Earth and Planetary Sciences","cited_by":143,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Environment and Climate Change Canada","funders":"Bundesministerium für Wirtschaft und Energie; Bundesministerium für Bildung und Forschung; U.S. Geological Survey; European Commission; Eesti Teadusagentuur; Horizon 2020 Framework Programme; Nuclear Safety and Security Commission; National Foundation for Science and Technology Development; National Aeronautics and Space Administration","keywords":"Hyperspectral imaging; Remote sensing; Water quality; Environmental science; In situ; Computer science; Geography; Ecology; Meteorology; Biology","score_opus":0.09523647153939807,"score_gpt":0.33412230150700406,"score_spread":0.238885829967606,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321076624","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":[0.8608541,0.000021860898,0.00015789796,0.00059469615,0.0015584088,0.00040993173,0.13156532,0.000034633526,0.0048031835],"genre_scores_gemma":[0.817582,0.0000020085415,0.0014645342,0.000023866769,0.00006875583,4.926835e-7,0.18032259,0.0000021666665,0.0005335528],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.998318,0.00006969779,0.0003192771,0.0005974269,0.00034057832,0.0003550325],"domain_scores_gemma":[0.9986945,0.00015452014,0.00004684099,0.0009875798,0.00003960551,0.000076953256],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028340023,0.00008104776,0.00017750001,0.00010192603,0.00010116504,0.00017042566,0.00070820586,0.000030611696,0.00020337207],"category_scores_gemma":[0.000251311,0.000058926944,0.000026720701,0.0004612972,0.00014917518,0.00040269044,0.0002911589,0.00005740402,0.00025391695],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000629151,0.00012463376,0.048464205,0.00044379555,0.00009829893,0.00015809467,0.0018851082,0.0006975196,0.035940398,0.0012330264,0.8519728,0.058352925],"study_design_scores_gemma":[0.0042445473,0.000516678,0.2718967,0.00019788285,0.0001225002,0.00006765944,0.015530696,0.22475669,0.034061458,0.017029386,0.42995933,0.0016164837],"about_ca_topic_score_codex":0.004891823,"about_ca_topic_score_gemma":0.04166069,"teacher_disagreement_score":0.42201352,"about_ca_system_score_codex":0.0000036439471,"about_ca_system_score_gemma":0.000057878155,"threshold_uncertainty_score":0.9758265},"labels":[],"label_agreement":null},{"id":"W4322764463","doi":"10.1038/s41597-023-02015-3","title":"The Three Terms Task - an open benchmark to compare human and artificial semantic representations","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Institut Universitaire de Gériatrie de Montréal","funders":"","keywords":"Computer science; Semantic memory; Natural language processing; Artificial intelligence; Semantic similarity; Task (project management); Benchmark (surveying); Word (group theory); Similarity (geometry); Associative property; Noun; Representation (politics); Cognition; Linguistics; Psychology; Mathematics","score_opus":0.14608141974920205,"score_gpt":0.4256313126982627,"score_spread":0.27954989294906063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4322764463","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":[0.17579252,0.0000860263,0.7963852,0.01414136,0.002382418,0.0032222548,0.001645191,0.0021539766,0.004191012],"genre_scores_gemma":[0.95876473,0.00000442477,0.035988793,0.00013659403,0.00008868626,0.000082386985,0.0026092445,0.000018263043,0.0023068846],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99752355,0.00008811398,0.0003051647,0.0012752996,0.00045103062,0.000356831],"domain_scores_gemma":[0.99381554,0.000117021176,0.000096965574,0.005727247,0.00008674231,0.00015651232],"candidate_categories":["sts","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.00216942,0.00012079532,0.00015365459,0.00022370304,0.0022210635,0.0049931067,0.009421047,0.000016429882,0.000013556624],"category_scores_gemma":[0.00017966355,0.00009184183,0.000018841112,0.0021587822,0.00031119288,0.0022756506,0.010258335,0.00009851468,0.00014605575],"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":[0.000007401924,0.0001555034,0.0041626533,0.000013214506,0.000055631972,0.000041013664,0.0018290624,0.0001677357,0.037545882,0.17699577,0.60323256,0.17579354],"study_design_scores_gemma":[0.00021829121,0.00009994993,0.06902393,0.00006365542,0.00005082445,0.000012466074,0.0007002301,0.26270416,0.0032574972,0.52527076,0.13786203,0.00073616207],"about_ca_topic_score_codex":0.00020267874,"about_ca_topic_score_gemma":0.009899545,"teacher_disagreement_score":0.7829722,"about_ca_system_score_codex":0.000017378894,"about_ca_system_score_gemma":0.00004476262,"threshold_uncertainty_score":0.9990779},"labels":[],"label_agreement":null},{"id":"W4324344293","doi":"10.1038/s41597-023-02059-5","title":"Newly reconstructed Arctic surface air temperatures for 1979–2021 with deep learning method","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"Arctic and Antarctic ice dynamics","field":"Earth and Planetary 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":"National Centers for Environmental Information; National Oceanic and Atmospheric Administration; Norges Forskningsråd; Alberta Agricultural Research Institute; U.S. Department of Energy","keywords":"Arctic; The arctic; Environmental science; Surface air temperature; Oceanography; Geology; Climate change","score_opus":0.0260754778403675,"score_gpt":0.2633308319054671,"score_spread":0.23725535406509957,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4324344293","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":[0.90159774,0.00047242368,0.06429287,0.0037228807,0.0094082225,0.0019354769,0.013772866,0.0008572916,0.00394024],"genre_scores_gemma":[0.8098704,0.00003710815,0.1466729,0.00012944834,0.00016991167,0.0000020520781,0.034842737,0.000015663418,0.008259737],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977637,0.0001336635,0.00022959545,0.00091528794,0.00038943984,0.0005683157],"domain_scores_gemma":[0.99807084,0.00060175185,0.00010872277,0.00092967355,0.00012545749,0.00016356616],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001956078,0.00017964336,0.00021131335,0.00012616483,0.0010091658,0.00036861296,0.00095531554,0.000059909915,0.0009281278],"category_scores_gemma":[0.00043165666,0.00013516861,0.00004258376,0.001204847,0.0003144826,0.0005768696,0.00012221135,0.00026251076,0.00039624106],"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":[0.00040583897,0.000057935584,0.45620748,0.00043993426,0.00031477565,0.00014250677,0.0023339228,0.13649042,0.0007228154,0.0006208495,0.036912337,0.36535117],"study_design_scores_gemma":[0.0007185561,0.00015714046,0.05189404,0.00009769289,0.00009655614,0.00011848012,0.004312989,0.8071802,0.00005386373,0.001269559,0.13358493,0.000515974],"about_ca_topic_score_codex":0.00070119486,"about_ca_topic_score_gemma":0.0025789293,"teacher_disagreement_score":0.6706898,"about_ca_system_score_codex":0.0000065714007,"about_ca_system_score_gemma":0.00016332287,"threshold_uncertainty_score":0.99998516},"labels":[],"label_agreement":null},{"id":"W4327811479","doi":"10.1038/s41597-023-02048-8","title":"A dataset of rodent cerebrovasculature from in vivo multiphoton fluorescence microscopy imaging","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre","funders":"CIHR Skin Research Training Centre; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; U.S. Department of Health and Human Services; National Institutes of Health; Government of Canada; Japan Agency for Medical Research and Development","keywords":"Fluorescence; Microscopy; Multiphoton fluorescence microscope; Fluorescence microscope; In vivo; Fluorescence-lifetime imaging microscopy; Rodent; Chemistry; Optics; Biology; Physics; Ecology","score_opus":0.015508928196742267,"score_gpt":0.3055314629526942,"score_spread":0.2900225347559519,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4327811479","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":[0.9457778,0.00065921014,0.00069054874,0.00006993338,0.00024846967,0.00031017602,0.052110214,0.000043365257,0.000090287016],"genre_scores_gemma":[0.61301124,0.00021602062,0.011034129,0.000087207605,0.000079123434,0.0000139483745,0.3746822,0.000030374731,0.0008457333],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99837136,0.00004518358,0.00025306482,0.00089579634,0.00021657183,0.00021805047],"domain_scores_gemma":[0.9967543,0.000010820336,0.00008562667,0.0030584675,0.000048450263,0.0000423702],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007497356,0.00010880086,0.00013964316,0.00015368154,0.000050891165,0.00009596267,0.0013568007,0.000053705728,0.000071323775],"category_scores_gemma":[0.00016064286,0.00010632887,0.000044445085,0.0005510095,0.00019515988,0.000020586813,0.001637176,0.00007645874,0.000035354828],"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":[0.00000614817,0.000025601785,0.0032513544,0.0000071393083,0.00001089439,0.00000488514,0.000018479166,0.0000045221436,0.6566638,1.9472604e-7,0.33939183,0.0006152055],"study_design_scores_gemma":[0.0001622572,0.0000039961988,0.0012374265,0.000027420774,0.000017240534,8.9273215e-7,0.000053591702,0.004362302,0.8524463,0.000017718727,0.14156461,0.00010621987],"about_ca_topic_score_codex":0.00085982354,"about_ca_topic_score_gemma":0.0009657692,"teacher_disagreement_score":0.33276653,"about_ca_system_score_codex":0.000009252812,"about_ca_system_score_gemma":0.00005184849,"threshold_uncertainty_score":0.43359655},"labels":[],"label_agreement":null},{"id":"W4328048033","doi":"10.1038/s41597-023-02030-4","title":"A synthetic population for agent-based modelling in Canada","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"demographic modeling and climate adaptation","field":"Decision Sciences","cited_by":37,"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":"Economic and Social Research Council; Research Councils UK","keywords":"Population; Computer science; Data science; Demography; Sociology","score_opus":0.4265268679097579,"score_gpt":0.4053863315042952,"score_spread":0.021140536405462707,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4328048033","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":[0.77740574,0.00004170224,0.21514471,0.00084778393,0.0029002796,0.0003786152,0.0030939912,0.000068614194,0.00011857467],"genre_scores_gemma":[0.9934009,0.0000014779366,0.0021608258,0.000046122856,0.000014682442,0.00001574572,0.0036999579,0.000007673126,0.00065263244],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971204,0.00007000267,0.0005032237,0.0008525428,0.0011662592,0.00028760676],"domain_scores_gemma":[0.9974605,0.00061450293,0.00012224565,0.0016030229,0.00013322313,0.00006649303],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0068738065,0.00007498299,0.0001309045,0.00053230324,0.00024448946,0.00042427858,0.0012394194,0.000024320274,0.000037659847],"category_scores_gemma":[0.0012035823,0.00006338184,0.000031270527,0.0022994252,0.00003384582,0.0003167137,0.00013985398,0.000047497433,0.00008442841],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013107008,0.000013332891,0.0029420923,0.000009076386,0.0000020174155,0.0000031910315,0.0000701288,0.92023957,0.000045996167,0.00025428814,0.046590652,0.02981653],"study_design_scores_gemma":[0.00017424439,0.0000028940065,0.0017534682,0.000018518802,0.0000042542038,1.9536229e-7,0.00044875502,0.9808065,0.000010574274,0.00936939,0.0073339245,0.00007724543],"about_ca_topic_score_codex":0.36568558,"about_ca_topic_score_gemma":0.8337536,"teacher_disagreement_score":0.46806797,"about_ca_system_score_codex":0.00009942504,"about_ca_system_score_gemma":0.00064900285,"threshold_uncertainty_score":0.63853836},"labels":[],"label_agreement":null},{"id":"W4362664032","doi":"10.1038/s41597-023-01946-1","title":"Data and Tools Integration in the Canadian Open Neuroscience Platform","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Douglas Mental Health University Institute; Robarts Clinical Trials; Concordia University; McGill University and Génome Québec Innovation Centre; Indoc Research; Ontario Brain Institute; Krembil Foundation; McGill University Health Centre; McGill University; University of Toronto; Western University; McGill Genome Centre; Montreal Neurological Institute and Hospital","funders":"Institut de Cardiologie de Montréal; University of Toronto; McGill University; Simon Fraser University; National Institutes of Health; Canada First Research Excellence Fund; Canada Research Chairs; Health Canada; Government of Ontario; Concordia University; Réseau en Bio-Imagerie du Quebec; Compute Canada; National Institute of Mental Health; Ontario Brain Institute; Fondation Brain Canada; National Institute of Biomedical Imaging and Bioengineering; Université Laval","keywords":"Computer science; Metadata; Data sharing; World Wide Web; Reuse; Data science; Software; Open science; Point (geometry); Data management; Open data; Database; Operating system","score_opus":0.7302211163254171,"score_gpt":0.4968576880176869,"score_spread":0.23336342830773016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362664032","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":[0.52941686,0.00027902835,0.011635363,0.115069106,0.057432793,0.008139371,0.14615828,0.0005421855,0.131327],"genre_scores_gemma":[0.9771547,0.000005776521,0.0007610906,0.0011044778,0.000058291702,0.0000096151925,0.012829768,0.0000069599882,0.008069345],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.994411,0.0001901528,0.00050574885,0.0024683955,0.0019257542,0.0004989718],"domain_scores_gemma":[0.9862486,0.00081016193,0.00012355922,0.012543396,0.00009633347,0.00017791157],"candidate_categories":["metaresearch","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["metaresearch","open_science"],"category_scores_codex":[0.06029262,0.000111170455,0.00013878004,0.00085434545,0.0015194195,0.03471262,0.033373933,0.000030013389,0.00007803613],"category_scores_gemma":[0.0146096675,0.00006771267,0.000010495278,0.006975681,0.00052409194,0.0068977177,0.01908664,0.00016500047,0.0007961924],"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":[0.0000013625919,0.0000097945185,0.00050238136,7.822631e-7,4.4093682e-7,0.000015086892,0.0003981706,0.000020305146,0.0000273337,0.0017213629,0.78014326,0.2171597],"study_design_scores_gemma":[0.000089847745,0.0000062152426,0.046390872,0.000011993604,0.000002689925,0.000005276612,0.0026249571,0.22019933,0.000002505424,0.0044986196,0.72607887,0.00008880854],"about_ca_topic_score_codex":0.018095978,"about_ca_topic_score_gemma":0.62701565,"teacher_disagreement_score":0.6089197,"about_ca_system_score_codex":0.000031964784,"about_ca_system_score_gemma":0.0004251864,"threshold_uncertainty_score":0.9999818},"labels":[],"label_agreement":null},{"id":"W4362673363","doi":"10.1038/s41597-023-02069-3","title":"Author Correction: GLORIA - A globally representative hyperspectral in situ dataset for optical sensing of water quality","year":2023,"lang":"en","type":"erratum","venue":"Scientific Data","topic":"Water Quality Monitoring and Analysis","field":"Environmental 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":"Environment and Climate Change Canada","funders":"","keywords":"Hyperspectral imaging; In situ; Remote sensing; Environmental science; Water quality; Quality (philosophy); Geography; Biology; Physics; Ecology; Meteorology","score_opus":0.12555651376025498,"score_gpt":0.38843788958646935,"score_spread":0.2628813758262144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362673363","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0587382,0.00015159782,0.003473966,0.009627917,0.45148918,0.0030348909,0.46312207,0.00045894063,0.009903224],"genre_scores_gemma":[0.010744394,0.00000988192,0.0076862955,0.00003076545,0.0016885955,0.000018675823,0.5272604,0.000074891,0.45248607],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99522585,0.0002550535,0.0008096938,0.0019287452,0.0011436604,0.00063698913],"domain_scores_gemma":[0.9964193,0.00018433717,0.00021930049,0.0029862884,0.000041538144,0.00014920562],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0057446705,0.00028627456,0.0005859598,0.00016888764,0.00027028,0.00037155047,0.0018319037,0.00023996814,0.00014477568],"category_scores_gemma":[0.00093125884,0.0002324175,0.00013157203,0.00083637284,0.0007953548,0.00045004996,0.0026004943,0.00043803558,0.0004252617],"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":[0.000039810402,0.00008201332,0.00009081037,0.00006378777,0.000054185126,0.000016491722,0.000591998,0.00006752386,0.01354822,0.000007886574,0.9848863,0.000550962],"study_design_scores_gemma":[0.00070089026,0.000097601056,0.0023330091,0.00033223612,0.00038997488,0.0000113284,0.003239369,0.0055230428,0.030628845,0.001360787,0.95432365,0.0010592748],"about_ca_topic_score_codex":0.0044946875,"about_ca_topic_score_gemma":0.002192731,"teacher_disagreement_score":0.4498006,"about_ca_system_score_codex":0.0002850349,"about_ca_system_score_gemma":0.00007832387,"threshold_uncertainty_score":0.947771},"labels":[],"label_agreement":null},{"id":"W4362717754","doi":"10.1038/s41597-023-02096-0","title":"A standardized catalogue of spectral indices to advance the use of remote sensing in Earth system research","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"Remote Sensing in Agriculture","field":"Environmental Science","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":"Artificial Intelligence in Medicine (Canada)","funders":"European Space Agency; Deutsche Forschungsgemeinschaft; Niedersächsische Ministerium für Wissenschaft und Kultur","keywords":"Remote sensing; Information retrieval; Earth (classical element); Computer science; Geography; Astronomy; Physics","score_opus":0.12454228153508677,"score_gpt":0.3377334745517816,"score_spread":0.2131911930166948,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362717754","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":[0.99604857,0.00001565117,0.00045769615,0.00035197663,0.00050330814,0.0005144236,0.0015890563,0.000037523885,0.00048180218],"genre_scores_gemma":[0.9560963,0.000008480184,0.041281413,0.000014724154,0.00003607362,1.75755e-7,0.0007493601,0.000015766429,0.001797709],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9970888,0.0002879249,0.00032297464,0.00065242994,0.0012340895,0.00041380015],"domain_scores_gemma":[0.99753267,0.00024733183,0.00010730276,0.001991744,0.000047865662,0.000073064795],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0047666337,0.00009154329,0.00018340617,0.00017905004,0.00020949266,0.00014109287,0.0011418243,0.000041488875,0.000013516132],"category_scores_gemma":[0.0008260574,0.000059178234,0.00002532005,0.004012215,0.0007641519,0.0003659681,0.0017422071,0.00020601298,0.00021680549],"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":[0.00018680317,0.00006313789,0.0020443716,0.00024963057,0.000031812728,0.0001841287,0.010911196,0.021956684,0.5287579,0.00011424435,0.29780808,0.13769199],"study_design_scores_gemma":[0.001065938,0.00015741706,0.14520001,0.0019554538,0.000034003584,0.0000910727,0.009645891,0.21729854,0.11816466,0.00053562643,0.50516564,0.0006857265],"about_ca_topic_score_codex":0.0030468833,"about_ca_topic_score_gemma":0.010627348,"teacher_disagreement_score":0.41059327,"about_ca_system_score_codex":0.000104776875,"about_ca_system_score_gemma":0.000042553755,"threshold_uncertainty_score":0.5930309},"labels":[],"label_agreement":null},{"id":"W4365515241","doi":"10.1038/s41597-023-02106-1","title":"Open science and data sharing in cognitive neuroscience with MouseBytes and MouseBytes+","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","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":"Robarts Clinical Trials; Western University","funders":"Canadian Open Neuroscience Platform; Canada First Research Excellence Fund","keywords":"Open science; Cognitive neuroscience; Neuroinformatics; Cognition; Neuroscience; Open data; Cognitive science; Data sharing; Psychology; Data science; Computer science; World Wide Web; Medicine; Physics","score_opus":0.19230217751921452,"score_gpt":0.4030885047671502,"score_spread":0.21078632724793567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4365515241","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":[0.9966497,0.00029976168,0.0001829304,0.00058583356,0.00021077316,0.00023166189,0.0014425312,0.00003176934,0.0003650609],"genre_scores_gemma":[0.99575794,0.00011255632,0.0014713536,0.00017238925,0.000023198418,0.000008157179,0.001430603,0.0000094333245,0.0010143917],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9973301,0.000020369122,0.000115834824,0.0018987702,0.00030374376,0.00033115665],"domain_scores_gemma":[0.99780476,0.000034095843,0.000052129362,0.0019282742,0.00006526532,0.00011545114],"candidate_categories":["sts","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0033287643,0.00009394969,0.00010039216,0.00013426761,0.00035743642,0.000895615,0.0054251775,0.000039522678,0.0000027995318],"category_scores_gemma":[0.003269489,0.000072926894,0.000002521662,0.0010341551,0.0031177923,0.0000769026,0.024622725,0.00007851523,0.000004250608],"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":[0.00016166865,0.0001765201,0.097942635,0.000086385335,0.000019262448,0.00009759078,0.0006716121,0.000007823835,0.59787416,0.0001543954,0.06856705,0.2342409],"study_design_scores_gemma":[0.0049264757,0.0010552829,0.49748978,0.00068406214,0.000085870626,0.00026927298,0.007828268,0.10064467,0.078633785,0.00083794835,0.30559555,0.0019490505],"about_ca_topic_score_codex":0.00007132318,"about_ca_topic_score_gemma":0.00037739036,"teacher_disagreement_score":0.5192404,"about_ca_system_score_codex":0.000004320046,"about_ca_system_score_gemma":0.00025063782,"threshold_uncertainty_score":0.99995595},"labels":[],"label_agreement":null},{"id":"W4366086895","doi":"10.1038/s41597-023-02094-2","title":"CarbonMonitor-Power near-real-time monitoring of global power generation on hourly to daily scales","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"Atmospheric and Environmental Gas Dynamics","field":"Environmental Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hudbay Minerals (Canada); University of Toronto","funders":"China Postdoctoral Science Foundation; Tsinghua University; National Natural Science Foundation of China","keywords":"Renewable energy; Environmental science; Wind power; Solar power; Meteorology; Electricity generation; Range (aeronautics); Fossil fuel; Climatology; Geography; Power (physics); Ecology; Engineering","score_opus":0.021934896263920173,"score_gpt":0.2620825650098672,"score_spread":0.24014766874594703,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366086895","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":[0.99383086,0.0000064048886,0.00029111965,0.0001210238,0.0015436555,0.00019384238,0.00066200015,0.0000848408,0.0032662307],"genre_scores_gemma":[0.9859082,0.0000056411163,0.009789058,0.000021667578,0.000059142254,0.00000709408,0.00043676698,0.000020344976,0.003752095],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9976859,0.000038553982,0.00025192506,0.0008379953,0.00078611105,0.00039951078],"domain_scores_gemma":[0.9981986,0.000019077492,0.00007867509,0.0015047205,0.000005979216,0.000192945],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00056578947,0.0001730654,0.00015319893,0.000010721423,0.00030061434,0.00016841714,0.0010600537,0.00006495989,0.0005979319],"category_scores_gemma":[0.0000428575,0.00016395104,0.00004019163,0.00086169736,0.0004335286,0.0003686088,0.0013551019,0.00006870826,0.0039188922],"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":[0.00005392984,0.00029865664,0.42340055,0.0000069270463,0.00003797194,0.00003054274,0.0009076884,0.14825137,0.23846757,0.000077514545,0.17055373,0.017913543],"study_design_scores_gemma":[0.0002720558,0.00016504257,0.9471959,0.000027732322,0.000020080684,0.0000028743975,0.0004751853,0.033668865,0.0021518504,0.00006823843,0.015523539,0.00042866287],"about_ca_topic_score_codex":0.00039980625,"about_ca_topic_score_gemma":0.000038992664,"teacher_disagreement_score":0.5237953,"about_ca_system_score_codex":0.00027163938,"about_ca_system_score_gemma":0.000016903943,"threshold_uncertainty_score":0.9968567},"labels":[],"label_agreement":null},{"id":"W4366280062","doi":"10.1038/s41597-023-02136-9","title":"Author Correction: MIMIC-IV, a freely accessible electronic health record dataset","year":2023,"lang":"en","type":"erratum","venue":"Scientific Data","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":146,"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","funders":"","keywords":"Electronic health record; Computer science; Information retrieval; Health records; World Wide Web; Data science; Health care; Political science","score_opus":0.10061696061468166,"score_gpt":0.3922536860077259,"score_spread":0.29163672539304425,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366280062","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000053741624,0.0045323255,0.04484897,0.044539265,0.7945916,0.0017710394,0.10330551,0.0029698918,0.0034359915],"genre_scores_gemma":[0.000017276552,0.00023063402,0.0060255895,0.0009453981,0.0018098805,0.000063871405,0.37049887,0.000112217975,0.6202963],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9884793,0.00091417966,0.0012141898,0.0051799756,0.001972671,0.0022396639],"domain_scores_gemma":[0.9806623,0.00030299186,0.0012102529,0.016925476,0.00027028928,0.00062872755],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.008393578,0.00068157853,0.0008828353,0.0011697718,0.0019679498,0.0041054445,0.023080623,0.0005194693,0.00036044169],"category_scores_gemma":[0.001627732,0.0006899359,0.0001182696,0.0049224054,0.00027873996,0.0020910741,0.011927613,0.004208623,0.0036908675],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003683687,0.000044203854,0.000053632724,0.00035558076,0.0000307128,0.000024591405,0.0001349244,0.000011869489,6.380936e-7,0.0003374119,0.92904985,0.06995292],"study_design_scores_gemma":[0.00011703074,0.000120368924,0.00021959489,0.00040115387,0.000015045678,0.000031413107,0.000024881178,0.1603359,7.383119e-7,0.0006766887,0.8375406,0.00051656517],"about_ca_topic_score_codex":0.0070494167,"about_ca_topic_score_gemma":0.023004806,"teacher_disagreement_score":0.7927818,"about_ca_system_score_codex":0.00069836114,"about_ca_system_score_gemma":0.010013485,"threshold_uncertainty_score":0.99956274},"labels":[],"label_agreement":null},{"id":"W4366824320","doi":"10.1038/s41597-023-02082-6","title":"Three-Dimensional Motion Capture Data of a Movement Screen from 183 Athletes","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"Sports Performance and Training","field":"Medicine","cited_by":16,"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 Ottawa","funders":"China Scholarship Council; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Motion capture; Athletes; Movement (music); Motion (physics); Computer science; Physical medicine and rehabilitation; Artificial intelligence; Medicine; Physics; Physical therapy; Acoustics","score_opus":0.12092658849877143,"score_gpt":0.3219926699935155,"score_spread":0.2010660814947441,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366824320","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":[0.9713471,0.00042636722,0.0002761302,0.0008367983,0.0014123877,0.00035696465,0.02478228,0.00013453633,0.0004274716],"genre_scores_gemma":[0.7332964,0.000010712688,0.003036063,0.0002452078,0.00023121978,0.0000031935142,0.26194587,0.000017642009,0.0012136869],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99815065,0.0000038253793,0.00025402402,0.0007237323,0.000645681,0.00022207372],"domain_scores_gemma":[0.99639666,0.000022904698,0.00008951034,0.0033366573,0.00007297603,0.00008128437],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010832859,0.00009611892,0.00017878319,0.00015529335,0.00012243673,0.000044132965,0.0008171037,0.000044997498,0.00053275307],"category_scores_gemma":[0.000074539785,0.000077676516,0.000023088423,0.00055416557,0.0001699155,0.00043476376,0.0012967294,0.00011029843,0.0002718873],"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":[0.000091319045,0.0002162313,0.13800985,0.000082730054,0.0001755742,0.00009012221,0.00042355698,0.000057207166,0.013197195,0.000112566035,0.7861143,0.061429407],"study_design_scores_gemma":[0.0016679286,0.000050631243,0.7446491,0.0005687299,0.00023770132,0.0000058228484,0.00054640457,0.19282672,0.0019383943,0.00074782287,0.056521013,0.00023974368],"about_ca_topic_score_codex":0.00074203586,"about_ca_topic_score_gemma":0.00044001895,"teacher_disagreement_score":0.7295932,"about_ca_system_score_codex":0.000011088573,"about_ca_system_score_gemma":0.00012613808,"threshold_uncertainty_score":0.58332723},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"observational","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W4367312806","doi":"10.1038/s41597-023-02137-8","title":"Author Correction: An analysis-ready and quality controlled resource for pediatric brain white-matter research","year":2023,"lang":"en","type":"erratum","venue":"Scientific Data","topic":"Neonatal and fetal brain pathology","field":"Medicine","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; Université de Montréal; Institut Universitaire en Santé Mentale de Québec; Western University; Polytechnique Montréal; Concordia University; University of Toronto","funders":"","keywords":"White matter; Resource (disambiguation); White paper; Quality (philosophy); White (mutation); Psychology; Computer science; Data science; Medicine; Geography; Biology; Physics; Archaeology","score_opus":0.18463636716419232,"score_gpt":0.44278307247781695,"score_spread":0.2581467053136246,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367312806","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01387956,0.0136450585,0.005033059,0.13265471,0.42527515,0.027069097,0.27923527,0.0021391553,0.101068944],"genre_scores_gemma":[0.000519707,0.000014221277,0.0001963768,0.000487307,0.002681254,0.00013196954,0.16254735,0.000060295235,0.8333615],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99311405,0.00096459646,0.0008819976,0.0028550588,0.001340929,0.00084337854],"domain_scores_gemma":[0.9918798,0.0021588136,0.00033351532,0.00449788,0.00066569477,0.00046425822],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.019936606,0.00036021462,0.00146397,0.002193806,0.0008492777,0.00052018097,0.0013008551,0.00061896787,0.00041852344],"category_scores_gemma":[0.0074830246,0.00029231436,0.00023154875,0.0033184886,0.0008552925,0.0002532563,0.0013946892,0.001402382,0.00047199885],"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":[0.0007718445,0.00013662482,0.0025916833,0.0004425319,0.00026779505,0.000044316865,0.00026682595,8.8916835e-7,0.000027729857,0.000030740088,0.99425405,0.0011649493],"study_design_scores_gemma":[0.0025257561,0.00026735454,0.023798916,0.000048285827,0.0015861503,0.00003129333,0.00070965063,0.004007191,0.0000015347571,0.00014834301,0.9665437,0.00033187316],"about_ca_topic_score_codex":0.00014260394,"about_ca_topic_score_gemma":0.0010407093,"teacher_disagreement_score":0.7322926,"about_ca_system_score_codex":0.00007577292,"about_ca_system_score_gemma":0.00054376246,"threshold_uncertainty_score":0.9999529},"labels":[],"label_agreement":null},{"id":"W4367314599","doi":"10.1038/s41597-023-02104-3","title":"Network Analysis of Academic Medical Center Websites in the United States","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"Web visibility and informetrics","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Office of Science; U.S. Department of Energy","keywords":"Centrality; Computer science; World Wide Web; Network analysis; Data science; Identification (biology); Health care; Key (lock); Web resource; Resource (disambiguation); Information retrieval; Web page; Computer security; Computer network; Political science; Engineering","score_opus":0.09259889426856219,"score_gpt":0.34146165408168183,"score_spread":0.24886275981311964,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367314599","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":[0.915919,0.00027011437,0.06316316,0.012503177,0.0031945258,0.00048399143,0.0028291899,0.0003188503,0.0013179572],"genre_scores_gemma":[0.9569788,0.0003073951,0.00307555,0.0039089513,0.00014949738,0.000010306033,0.034571107,0.000010636286,0.0009877604],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997596,0.00014854211,0.00039537434,0.000481477,0.0010447396,0.00033386878],"domain_scores_gemma":[0.996641,0.00064675644,0.000092234026,0.0024858215,0.00006710346,0.000067086425],"candidate_categories":["bibliometrics","open_science"],"consensus_categories":[],"category_scores_codex":[0.009518505,0.00007001553,0.00015567442,0.0013778101,0.00013092541,0.00024372364,0.007098274,0.000064943335,0.000083935054],"category_scores_gemma":[0.001052184,0.00004618333,0.000042404612,0.037435383,0.0002514191,0.00070622837,0.0022467927,0.00024874922,0.00015466544],"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":[0.0000044891613,0.000091236514,0.10608199,0.000023561717,0.000103186714,0.0000131970655,0.0019104127,0.006988735,0.000007968812,0.009485473,0.8683748,0.006914926],"study_design_scores_gemma":[0.00009259104,0.000008201653,0.049007982,0.00001502247,0.000018985642,6.424832e-7,0.00013220409,0.8379676,0.0000068118784,0.0015483979,0.11114162,0.000059975075],"about_ca_topic_score_codex":0.00008818198,"about_ca_topic_score_gemma":0.0002055188,"teacher_disagreement_score":0.8309788,"about_ca_system_score_codex":0.000011533926,"about_ca_system_score_gemma":0.00010288795,"threshold_uncertainty_score":0.9982738},"labels":[],"label_agreement":null},{"id":"W4368360783","doi":"10.1038/s41597-023-02160-9","title":"A dataset of direct observations of sea ice drift and waves in ice","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"Arctic and Antarctic ice dynamics","field":"Earth and Planetary Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Environment and Climate Change Canada; Centre For Cold Ocean Resources Engineering","funders":"Norges Forskningsråd; U.S. Department of Defense","keywords":"Sea ice; Drift ice; Sea ice thickness; Geology; Arctic ice pack; Antarctic sea ice; Sea ice concentration; Cryosphere; Lead (geology); Breakup; Sea ice growth processes; Climatology; Oceanography; Physics; Geomorphology","score_opus":0.06736690355056935,"score_gpt":0.26852421829017853,"score_spread":0.20115731473960918,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4368360783","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":[0.8508224,0.000067488996,0.00002280724,0.00024352105,0.00035686677,0.00010068222,0.14782389,0.000012664594,0.00054968713],"genre_scores_gemma":[0.8841481,0.000067931454,0.0015201307,0.000031182037,0.000012643637,2.5816954e-7,0.11378468,0.0000017408777,0.00043333948],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9990135,0.000040632898,0.00022631863,0.00032253037,0.00022971064,0.00016732333],"domain_scores_gemma":[0.9988877,0.00023857712,0.00008035332,0.0007185096,0.000027245285,0.000047576097],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012130591,0.00005827153,0.00012264156,0.0001304468,0.00010073299,0.000039252795,0.00056601234,0.00002318073,0.00016175486],"category_scores_gemma":[0.00025723685,0.000049118717,0.000009553936,0.0009026103,0.0003285011,0.00045343937,0.00017019543,0.000055928114,0.000037900627],"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":[0.000015729995,0.00003639711,0.915242,0.0001475013,0.00001672264,0.000011657145,0.000641415,0.00042528982,0.00032081598,0.000100379475,0.06913516,0.013906888],"study_design_scores_gemma":[0.0001381475,0.000018820107,0.8266649,0.00004502082,0.00001627151,0.0000027971741,0.0008381006,0.13522029,0.000035437704,0.0002851838,0.03664747,0.000087543085],"about_ca_topic_score_codex":0.0033125905,"about_ca_topic_score_gemma":0.008405308,"teacher_disagreement_score":0.13479501,"about_ca_system_score_codex":9.76777e-7,"about_ca_system_score_gemma":0.00006894779,"threshold_uncertainty_score":0.5007668},"labels":[],"label_agreement":null},{"id":"W4375850863","doi":"10.1038/s41597-023-02171-6","title":"Haplotype-resolved genome assembly of Coriaria nepalensis a non-legume nitrogen-fixing shrub","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"Legume Nitrogen Fixing Symbiosis","field":"Agricultural and Biological Sciences","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":"Université Laval; University of British Columbia","funders":"National Natural Science Foundation of China","keywords":"Biology; Genome; Contig; Frankia; Botany; Sequence assembly; Nitrogen fixation; Whole genome sequencing; Gene; Genetics; Root nodule; Bacteria; Transcriptome","score_opus":0.04886845499612701,"score_gpt":0.2565052895636224,"score_spread":0.20763683456749538,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4375850863","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":[0.99191076,0.00012288729,0.0000057522025,0.00062028394,0.0014899953,0.00032133094,0.0046414975,0.00027443998,0.0006130302],"genre_scores_gemma":[0.99069214,0.0000074263176,0.00043123923,0.0000679843,0.000306238,0.000012882899,0.007106808,0.0000049877285,0.0013703062],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99674624,0.00010482359,0.0004997735,0.0011941243,0.0007494068,0.0007056295],"domain_scores_gemma":[0.99814075,0.00025651735,0.00022897442,0.0009694819,0.0002049858,0.00019930709],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0020252168,0.00023977683,0.0003550045,0.0000982147,0.0005261884,0.00036104262,0.0026442234,0.00013923763,0.00047630933],"category_scores_gemma":[0.0003676525,0.00011371882,0.00014042834,0.0028024244,0.00030264942,0.0005376461,0.0017301436,0.00016576775,0.0014586378],"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":[0.000016448968,0.00006740691,0.0031993454,0.00001566009,0.000048001635,0.000011521731,0.000100517515,0.0000010816898,0.9626311,0.00005629125,0.03071013,0.0031425096],"study_design_scores_gemma":[0.0014862675,0.00054602814,0.30682465,0.0002816154,0.0004442706,0.000042811742,0.0020335787,0.0074230265,0.4396255,0.0029743537,0.235869,0.0024488717],"about_ca_topic_score_codex":0.00039919335,"about_ca_topic_score_gemma":0.00052067684,"teacher_disagreement_score":0.5230056,"about_ca_system_score_codex":0.00003339053,"about_ca_system_score_gemma":0.000054852277,"threshold_uncertainty_score":0.99931884},"labels":[],"label_agreement":null},{"id":"W4376127614","doi":"10.1038/s41597-023-02080-8","title":"Social and moral psychology of COVID-19 across 69 countries","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"COVID-19 and Mental Health","field":"Psychology","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":"University of Alberta; Western University; Carleton University; University of Waterloo; Toronto Metropolitan University; University of Toronto; University of British Columbia","funders":"Biotechnology and Biological Sciences Research Council; Medical Research Council","keywords":"Pandemic; Public health; Psychology; Social psychology; General Social Survey; Survey data collection; Personality psychology; Coronavirus disease 2019 (COVID-19); Personality; Sociology; Social science; Medicine","score_opus":0.40192822931789274,"score_gpt":0.5808020181795318,"score_spread":0.17887378886163907,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4376127614","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":[0.9488539,0.00055687974,0.00019167307,0.015355313,0.0077675874,0.00048131973,0.023567375,0.00022846171,0.0029974608],"genre_scores_gemma":[0.9744567,0.000051414223,0.000061795596,0.0036991362,0.00021014667,0.00002062457,0.0047485037,0.000020145506,0.016731529],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981276,0.00010418358,0.00026709438,0.0007791298,0.00024482072,0.00047718183],"domain_scores_gemma":[0.998392,0.00014594429,0.00010469526,0.0011469638,0.00003331534,0.00017710784],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002255977,0.00009789996,0.00018767649,0.00013136998,0.0005526849,0.00007452119,0.0007701042,0.00009271952,0.0007797476],"category_scores_gemma":[0.000135695,0.0000950097,0.00002365844,0.0006583838,0.0012502043,0.00014185981,0.0007294863,0.000103667335,0.00075421477],"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":[0.000115945186,0.00007805467,0.019944208,0.00016196589,0.000020046808,0.000025034777,0.009619337,2.2591757e-7,0.00021051404,0.006670992,0.95635825,0.0067954496],"study_design_scores_gemma":[0.0009040035,0.000046926354,0.06587426,0.0000048845973,0.0000109486855,0.000010211684,0.0025516828,0.000032272357,0.000018674053,0.0022865552,0.92815375,0.00010584959],"about_ca_topic_score_codex":0.000818705,"about_ca_topic_score_gemma":0.0009940681,"teacher_disagreement_score":0.045930054,"about_ca_system_score_codex":0.00005028183,"about_ca_system_score_gemma":0.00035620888,"threshold_uncertainty_score":0.9694156},"labels":[],"label_agreement":null},{"id":"W4376133730","doi":"10.1038/s41597-023-02163-6","title":"A spatio-temporal dataset on food flows for four West African cities","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"Urban Agriculture and Sustainability","field":"Agricultural and Biological Sciences","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":"Bundesministerium für Bildung und Forschung; Consortium of International Agricultural Research Centers; Deutsche Forschungsgemeinschaft","keywords":"Food security; Geography; Sustainability; Psychological intervention; Resilience (materials science); Socioeconomics; Environmental planning; Business; Agriculture; Ecology; Economics","score_opus":0.10629855697655285,"score_gpt":0.2652192563099462,"score_spread":0.15892069933339334,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4376133730","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":[0.76802695,0.00002868917,0.0000066314583,0.0049789776,0.0009497204,0.00073486625,0.22467358,0.00020619555,0.00039436322],"genre_scores_gemma":[0.7403566,0.0000016330947,0.00009086723,0.00011102001,0.0002940898,0.000046674708,0.2557214,0.0000010224146,0.003376639],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980381,0.00006040882,0.00021333521,0.00087864924,0.00036279712,0.0004466857],"domain_scores_gemma":[0.9988786,0.00026767666,0.000069095906,0.00056139234,0.000098767596,0.00012444907],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011961116,0.00014870812,0.00015814042,0.000029619328,0.0006515635,0.0004601784,0.0013986923,0.000059363832,0.0002849771],"category_scores_gemma":[0.00037843318,0.00005306272,0.00005835631,0.0010192991,0.00014519054,0.0003392033,0.00057156093,0.00008180286,0.00027782333],"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":[0.00002879427,0.00006389204,0.0011459757,0.0000146361535,0.000009940164,0.0000032854455,0.000077340635,0.0000026981158,0.0007196256,0.000278934,0.9863239,0.011330964],"study_design_scores_gemma":[0.00010266172,0.00024046325,0.022330591,0.000007312815,0.000011305227,0.0000011456162,0.0012219435,0.00046745563,0.00010342718,0.0016058782,0.9737318,0.00017598449],"about_ca_topic_score_codex":0.00016051487,"about_ca_topic_score_gemma":0.010485176,"teacher_disagreement_score":0.031047821,"about_ca_system_score_codex":0.000027735367,"about_ca_system_score_gemma":0.0000285502,"threshold_uncertainty_score":0.58509743},"labels":[],"label_agreement":null},{"id":"W4376503834","doi":"10.1038/s41597-023-02177-0","title":"An inventory of greenhouse gas emissions due to natural gas pipeline incidents in the United States and Canada from 1980s to 2021","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"Atmospheric and Environmental Gas Dynamics","field":"Environmental Science","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Calgary","funders":"Natural Science Foundation of Jiangsu Province; Government of Jiangsu Province; Tencent","keywords":"Greenhouse gas; Natural gas; Environmental science; Pipeline transport; Pipeline (software); Methane; Fugitive emissions; Compressor station; Emission inventory; Natural resource economics; Environmental protection; Environmental engineering; Waste management; Engineering; Geography; Meteorology; Ecology; Economics; Air quality index","score_opus":0.015316847315076224,"score_gpt":0.24122568541476386,"score_spread":0.22590883809968765,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4376503834","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":[0.99739414,0.000013554744,0.00015643086,0.00069311226,0.0003231485,0.00020545314,0.0011759314,0.0000114268705,0.000026783538],"genre_scores_gemma":[0.9912931,0.000030359566,0.0016740683,0.000678389,0.0000214843,0.0000073935867,0.005153718,0.00001464467,0.0011268726],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982094,0.000086527616,0.00022865437,0.0005846074,0.0005932367,0.00029754886],"domain_scores_gemma":[0.99845916,0.00005516446,0.00004979411,0.0011993387,0.0000042637716,0.0002322863],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006442918,0.000122050435,0.00012207674,0.000030729625,0.00017998653,0.00006994681,0.00136854,0.000026359192,0.00026937397],"category_scores_gemma":[0.00009130761,0.00009355672,0.000010168145,0.0011078272,0.00023578294,0.00023556278,0.0015429148,0.00011411059,0.00006546322],"study_design_candidate":"not_applicable","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":[0.000059324517,0.00029375186,0.24931222,0.000012591301,0.000016524731,0.00021291181,0.012481581,0.0995418,0.012196449,0.0000062995628,0.60115474,0.02471182],"study_design_scores_gemma":[0.00046402638,0.000075920754,0.41404566,0.00006866341,0.000028646804,0.000007900515,0.01696904,0.43198973,0.0002380054,0.0003790567,0.13524766,0.00048568333],"about_ca_topic_score_codex":0.7188677,"about_ca_topic_score_gemma":0.8271393,"teacher_disagreement_score":0.46590707,"about_ca_system_score_codex":0.0001431886,"about_ca_system_score_gemma":0.000036845606,"threshold_uncertainty_score":0.38151324},"labels":[],"label_agreement":null},{"id":"W4376959108","doi":"10.1038/s41597-023-02214-y","title":"Responses of pyramidal cell somata and apical dendrites in mouse visual cortex over multiple days","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"Neural dynamics and brain function","field":"Neuroscience","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":"McGill University; Université de Montréal; Vector Institute; Canadian Institute for Advanced Research; Montreal Neurological Institute and Hospital; University of Toronto; Mila - Quebec Artificial Intelligence Institute; The Scarborough Hospital; York University","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Government of Canada; Canadian Institute for Advanced Research; Alfred P. Sloan Foundation","keywords":"Visual cortex; Pyramidal cell; Neuroscience; Biology; Cortex (anatomy); Cerebral cortex; Anatomy; Hippocampus","score_opus":0.06469699247135695,"score_gpt":0.31159061401491306,"score_spread":0.2468936215435561,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4376959108","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":[0.99566174,0.000013731303,0.00002160719,0.000094729316,0.0007385406,0.00015169533,0.003197782,0.000060920895,0.000059231243],"genre_scores_gemma":[0.9941172,0.000014141233,0.000052361906,0.000060627353,0.000018079836,0.000002829657,0.0004906967,0.000011210088,0.005232869],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9982533,0.0001030051,0.00023125777,0.0007919506,0.00035865925,0.0002618293],"domain_scores_gemma":[0.9985092,0.0005518276,0.000069010384,0.0007841095,0.000017336755,0.000068477515],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006558832,0.000095653035,0.00012545999,0.00027704856,0.00014966344,0.00019952137,0.0005944467,0.00004253133,0.00003456837],"category_scores_gemma":[0.0014005075,0.000085814834,0.000018321538,0.00082329486,0.00046737806,0.00043674512,0.0010837789,0.00010903087,0.000068733876],"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":[0.000058578775,0.00009130067,0.0069953697,0.000021964019,6.161053e-7,0.000023045577,0.000056535944,0.000010238494,0.9848113,0.00013658867,0.0072496813,0.00054478284],"study_design_scores_gemma":[0.0010140304,0.000086615546,0.111962475,0.00002985328,0.000007568772,0.000011490103,0.00016110885,0.42416233,0.4536597,0.00040341957,0.008237706,0.00026369674],"about_ca_topic_score_codex":0.000040882598,"about_ca_topic_score_gemma":0.00014923011,"teacher_disagreement_score":0.5311516,"about_ca_system_score_codex":0.000010334843,"about_ca_system_score_gemma":0.000043772412,"threshold_uncertainty_score":0.34994274},"labels":[],"label_agreement":null},{"id":"W4377093063","doi":"10.1038/s41597-023-02174-3","title":"M100 ExaData: a data collection campaign on the CINECA’s Marconi100 Tier-0 supercomputer","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"Advanced Data Storage Technologies","field":"Computer Science","cited_by":32,"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":"","keywords":"Supercomputer; Computer science; Workload; Software; Data science; Operating system","score_opus":0.15939045995022397,"score_gpt":0.31590441355818877,"score_spread":0.1565139536079648,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4377093063","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":[0.005880384,0.00020918717,0.9320571,0.02411447,0.011873379,0.0014045639,0.017225709,0.005376137,0.0018590789],"genre_scores_gemma":[0.18524434,0.0005768078,0.54632723,0.0053664735,0.0016331597,0.00037028294,0.17430028,0.00032000506,0.0858614],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9954464,0.00014775908,0.00033979357,0.0024983073,0.0008930971,0.0006746711],"domain_scores_gemma":[0.9760736,0.00050638703,0.00011079656,0.023129512,0.000088855,0.00009080119],"candidate_categories":["scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.0034058094,0.0002569326,0.00021343316,0.00048599514,0.0011055378,0.0017145339,0.025556305,0.00008824133,0.00007747033],"category_scores_gemma":[0.0011397288,0.0001825119,0.000028177465,0.004464674,0.0005510214,0.0044338536,0.026898306,0.00037424767,0.002351698],"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":[0.0000035566018,0.00003565397,0.000021442174,0.0000072246594,0.000014324251,0.000039965995,0.00010949307,0.000032534805,0.00038411305,0.010978709,0.9600029,0.028370082],"study_design_scores_gemma":[0.00018948143,0.000044857876,0.0003291205,0.00003630315,0.000009113205,0.000027484453,0.0002215569,0.251601,0.00062613003,0.0058036917,0.74081296,0.00029829552],"about_ca_topic_score_codex":0.000055845067,"about_ca_topic_score_gemma":0.00012768076,"teacher_disagreement_score":0.38572985,"about_ca_system_score_codex":0.00008442181,"about_ca_system_score_gemma":0.00023847868,"threshold_uncertainty_score":0.99932176},"labels":[],"label_agreement":null},{"id":"W4377096557","doi":"10.1038/s41597-023-02167-2","title":"FAIR in action - a flexible framework to guide FAIRification","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"Research Data Management Practices","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Institute for Cancer Research","funders":"Biotechnology and Biological Sciences Research Council; Innovative Medicines Initiative","keywords":"Action (physics); Computer science; Physics","score_opus":0.4095442173766862,"score_gpt":0.49234319063888665,"score_spread":0.08279897326220043,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4377096557","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":[0.0029457833,0.000017489014,0.97183406,0.017615043,0.0021745444,0.0005495461,0.0002914857,0.00057494425,0.0039971294],"genre_scores_gemma":[0.15522599,0.00040717816,0.5780635,0.001342323,0.0004475835,0.00037035215,0.012831167,0.00006649345,0.25124544],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9967618,0.00014635682,0.0002686599,0.0014458221,0.00090364827,0.00047371187],"domain_scores_gemma":[0.99268633,0.00022699352,0.00007818927,0.0068014655,0.00007492715,0.00013210047],"candidate_categories":["scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0069765393,0.000092633265,0.00008897602,0.0010027024,0.00025361983,0.0066257804,0.00960432,0.000039723807,0.00003310703],"category_scores_gemma":[0.003452248,0.000092876086,0.000014291644,0.007103476,0.00006507407,0.03236872,0.006798924,0.0001879662,0.0043689054],"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":[0.0000059018753,0.00006554847,0.00030968472,0.000028814167,0.0000073213605,0.000021085172,0.00031232226,0.00028367233,0.0023751343,0.14502652,0.76191026,0.08965373],"study_design_scores_gemma":[0.00006735781,0.000013589343,0.007739691,0.000033918717,0.0000016650621,8.531912e-7,0.00019745113,0.043162152,0.0005535809,0.0050632046,0.94304454,0.00012198125],"about_ca_topic_score_codex":0.00016104298,"about_ca_topic_score_gemma":0.00023049573,"teacher_disagreement_score":0.39377058,"about_ca_system_score_codex":0.000082997365,"about_ca_system_score_gemma":0.0001445485,"threshold_uncertainty_score":0.9964063},"labels":[],"label_agreement":null},{"id":"W4378530983","doi":"10.1038/s41597-023-02222-y","title":"A compendium of bacterial and archaeal single-cell amplified genomes from oxygen deficient marine waters","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"Microbial Community Ecology and Physiology","field":"Environmental Science","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":"Genome British Columbia; University of British Columbia, Okanagan Campus; University of British Columbia","funders":"CHIST-ERA; Leibniz-Gemeinschaft; Office of Science; Directorate for Biological Sciences; Agencia Nacional de Investigación y Desarrollo; Natural Sciences and Engineering Research Council of Canada; Universidad de Concepción; Genome British Columbia; University of Hawai'i; Agenția Națională pentru Cercetare și Dezvoltare; Joint Genome Institute; Canadian Institute for Advanced Research; U.S. Department of Energy; Georgia Institute of Technology; Southern California Gas Company; Simons Foundation; National Science Foundation","keywords":"Biogeochemical cycle; Anoxic waters; Oxygen minimum zone; Compendium; Ecology; Biology; Ecosystem; Organism; Environmental science; Geography; Upwelling","score_opus":0.051002630215706043,"score_gpt":0.23699682538906905,"score_spread":0.18599419517336302,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378530983","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":[0.994386,0.000010608939,0.000015287598,0.00011293197,0.00082646654,0.0001348603,0.0031397445,0.000029312356,0.0013447634],"genre_scores_gemma":[0.9772755,0.000010387146,0.0006387892,0.000041342922,0.00002334479,0.0000020529894,0.021008888,0.0000075116955,0.0009921757],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987623,0.00013441751,0.00019726754,0.0004985692,0.00012369426,0.0002837454],"domain_scores_gemma":[0.99857295,0.00011870689,0.00007705947,0.0011531576,0.0000060730226,0.00007202947],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00062805554,0.00009935833,0.0001648855,0.00006132601,0.00026921995,0.000050013663,0.0011279057,0.000052171752,0.0061550657],"category_scores_gemma":[0.000024402907,0.00009028256,0.00001955246,0.00025957832,0.0010003598,0.00013106574,0.0059596016,0.000101078695,0.0008551716],"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":[0.000060179842,0.00013306996,0.0055808,0.000012342666,0.000011150955,0.0000035968856,0.0011279677,0.000043247666,0.9339028,0.00001926227,0.056899756,0.0022058235],"study_design_scores_gemma":[0.0018191315,0.00030028343,0.3848371,0.000019746802,0.000077663135,0.0000089916775,0.0010213527,0.0022941635,0.038312085,0.005835242,0.56478494,0.0006892893],"about_ca_topic_score_codex":0.00083608826,"about_ca_topic_score_gemma":0.0018129367,"teacher_disagreement_score":0.8955907,"about_ca_system_score_codex":0.000022101567,"about_ca_system_score_gemma":0.000013661464,"threshold_uncertainty_score":0.99992275},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W4379259280","doi":"10.1038/s41597-023-02264-2","title":"The FORCIS database: A global census of planktonic Foraminifera from ocean waters","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"Geology and Paleoclimatology Research","field":"Earth and Planetary Sciences","cited_by":22,"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":"Natural Environment Research Council; Labex OT-Med; Max-Planck-Institut für Chemie; Fondation pour la Recherche sur la Biodiversite; Agence Nationale de la Recherche; Sight Research UK","keywords":"Foraminifera; Census; Oceanography; Plankton; Geography; Geology; Benthic zone; Population; Demography","score_opus":0.0734677861201946,"score_gpt":0.30287168208383597,"score_spread":0.22940389596364136,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379259280","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":[0.90481865,0.00074297114,0.000012420284,0.0012330499,0.002271963,0.00017798843,0.08895908,0.000059714384,0.0017241744],"genre_scores_gemma":[0.91301924,0.00009619911,0.00014449525,0.000025320904,0.000032433963,3.9535263e-7,0.08583354,0.0000016160841,0.0008467542],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99810404,0.00014104269,0.00022807147,0.00056895224,0.0003965348,0.00056139135],"domain_scores_gemma":[0.9974735,0.00056138117,0.00006450237,0.0017479853,0.000043998385,0.00010864365],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002066236,0.00009700278,0.00014115193,0.00006204545,0.00072525133,0.00014989098,0.0022675896,0.00006570069,0.00041287448],"category_scores_gemma":[0.00027383046,0.00006089651,0.000029577079,0.000836927,0.0010866051,0.00024394218,0.00038038476,0.00014008817,0.0015239546],"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":[0.00004732239,0.000005554224,0.8864369,0.000008843742,0.000024734733,0.000030076633,0.000042708816,0.00002853853,0.0000034105485,0.00011308883,0.110521205,0.0027376069],"study_design_scores_gemma":[0.0003969905,0.00004780062,0.8583702,0.00002161802,0.000029060102,0.000025497906,0.0007300046,0.027510393,0.00007879207,0.003784894,0.10883574,0.00016900324],"about_ca_topic_score_codex":0.0004651762,"about_ca_topic_score_gemma":0.0069080316,"teacher_disagreement_score":0.028066704,"about_ca_system_score_codex":0.0000010008732,"about_ca_system_score_gemma":0.00012075041,"threshold_uncertainty_score":0.99925345},"labels":[],"label_agreement":null},{"id":"W4379520140","doi":"10.1038/s41597-023-02058-6","title":"A 100-member ensemble simulations of global historical (1951–2010) wave heights","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"Ocean Waves and Remote Sensing","field":"Earth and Planetary Sciences","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":"Environment and Climate Change Canada","funders":"Japan Agency for Marine-Earth Science and Technology; Ministry of Education, Culture, Sports, Science and Technology","keywords":"Climatology; Scale (ratio); Submarine pipeline; Climate change; Environmental science; Temporal scales; Meteorology; Geography; Geology; Oceanography; Cartography","score_opus":0.12310294191506743,"score_gpt":0.28208088045440594,"score_spread":0.1589779385393385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379520140","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":[0.9605513,0.00035169124,0.00020399773,0.0009025062,0.011657404,0.00024170178,0.0096251955,0.00016803724,0.01629814],"genre_scores_gemma":[0.97624373,0.0000066674324,0.0019194661,0.000023676928,0.00015104571,3.2861152e-9,0.0057632294,0.000003285978,0.01588887],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983686,0.00004475042,0.0002541782,0.00054276234,0.00045406175,0.00033563454],"domain_scores_gemma":[0.9985255,0.00010225145,0.00008108697,0.0010886121,0.00006340734,0.00013912666],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00051012204,0.000101753285,0.00015535051,0.00009048861,0.00034315983,0.00013173946,0.000494217,0.000057267614,0.0006226674],"category_scores_gemma":[0.0001167329,0.000079288366,0.000045328452,0.0012782975,0.00017034089,0.00031165153,0.00014027787,0.000074815456,0.00080045126],"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":[0.000030858602,0.00007553939,0.019982025,0.00006160489,0.000052200652,0.00010887188,0.00038929665,0.009289676,0.0005386245,0.000284876,0.8605185,0.108667895],"study_design_scores_gemma":[0.00019048728,0.000029349247,0.073401116,0.000026234065,0.000027561107,0.000019445648,0.00007928965,0.68190444,0.00007242929,0.0024542052,0.24160247,0.00019295976],"about_ca_topic_score_codex":0.0012416887,"about_ca_topic_score_gemma":0.003273835,"teacher_disagreement_score":0.67261475,"about_ca_system_score_codex":0.000018714945,"about_ca_system_score_gemma":0.00010957559,"threshold_uncertainty_score":0.9999775},"labels":[],"label_agreement":null},{"id":"W4379875502","doi":"10.1038/s41597-023-02284-y","title":"Carbon Monitor Europe near-real-time daily CO2 emissions for 27 EU countries and the United Kingdom","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"Air Quality and Health Impacts","field":"Environmental Science","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":"University of Toronto","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Greenhouse gas; Aviation; European union; Business; Environmental science; Natural resource economics; International trade; Economics; Engineering","score_opus":0.10521872005893303,"score_gpt":0.3466945938191512,"score_spread":0.24147587376021817,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379875502","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":[0.9466424,0.000057093835,0.000080152,0.039024748,0.0021234713,0.0013455171,0.0059749507,0.00030044242,0.0044512223],"genre_scores_gemma":[0.57836753,0.0014423449,0.011322166,0.021391897,0.0014823255,0.00026351522,0.043297295,0.0003719404,0.342061],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981557,0.00015651381,0.00023722446,0.00055662513,0.00043609552,0.00045782357],"domain_scores_gemma":[0.9978868,0.00050383044,0.00009601991,0.0012559597,0.000024437424,0.00023296417],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0037553487,0.00011705378,0.00014713386,0.000051606366,0.001398085,0.00047469058,0.0009472629,0.00004722557,0.00028873864],"category_scores_gemma":[0.00083314406,0.00007815219,0.000017076994,0.0010910451,0.0017629891,0.00028236088,0.0012092198,0.000103626204,0.0008562791],"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":[0.00007653338,0.000020838408,0.001094879,0.00003916948,0.0000070627343,0.000002666892,0.001286539,0.000106260006,0.00070254493,0.0005217275,0.99548095,0.0006608116],"study_design_scores_gemma":[0.000565153,0.000021018419,0.0063079163,0.00002788888,0.00002127848,0.0000017864585,0.00013970067,0.08315258,0.00007867048,0.00028208544,0.909289,0.000112934984],"about_ca_topic_score_codex":0.0018855708,"about_ca_topic_score_gemma":0.00012383511,"teacher_disagreement_score":0.3682749,"about_ca_system_score_codex":0.00003393606,"about_ca_system_score_gemma":0.000078147175,"threshold_uncertainty_score":0.9999217},"labels":[],"label_agreement":null},{"id":"W4381684967","doi":"10.1038/s41597-023-02273-1","title":"A Database of Snow on Sea Ice in the Central Arctic Collected during the MOSAiC expedition","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"Arctic and Antarctic ice dynamics","field":"Earth and Planetary Sciences","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 Victoria","funders":"Swiss Polar Institute; European Commission; WSL-Institut für Schnee- und Lawinenforschung SLF; National Science Foundation","keywords":"Snow; Arctic; Sea ice; Sea ice thickness; Arctic ice pack; Geology; Cryosphere; Atmospheric sciences; Environmental science; Climatology; Oceanography; Geomorphology","score_opus":0.03270510775488677,"score_gpt":0.24251858032489781,"score_spread":0.20981347257001104,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381684967","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":[0.9852062,0.00002087302,0.000037744954,0.0010846148,0.0011096124,0.00029508464,0.011693381,0.00002971141,0.00052281306],"genre_scores_gemma":[0.979697,0.000029035835,0.00005721124,0.00010788976,0.00008265215,0.0000017825355,0.019363128,0.0000024998442,0.00065878686],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99834067,0.00016513126,0.00019818182,0.00039087053,0.0005357978,0.0003693272],"domain_scores_gemma":[0.99816155,0.00049392646,0.00007489671,0.0011948928,0.000027425136,0.000047317153],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014371917,0.00008962464,0.000089239526,0.00011670231,0.00050909107,0.00013799629,0.001323734,0.000024034525,0.00049509597],"category_scores_gemma":[0.00042325462,0.000050976734,0.000023321065,0.0016002787,0.00030963853,0.00033758217,0.00011446517,0.00017416435,0.0002037329],"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":[0.0004288171,0.00037738789,0.66470516,0.0005526238,0.00008252281,0.00028753394,0.015962714,0.0076513235,0.0005730102,0.00067960215,0.2900166,0.018682713],"study_design_scores_gemma":[0.0003240329,0.000035309877,0.8861054,0.00011434603,0.000019397383,0.000022292787,0.0048324703,0.103036515,0.000053854943,0.00031046662,0.0050206427,0.0001252262],"about_ca_topic_score_codex":0.0019552002,"about_ca_topic_score_gemma":0.0064743366,"teacher_disagreement_score":0.28499594,"about_ca_system_score_codex":0.000007794967,"about_ca_system_score_gemma":0.00009592617,"threshold_uncertainty_score":0.54209536},"labels":[],"label_agreement":null},{"id":"W4381839070","doi":"10.1038/s41597-023-02303-y","title":"DOCU-CLIM: A global documentary climate dataset for climate reconstructions","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"Tree-ring climate responses","field":"Earth and Planetary Sciences","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"National Supercomputing Centre Singapore; Centro Svizzero di Calcolo Scientifico; European Commission; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Documentary evidence; Climatology; Climate change; Proxy (statistics); Geography; Precipitation; Series (stratigraphy); Newspaper; Meteorology; Archaeology; Geology; Computer science; Political science; Oceanography","score_opus":0.06823592943993621,"score_gpt":0.3269455598863753,"score_spread":0.2587096304464391,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381839070","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1435784,0.00016040036,0.000025855672,0.00076143356,0.0048748315,0.00045211284,0.8487357,0.0003113244,0.0010999589],"genre_scores_gemma":[0.055105437,0.00043130654,0.0070573133,0.00018558864,0.00026068543,0.000013239538,0.93648857,0.0000144771,0.00044340975],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9966333,0.00009926416,0.0004351575,0.0012671561,0.00045349708,0.0011116511],"domain_scores_gemma":[0.9968442,0.00037025835,0.00013853099,0.002348326,0.000044347053,0.00025435316],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0025132122,0.00021969299,0.00023065427,0.00023040034,0.0012814887,0.0009865626,0.0019105102,0.00006668311,0.0023682609],"category_scores_gemma":[0.00027601348,0.00019775078,0.00006373957,0.0014314083,0.00047048816,0.001483037,0.0005888331,0.000104046376,0.007231512],"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":[0.0001732411,0.000027963564,0.11133441,0.00014215641,0.000046106372,0.000040817773,0.000042856907,0.00019757186,0.00005613505,0.00017257608,0.83242,0.055346165],"study_design_scores_gemma":[0.00065326324,0.00006761534,0.14585744,0.00005940399,0.00008830907,0.00011121691,0.0005623766,0.011198856,0.00003471706,0.0013503538,0.83959126,0.0004252061],"about_ca_topic_score_codex":0.0005669768,"about_ca_topic_score_gemma":0.008476865,"teacher_disagreement_score":0.088472955,"about_ca_system_score_codex":0.000015645974,"about_ca_system_score_gemma":0.0001349237,"threshold_uncertainty_score":0.99854374},"labels":[],"label_agreement":null},{"id":"W4382501545","doi":"10.1038/s41597-023-02320-x","title":"Author Correction: MusMorph, a database of standardized mouse morphology data for morphometric meta-analyses","year":2023,"lang":"en","type":"erratum","venue":"Scientific Data","topic":"Bat Biology and Ecology Studies","field":"Agricultural and Biological 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":"McMaster University; Alberta Children's Hospital; University of Alberta; Alberta Bone and Joint Health Institute; University of Calgary","funders":"","keywords":"Morphology (biology); Meta-analysis; Database; Information retrieval; Computer science; Biology; Zoology; Medicine; Pathology","score_opus":0.4249550949419449,"score_gpt":0.3974539525286545,"score_spread":0.02750114241329038,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382501545","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020154156,0.010393897,0.000158573,0.0042455164,0.11379485,0.0014245035,0.86721116,0.00029631876,0.00045974157],"genre_scores_gemma":[0.00037984393,0.0005183406,0.0008135547,0.00011945988,0.0010497882,0.00013335513,0.5328869,0.000008349342,0.46409035],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.993792,0.0004373103,0.0010553552,0.0032384195,0.0006224034,0.0008545134],"domain_scores_gemma":[0.99277365,0.0020270457,0.000954929,0.0035499467,0.0005297436,0.00016471156],"candidate_categories":["open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.006865435,0.0005758349,0.002012471,0.0003150919,0.0011799098,0.00019621589,0.007446567,0.0007886191,0.0021138988],"category_scores_gemma":[0.0075099333,0.00022843287,0.00043707152,0.0031456645,0.0015001696,0.00050538,0.007988835,0.00069920847,0.00021565413],"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":[0.00009294123,0.00014869586,0.000031080122,0.00007002633,0.0034124064,0.000013536534,0.000011852234,0.0000013518581,0.006284382,0.00000842057,0.9882223,0.0017029998],"study_design_scores_gemma":[0.00023195465,0.00016627918,0.00048888905,0.000023276578,0.0060288766,0.000014777605,0.00028772396,0.0006530534,0.00037644675,0.000079440324,0.9912035,0.00044576573],"about_ca_topic_score_codex":0.000653131,"about_ca_topic_score_gemma":0.012029623,"teacher_disagreement_score":0.46363062,"about_ca_system_score_codex":0.000041290306,"about_ca_system_score_gemma":0.0002033788,"threshold_uncertainty_score":0.9987983},"labels":[],"label_agreement":null},{"id":"W4383711048","doi":"10.1038/s41597-023-02614-0","title":"A comparison of neuroelectrophysiology databases","year":2023,"lang":"en","type":"review","venue":"Scientific Data","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Baycrest Hospital; Indoc Research; Ontario Brain Institute","funders":"National Institutes of Health; National Institute of Neurological Disorders and Stroke; National Institute of Mental Health; University of Southern California; U.S. Department of Health and Human Services","keywords":"Neuroinformatics; Data sharing; Computer science; Data science; Data integration; Field (mathematics); World Wide Web; Metadata; Database","score_opus":0.6093313146232971,"score_gpt":0.49693759619651007,"score_spread":0.11239371842678708,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383711048","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":[0.0000060547586,0.9651166,0.000036595993,0.00008944805,0.004585355,0.0005877035,0.029166384,0.00017297793,0.0002388788],"genre_scores_gemma":[0.000012133353,0.9912314,0.00007673889,0.00005890738,0.00014641263,0.000040128103,0.005756061,0.00005362921,0.0026246172],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9955411,0.0004837434,0.0006764133,0.0023051538,0.00057774613,0.00041582985],"domain_scores_gemma":[0.9853911,0.009730342,0.0005500056,0.0042165266,0.00005259468,0.000059436716],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000713271,0.00031812888,0.0015556432,0.00045344702,0.0003695199,0.00009559243,0.0032363948,0.000064070286,0.0000816314],"category_scores_gemma":[0.029082485,0.0002582634,0.00016721946,0.002192738,0.00095848594,0.00028043013,0.0048155147,0.00037656573,0.0012905563],"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":[0.0000053201557,0.00016460843,0.0000010200214,0.0074942308,0.00004588221,0.000016089516,0.000017755241,0.0000014776646,0.0010309052,0.0012545076,0.6063864,0.38358176],"study_design_scores_gemma":[0.000036545083,0.00004275765,0.0000012537623,0.0011722217,0.00016576127,0.000011096618,0.000007805207,0.00012285142,0.00018827259,0.000081344704,0.99797386,0.00019625145],"about_ca_topic_score_codex":0.000017193865,"about_ca_topic_score_gemma":0.00004747032,"teacher_disagreement_score":0.3915874,"about_ca_system_score_codex":0.000032476262,"about_ca_system_score_gemma":0.0004095727,"threshold_uncertainty_score":0.99998695},"labels":[],"label_agreement":null},{"id":"W4383907966","doi":"10.1038/s41597-023-02356-z","title":"Haplotype-resolved chromosomal-level assembly of wasabi (Eutrema japonicum) genome","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"Plant Virus Research Studies","field":"Agricultural and Biological Sciences","cited_by":10,"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; Japan Society for the Promotion of Science","keywords":"Haplotype; Genome; Biology; Genetics; Computational biology; Evolutionary biology; Gene; Genotype","score_opus":0.21633691570144425,"score_gpt":0.3191772619451976,"score_spread":0.10284034624375332,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383907966","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":[0.9448274,0.0003181238,0.0000022361842,0.00131432,0.00045029982,0.00030303828,0.051206365,0.00018770341,0.0013905166],"genre_scores_gemma":[0.9636428,0.00015180594,0.00013956882,0.000039559338,0.00022049385,0.000018164284,0.020466644,0.0000026070963,0.015318388],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974107,0.000088870234,0.00028661653,0.0008062589,0.0008106627,0.0005968758],"domain_scores_gemma":[0.9987102,0.0003439809,0.00009569969,0.00057725096,0.00013455778,0.0001383039],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0017046172,0.00014674364,0.00024098865,0.000058153382,0.0005078805,0.00021046092,0.0023791683,0.00006138207,0.00043641025],"category_scores_gemma":[0.0005661532,0.000057812027,0.000061804436,0.0017843742,0.0004181609,0.00035152544,0.0025164506,0.00011653556,0.0014920827],"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":[0.000011204046,0.000051103416,0.00015857481,0.000014554657,0.000024027013,0.000012505663,0.000038012848,0.00000141278,0.8659668,0.000060240236,0.12863868,0.0050229137],"study_design_scores_gemma":[0.0002477241,0.00014706128,0.22980975,0.00006382339,0.000024802057,0.000007014537,0.0005276115,0.0013727753,0.0452132,0.00032541165,0.7218464,0.0004144371],"about_ca_topic_score_codex":0.00028231018,"about_ca_topic_score_gemma":0.001927596,"teacher_disagreement_score":0.8207536,"about_ca_system_score_codex":0.000021090302,"about_ca_system_score_gemma":0.000050368068,"threshold_uncertainty_score":0.9992854},"labels":[],"label_agreement":null},{"id":"W4384025130","doi":"10.1038/s41597-023-02330-9","title":"Magnetic resonance imaging datasets with anatomical fiducials for quality control and registration","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"Advanced MRI Techniques and Applications","field":"Medicine","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":"Robarts Clinical Trials; University of British Columbia; McMaster University; Western University","funders":"Canada Foundation for Innovation; National Center for Research Resources; National Institute of Mental Health; NIH Blueprint for Neuroscience Research; National Institute on Aging; McDonnell Center for Systems Neuroscience; National Institutes of Health; Canada Research Chairs; Canada First Research Excellence Fund; Mitacs; Natural Sciences and Engineering Research Council of Canada; Fondation Brain Canada","keywords":"Fiducial marker; Neuroimaging; Computer science; Magnetic resonance imaging; Artificial intelligence; Image registration; Neuroanatomy; Computer vision; Medical physics; Medicine; Radiology; Image (mathematics); Anatomy","score_opus":0.06958832490861831,"score_gpt":0.4077585015990662,"score_spread":0.33817017669044785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384025130","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":[0.051828265,0.0037589204,0.662637,0.0399677,0.0005421711,0.008042047,0.2308789,0.0013447285,0.0010002587],"genre_scores_gemma":[0.6080889,0.00014397969,0.23176457,0.0010827061,0.0002981329,0.00052635284,0.15240902,0.000058394857,0.00562792],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989876,0.000013478198,0.00016267067,0.00052707276,0.00015435262,0.00015483545],"domain_scores_gemma":[0.9985038,0.000092142676,0.000054782216,0.00122922,0.000056011675,0.000064053835],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009552619,0.000060795497,0.00011538198,0.000049336275,0.0001850147,0.00007765416,0.00019590565,0.0000172274,0.000008579223],"category_scores_gemma":[0.00026632936,0.00004912089,0.000008939618,0.00027661218,0.00024444587,0.00017733981,0.000096707634,0.0000459983,0.000008108828],"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":[0.00019174034,0.00007110769,0.0017390475,0.000076214805,0.0000029037851,0.000008844102,0.000037201633,0.000001528008,0.023487909,0.008822012,0.83238304,0.13317844],"study_design_scores_gemma":[0.0013807683,0.00005362366,0.022742257,0.00007543224,0.000051846186,0.00001963877,0.00009688143,0.022919657,0.0007787734,0.0036846192,0.94806236,0.00013413464],"about_ca_topic_score_codex":0.000016419193,"about_ca_topic_score_gemma":0.000041057137,"teacher_disagreement_score":0.55626065,"about_ca_system_score_codex":0.000010834889,"about_ca_system_score_gemma":0.000062029525,"threshold_uncertainty_score":0.20030917},"labels":[],"label_agreement":null},{"id":"W4385343011","doi":"10.1038/s41597-023-02413-7","title":"Author Correction: A Database of Snow on Sea Ice in the Central Arctic Collected during the MOSAiC expedition","year":2023,"lang":"en","type":"erratum","venue":"Scientific Data","topic":"Arctic and Antarctic ice dynamics","field":"Earth and Planetary Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Mosaic; Snow; Arctic; Sea ice; Oceanography; Physical geography; The arctic; Climatology; Geology; Geography; Meteorology; Archaeology","score_opus":0.035128624466839044,"score_gpt":0.2545644915385897,"score_spread":0.21943586707175064,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385343011","genre_codex":"editorial","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0568511,0.000760109,0.00036919786,0.009331566,0.6226315,0.004340938,0.28795525,0.0003722373,0.017388089],"genre_scores_gemma":[0.17537726,0.00029475792,0.000111434994,0.00030383744,0.0027907817,0.00001672008,0.424389,0.000032448635,0.39668375],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.996491,0.00038726284,0.00044891456,0.00091637386,0.0011587157,0.0005977372],"domain_scores_gemma":[0.9963727,0.00078941433,0.00030236633,0.002361878,0.00008353626,0.000090092864],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0020938844,0.00026136125,0.00026792675,0.0002611131,0.0009719603,0.00035852753,0.002601767,0.00015707781,0.001020338],"category_scores_gemma":[0.0011792409,0.00015864747,0.00006959925,0.0020498498,0.00056050904,0.00039282072,0.00022132171,0.0010548956,0.00025655658],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004953906,0.000044676523,0.0029205044,0.00015896847,0.000021717804,0.000040923762,0.0009227496,0.00022970139,0.0000013485934,0.000008362289,0.994372,0.0012294932],"study_design_scores_gemma":[0.00057240785,0.00014878628,0.3479373,0.0018022665,0.00020380173,0.00015119628,0.009392619,0.1940013,0.000008766083,0.00024148317,0.44487822,0.0006618785],"about_ca_topic_score_codex":0.006047428,"about_ca_topic_score_gemma":0.03516088,"teacher_disagreement_score":0.61984074,"about_ca_system_score_codex":0.000034741486,"about_ca_system_score_gemma":0.0005312021,"threshold_uncertainty_score":0.9998929},"labels":[],"label_agreement":null},{"id":"W4386026821","doi":"10.1038/s41597-023-02377-8","title":"A longitudinal resource for population neuroscience of school-age children and adolescents in China","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","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 Health Centre; Université de Montréal; Western University; Hospital for Sick Children; University of Toronto; Montreal Neurological Institute and Hospital; Douglas Mental Health University Institute; McGill University; Centre Hospitalier Universitaire Sainte-Justine; Queen's University; Holland Bloorview Kids Rehabilitation Hospital","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Social Science Fund of China; National Key Research and Development Program of China; Beijing Municipal Science and Technology Commission; Medical Research Council; Chinese Academy of Sciences; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Beijing Normal University; National Natural Science Foundation of China; Child Mind Institute","keywords":"Population; Psychology; Longitudinal study; Resource (disambiguation); Cognition; Computer science; Neuroscience; Demography; Medicine; Sociology","score_opus":0.09694316819790338,"score_gpt":0.32209723093467496,"score_spread":0.22515406273677158,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386026821","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":[0.99577916,0.000016841328,0.000095275944,0.001140189,0.00062438945,0.0004488448,0.0017880829,0.000061786035,0.00004544333],"genre_scores_gemma":[0.99896467,0.000003895722,0.00006129235,0.00014010846,0.00003242581,0.000009395352,0.00029518513,0.000008902518,0.000484116],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9978833,0.00006966843,0.00020267227,0.0011532092,0.00041689514,0.00027425765],"domain_scores_gemma":[0.99863213,0.00035410537,0.00008690035,0.0008482207,0.00001852541,0.000060125407],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0012719509,0.00009678649,0.00013619756,0.00034440833,0.00035141938,0.00015218997,0.0007560432,0.00002390116,0.0000028231118],"category_scores_gemma":[0.014220151,0.00009338331,0.000020287005,0.0015370892,0.00038360155,0.00053155975,0.0010815453,0.00009126302,0.000011500121],"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":[0.000106136686,0.00016516421,0.8203033,0.00010536615,0.0000025430356,0.0000116534475,0.00016999608,0.00034676163,0.076881684,0.00057643687,0.09770083,0.0036300845],"study_design_scores_gemma":[0.00031034474,0.000028391301,0.99204344,0.000051899395,0.000003861139,0.0000053096865,0.000009506622,0.0043383655,0.0009925172,0.00053996406,0.0015885384,0.00008789146],"about_ca_topic_score_codex":0.000092052935,"about_ca_topic_score_gemma":0.00017535605,"teacher_disagreement_score":0.17174006,"about_ca_system_score_codex":0.000017642391,"about_ca_system_score_gemma":0.000031024156,"threshold_uncertainty_score":0.99408346},"labels":[],"label_agreement":null},{"id":"W4386070053","doi":"10.1038/s41597-023-02439-x","title":"Spatial and Temporal Availability of Cloud-free Optical Observations in the Tropics to Monitor Deforestation","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"Remote Sensing in Agriculture","field":"Environmental Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University; Ste. Anne's Hospital; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Marshall Space Flight Center; National Aeronautics and Space Administration","keywords":"Tropics; Cloud computing; Deforestation (computer science); Environmental science; Remote sensing; Satellite imagery; Metadata; Computer science; Database; Geography; Meteorology; Ecology","score_opus":0.05593065947997162,"score_gpt":0.2739383081052171,"score_spread":0.21800764862524546,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386070053","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":[0.9962676,0.0000020980335,0.0003514645,0.0020174515,0.00046259852,0.00026306722,0.00039096878,0.000017722243,0.00022703865],"genre_scores_gemma":[0.9909961,0.0000010372374,0.007837611,0.000036249206,0.0000419839,0.0000014245478,0.0007327944,0.0000032348557,0.00034952746],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9987984,0.0000640353,0.00018193833,0.00038595952,0.0004199053,0.00014977028],"domain_scores_gemma":[0.9985971,0.00008656036,0.00003757819,0.0012212734,0.00001290558,0.000044587658],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010974607,0.000058307793,0.00006640355,0.000030465559,0.00012375697,0.0000982874,0.00087144977,0.000030977204,0.000024568082],"category_scores_gemma":[0.00077063125,0.000037235535,0.000010190539,0.0009306975,0.0003441928,0.00020405944,0.0008866097,0.00007466239,0.00009776378],"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":[0.000018303113,0.00014676538,0.5197956,0.000023778424,0.0000041671756,0.000008562106,0.0033056866,0.0010151525,0.020679178,0.00025749745,0.4288474,0.025897916],"study_design_scores_gemma":[0.00008519255,0.000016441816,0.98147976,0.0000072191046,0.0000041614417,0.0000013371478,0.00031620814,0.010508433,0.00024039965,0.00093722646,0.006351839,0.000051801977],"about_ca_topic_score_codex":0.00081930304,"about_ca_topic_score_gemma":0.006804969,"teacher_disagreement_score":0.46168414,"about_ca_system_score_codex":0.000033082895,"about_ca_system_score_gemma":0.000009876041,"threshold_uncertainty_score":0.37973326},"labels":[],"label_agreement":null},{"id":"W4386127240","doi":"10.1038/s41597-023-02478-4","title":"Greenhouse gas emissions from U.S. crude oil pipeline accidents: 1968 to 2020","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"Atmospheric and Environmental Gas Dynamics","field":"Environmental Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Natural Science Foundation of Jiangsu Province; Government of Jiangsu Province","keywords":"Greenhouse gas; Environmental science; Pipeline (software); Crude oil; Petroleum engineering; Engineering; Geology; Oceanography","score_opus":0.02372505400748101,"score_gpt":0.2601706665585461,"score_spread":0.23644561255106508,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386127240","genre_codex":"empirical","genre_gemma":"other","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":[0.98279166,0.000048657683,0.005020697,0.0027083184,0.002181429,0.00020865242,0.0025396566,0.0003972725,0.0041036257],"genre_scores_gemma":[0.41814908,0.00063830114,0.08140381,0.0029817652,0.0006936174,0.00008225614,0.02164028,0.0002433365,0.47416756],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9968361,0.00004307924,0.000325173,0.0013778936,0.0008334537,0.000584304],"domain_scores_gemma":[0.9966224,0.00004913625,0.00007624989,0.002760037,0.0000038767284,0.00048830395],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0006045301,0.00022086463,0.00017965393,0.000019954168,0.00048982236,0.0002186591,0.0026574822,0.00007368268,0.008523811],"category_scores_gemma":[0.000171131,0.00020071588,0.000049135364,0.0013533242,0.00035177526,0.00059428765,0.006116072,0.0001588831,0.027091442],"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":[0.000013073988,0.00011414496,0.012500916,0.0000027756812,0.0000093278895,0.000046217243,0.00038965282,0.007493572,0.011047001,0.0000026575433,0.87180495,0.096575685],"study_design_scores_gemma":[0.00032716003,0.000023735282,0.03778573,0.000031422765,0.00003541609,0.0000044156445,0.00058052177,0.05382369,0.00026396604,0.00040485567,0.9062688,0.00045032494],"about_ca_topic_score_codex":0.0012415624,"about_ca_topic_score_gemma":0.0009222189,"teacher_disagreement_score":0.5646426,"about_ca_system_score_codex":0.00015938803,"about_ca_system_score_gemma":0.000018928766,"threshold_uncertainty_score":0.9923825},"labels":[],"label_agreement":null},{"id":"W4386195873","doi":"10.1038/s41597-023-02464-w","title":"Digitization of the Australian Parliamentary Debates, 1998–2022","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Parliament; Digitization; Democracy; Politics; Resource (disambiguation); Metadata; Public administration; Political science; Library science; Data science; Sociology; Computer science; World Wide Web; Law","score_opus":0.1295125417729573,"score_gpt":0.39690934396953004,"score_spread":0.26739680219657275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386195873","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":[0.90016884,0.00028013618,0.0045419736,0.040875398,0.018961608,0.0013144201,0.009591341,0.0006024262,0.023663849],"genre_scores_gemma":[0.9436088,0.000019194862,0.00083546696,0.00007648394,0.0001598047,0.0000040644486,0.004276157,0.000006145891,0.051013865],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986581,0.00019394659,0.00015113427,0.0002698883,0.00057468575,0.00015223019],"domain_scores_gemma":[0.999097,0.00013147938,0.00007734422,0.00060328527,0.000048559265,0.00004231635],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023887458,0.000040014747,0.000066969245,0.00008702769,0.00064855453,0.0001693393,0.0011115806,0.000018991685,0.00025682038],"category_scores_gemma":[0.000318496,0.000029420937,0.000039216015,0.0022711651,0.0004142191,0.00027711026,0.00044641178,0.000040489045,0.00011324019],"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":[0.0000032879557,0.000069382026,0.017648919,0.000016381466,0.00004983856,0.0000019401296,0.004267078,0.00057258265,0.00085825316,0.009724496,0.8402878,0.12650001],"study_design_scores_gemma":[0.000061145234,0.0000025514746,0.021032948,0.00001490801,0.000028461647,1.5014602e-7,0.0026690545,0.0034712583,0.00027283048,0.0169553,0.95541835,0.00007302235],"about_ca_topic_score_codex":0.0011626558,"about_ca_topic_score_gemma":0.0031013289,"teacher_disagreement_score":0.12642698,"about_ca_system_score_codex":0.00002048496,"about_ca_system_score_gemma":0.0001481713,"threshold_uncertainty_score":0.49882227},"labels":[],"label_agreement":null},{"id":"W4386416992","doi":"10.1038/s41597-023-02467-7","title":"Plant traits and associated data from a warming experiment, a seabird colony, and along elevation in Svalbard","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"Geology and Paleoclimatology Research","field":"Earth and Planetary Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Senter for Internasjonalisering av Utdanning; Universitetet i Bergen","keywords":"Ecosystem; Microclimate; Seabird; Ecology; Climate change; Arctic; Vegetation (pathology); Trait; Environmental science; Environmental change; Global warming; Physical geography; Geography; Biology","score_opus":0.1270747668648577,"score_gpt":0.3179991794282997,"score_spread":0.190924412563442,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386416992","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":[0.98574215,0.0006005536,0.0000032966882,0.00049445615,0.00027958848,0.00016826013,0.012464672,0.00004332958,0.000203666],"genre_scores_gemma":[0.94189346,0.00007679092,0.00013724924,0.000032287673,0.000016521899,0.0000013638775,0.057577547,0.0000021074552,0.00026267653],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99817497,0.00019943458,0.00018796159,0.0008267327,0.00023192778,0.0003789939],"domain_scores_gemma":[0.9987539,0.0005067578,0.00004967808,0.000576184,0.000016649385,0.00009681148],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002594714,0.00009031179,0.00015669884,0.00019603611,0.0003227043,0.00018205798,0.00083217846,0.000093288545,0.00028336325],"category_scores_gemma":[0.000545298,0.00008154009,0.0000051956417,0.0005651462,0.00035261628,0.0005618489,0.0004686043,0.00016696267,0.00023114635],"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":[0.00002166491,0.000010649516,0.9850156,0.0000076742535,0.000014175855,0.00005633455,0.00047853834,0.000005010445,0.00014969695,0.0000056267486,0.012746768,0.0014883073],"study_design_scores_gemma":[0.00035116452,0.000016836724,0.9208718,0.000022877963,0.0000082469005,0.000009958696,0.00042206264,0.075427465,0.000023467323,0.0003312183,0.0024223216,0.000092584596],"about_ca_topic_score_codex":0.0013902964,"about_ca_topic_score_gemma":0.07217709,"teacher_disagreement_score":0.07542246,"about_ca_system_score_codex":0.0000011723241,"about_ca_system_score_gemma":0.000080621365,"threshold_uncertainty_score":0.9447533},"labels":[],"label_agreement":null},{"id":"W4386573853","doi":"10.1038/s41597-023-02488-2","title":"One high quality genome and two transcriptome datasets for new species of Mantamonas, a deep-branching eukaryote clade","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"Protist diversity and phylogeny","field":"Biochemistry, Genetics and Molecular Biology","cited_by":17,"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 Alberta","funders":"European Commission; Government of Canada; Simons Foundation","keywords":"Clade; Eukaryote; Biology; Evolutionary biology; Transcriptome; Genome; Branching (polymer chemistry); Computational biology; Phylogenetics; Gene; Genetics; Gene expression","score_opus":0.08410650693930481,"score_gpt":0.3129157311745487,"score_spread":0.22880922423524386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386573853","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":[0.8696842,0.0009209785,0.008126562,0.00034787643,0.00064215704,0.00050456595,0.119607255,0.000025879022,0.0001405346],"genre_scores_gemma":[0.8434536,0.0000973507,0.0032136065,0.00008939058,0.00018564909,0.0000039950955,0.15045533,0.000011738455,0.002489352],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987368,0.00004327919,0.00018843419,0.00062555115,0.00016990265,0.00023604477],"domain_scores_gemma":[0.9986745,0.00002004638,0.0000717812,0.0011074201,0.000029497629,0.00009672686],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00068950054,0.000096580916,0.00015401898,0.000065926964,0.00020210142,0.000081650156,0.0008304245,0.000054423068,0.000034505592],"category_scores_gemma":[0.000080280995,0.00010580098,0.00003736482,0.00019294953,0.00023538624,0.00002235671,0.0006929472,0.000050049544,0.000015408847],"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":[0.00009020833,0.000037318954,0.00083982386,0.000119062,0.000063376094,0.0000014560135,0.00011893805,0.0000071325903,0.9648261,0.0005863413,0.031272758,0.002037468],"study_design_scores_gemma":[0.0031379596,0.00018823656,0.37615275,0.000047603295,0.00015520449,0.0000049194537,0.00030006032,0.0002075692,0.18683805,0.0043575084,0.4279808,0.0006293177],"about_ca_topic_score_codex":0.00013315203,"about_ca_topic_score_gemma":0.00019478635,"teacher_disagreement_score":0.7779881,"about_ca_system_score_codex":0.0000044658186,"about_ca_system_score_gemma":0.00006382695,"threshold_uncertainty_score":0.43144387},"labels":[],"label_agreement":null},{"id":"W4386740911","doi":"10.1038/s41597-023-02501-8","title":"Shared metadata for data-centric materials science","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"Machine Learning in Materials Science","field":"Materials Science","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":"Carleton University","funders":"Horizon 2020 Framework Programme; Humboldt-Universität zu Berlin; Engineering and Physical Sciences Research Council; Deutsche Forschungsgemeinschaft; European Commission","keywords":"Metadata; Computer science; Interoperability; Workflow; Data sharing; Data science; Data curation; Big data; World Wide Web; Database; Data mining","score_opus":0.14759973735751378,"score_gpt":0.3791868367131539,"score_spread":0.23158709935564012,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386740911","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":[0.6639616,0.00019914919,0.021356823,0.0023215425,0.05005785,0.0030469107,0.25576022,0.0025213854,0.0007745288],"genre_scores_gemma":[0.5554418,0.000037374637,0.23146676,0.00056903425,0.0018615428,0.00027637254,0.18464282,0.00023351429,0.025470812],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9916163,0.00020154838,0.00079085794,0.004020783,0.0019079649,0.001462533],"domain_scores_gemma":[0.9855716,0.00034027122,0.00040379952,0.013022555,0.00034235616,0.00031937612],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["metaresearch","open_science","insufficient_payload"],"category_scores_codex":[0.032366425,0.00031508596,0.00043731387,0.000716158,0.0021283336,0.0073756957,0.025017487,0.00006993082,0.0022057528],"category_scores_gemma":[0.008895224,0.00026897178,0.000029183595,0.0041294917,0.0021749523,0.009623286,0.01759927,0.000102007674,0.005882768],"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":[0.0000181369,0.00003156755,0.000042283737,0.00006404156,0.0000032096661,0.000005941239,0.000053209325,0.000057681562,0.8188085,0.0012056652,0.17916767,0.0005420858],"study_design_scores_gemma":[0.00085582247,0.000064634354,0.0020851006,0.00009527429,0.00009678635,0.00003154299,0.00015733416,0.11363853,0.4530991,0.002431235,0.4264461,0.000998537],"about_ca_topic_score_codex":0.00014444186,"about_ca_topic_score_gemma":0.00003312259,"teacher_disagreement_score":0.36570942,"about_ca_system_score_codex":0.00006902215,"about_ca_system_score_gemma":0.000874906,"threshold_uncertainty_score":0.9999763},"labels":[],"label_agreement":null},{"id":"W4386798604","doi":"10.1038/s41597-023-02502-7","title":"Whole genomes from bacteria collected at diagnostic units around the world 2020","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier Universitaire de Sherbrooke","funders":"Horizon 2020 Framework Programme; Novo Nordisk Fonden; European Commission","keywords":"Genome; Bacteria; Biology; Computational biology; Evolutionary biology; Genetics; Gene","score_opus":0.04050191828275441,"score_gpt":0.25942383480733133,"score_spread":0.21892191652457693,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386798604","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":[0.9831501,0.0022079572,0.0000074156424,0.00076150463,0.0017137795,0.00021646215,0.011379949,0.000012008097,0.00055078545],"genre_scores_gemma":[0.9036604,0.0004958813,0.00021083328,0.00021342655,0.0006140818,0.000034975692,0.039309073,0.000030783754,0.0554305],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99862283,0.000063134365,0.00016887502,0.00069829763,0.00015253472,0.00029434555],"domain_scores_gemma":[0.9978731,0.00014629209,0.00006181548,0.0017664855,0.00008495387,0.00006735143],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003629392,0.00013422486,0.000114361224,0.000045601013,0.0006003751,0.00021088026,0.0011475513,0.00004091218,0.00009095681],"category_scores_gemma":[0.00038032586,0.000101676174,0.000027125774,0.0009064334,0.00025610934,0.0000019058426,0.0024710025,0.000050523835,0.00044548602],"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":[0.00000965792,0.000009999941,0.0030703775,0.0000027111473,0.00006506907,0.0000034171153,0.000088194276,0.000023563902,0.4120188,0.000004864372,0.58422047,0.00048284998],"study_design_scores_gemma":[0.00018385127,0.000017406634,0.07085438,0.000005731978,0.000029285677,0.0000013157278,0.00014116541,0.0001729938,0.010075166,0.000114486,0.91826355,0.00014065801],"about_ca_topic_score_codex":0.000029367313,"about_ca_topic_score_gemma":0.0037485294,"teacher_disagreement_score":0.40194365,"about_ca_system_score_codex":0.000012280272,"about_ca_system_score_gemma":0.00010386361,"threshold_uncertainty_score":0.572597},"labels":[],"label_agreement":null},{"id":"W4386829292","doi":"10.1038/s41597-023-02535-y","title":"A daily high-resolution (1 km) human thermal index collection over the North China Plain from 2003 to 2020","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"Urban Heat Island Mitigation","field":"Environmental Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario; University of Toronto","funders":"National Natural Science Foundation of China","keywords":"China; Index (typography); Environmental science; Coastal plain; Geography; Remote sensing; Biology; Ecology; Archaeology; World Wide Web; Computer science","score_opus":0.02063176456647712,"score_gpt":0.2386361082318871,"score_spread":0.21800434366541,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386829292","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":[0.99286956,0.000008468101,0.00028657616,0.0005537228,0.0013760774,0.00047355006,0.0033040077,0.00010074058,0.0010272751],"genre_scores_gemma":[0.98098207,0.0000017298015,0.00014369181,0.00012833532,0.00014500604,0.000030823074,0.008981004,0.000014520649,0.0095728375],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.997997,0.00010562211,0.00019322449,0.00076612516,0.0006082077,0.000329846],"domain_scores_gemma":[0.99838895,0.000030957508,0.000060718554,0.0014067168,0.000011698371,0.000100981604],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0008008709,0.00012013792,0.00008889876,0.000069374255,0.0010078029,0.00027141403,0.0010445126,0.00004729046,0.0023823413],"category_scores_gemma":[0.00012819433,0.00009133754,0.000018235447,0.0025760676,0.0002155716,0.0005182964,0.001070463,0.00013247784,0.003564421],"study_design_candidate":"not_applicable","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":[0.00001145268,0.000027901366,0.06735595,0.0000011861057,0.0000071181253,0.0000032198468,0.00077302335,0.0011670737,0.011800557,0.000014104635,0.9174631,0.001375299],"study_design_scores_gemma":[0.00020671908,0.00002019789,0.9169797,0.0000064035403,0.000011758275,5.404648e-7,0.00005167868,0.014826182,0.00024832052,0.0001853334,0.06734252,0.00012070348],"about_ca_topic_score_codex":0.0064627095,"about_ca_topic_score_gemma":0.021587735,"teacher_disagreement_score":0.8501206,"about_ca_system_score_codex":0.0001460349,"about_ca_system_score_gemma":0.000031674816,"threshold_uncertainty_score":0.9985296},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W4387014311","doi":"10.1038/s41597-023-02513-4","title":"Integrative GWAS and co-localisation analysis suggests novel genes associated with age-related multimorbidity","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"Chronic Disease Management Strategies","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Discovery Centre","funders":"Medical Research Council; Wellcome Trust","keywords":"Genome-wide association study; Computational biology; Gene; Biology; Genetics; Evolutionary biology; Single-nucleotide polymorphism; Genotype","score_opus":0.13345698917719945,"score_gpt":0.3774755081471648,"score_spread":0.24401851896996535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387014311","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":[0.9852556,0.0001380457,0.0011305312,0.00089960796,0.00045069886,0.0007876654,0.00610946,0.0004983068,0.0047300914],"genre_scores_gemma":[0.904862,0.000023375884,0.00017468259,0.000028113844,0.000020623198,0.000011195743,0.08566515,0.000014288858,0.009200578],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9980616,0.00005530766,0.00023712417,0.0008222985,0.0005501551,0.00027352152],"domain_scores_gemma":[0.99830574,0.00010330439,0.00012728114,0.001197962,0.0001339286,0.00013178228],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011250048,0.00016505158,0.00029403303,0.00053832337,0.00023451263,0.0003152432,0.0003245012,0.000055496617,0.00027272457],"category_scores_gemma":[0.0004437446,0.00012290859,0.000045944467,0.0032742417,0.0007263048,0.00038199747,0.00032211654,0.000118997414,0.000085806765],"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":[0.0004833766,0.002617163,0.18319449,0.00061882427,0.021120487,0.0013294457,0.0060559968,0.004223521,0.014963602,0.004844771,0.73645014,0.02409816],"study_design_scores_gemma":[0.0033182863,0.00010268202,0.72892493,0.00022474334,0.004329447,0.0000041495127,0.0027279474,0.25049254,0.00030615646,0.00024529675,0.008925474,0.0003983574],"about_ca_topic_score_codex":0.00019640524,"about_ca_topic_score_gemma":0.0014523254,"teacher_disagreement_score":0.7275247,"about_ca_system_score_codex":0.000090709764,"about_ca_system_score_gemma":0.00016498027,"threshold_uncertainty_score":0.50120664},"labels":[],"label_agreement":null},{"id":"W4387188565","doi":"10.1038/s41597-023-02579-0","title":"ecolo-zip: A global, rich and granular characterization of biogeophysical ecology for 1.5 million postal codes","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"Land Use and Ecosystem Services","field":"Environmental Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Karl Landsteiner Privatuniversität für Gesundheitswissenschaften","keywords":"Geospatial analysis; Shuttle Radar Topography Mission; Granularity; Geography; Vegetation (pathology); Scale (ratio); Resource (disambiguation); Remote sensing; Climate change; Environmental resource management; Digital elevation model; Ecology; Physical geography; Data science; Computer science; Environmental science; Cartography; Biology","score_opus":0.021260797631806445,"score_gpt":0.2548493101242048,"score_spread":0.23358851249239837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387188565","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":[0.9900652,0.0000070256483,0.00006795518,0.00031319677,0.00035710091,0.00025435112,0.008865263,0.000030846968,0.000039038743],"genre_scores_gemma":[0.99180573,0.00001424633,0.000090517286,0.000048332455,0.000030267332,0.000009056344,0.0079474775,0.0000044805406,0.000049862305],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99899906,0.000025572763,0.00015514123,0.00046699878,0.00015217515,0.000201073],"domain_scores_gemma":[0.99939984,0.000027401169,0.00007448632,0.0004233635,0.000012009897,0.000062875304],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044431025,0.00007017527,0.00012523253,0.000027246779,0.00017080971,0.00007142365,0.0004320279,0.000043108153,0.000115650226],"category_scores_gemma":[0.000028360375,0.00005662914,0.000017081808,0.00053253275,0.0000783542,0.00036423074,0.0006424537,0.000017331413,0.00025164057],"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":[0.00012722283,0.00029819133,0.56322706,0.00047578182,0.000048612816,0.000008592236,0.0007261241,0.000120193436,0.3926814,0.00018906641,0.034431357,0.0076664165],"study_design_scores_gemma":[0.0005946299,0.00015678104,0.88350534,0.000022399108,0.000048963895,0.0000035510725,0.00011195082,0.07887046,0.0045705694,0.00068457477,0.031206332,0.00022444055],"about_ca_topic_score_codex":0.00007693284,"about_ca_topic_score_gemma":0.000599061,"teacher_disagreement_score":0.38811082,"about_ca_system_score_codex":0.000013557619,"about_ca_system_score_gemma":0.000009723872,"threshold_uncertainty_score":0.32344142},"labels":[],"label_agreement":null},{"id":"W4387389354","doi":"10.1038/s41597-023-02588-z","title":"Transcriptome profiling of Fraxinus excelsior genotypes infested by emerald ash borer","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"Forest Insect Ecology and Management","field":"Environmental 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":"Natural Resources Canada; Canadian Forest Service","funders":"Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Fraxinus; Biology; Emerald ash borer; Transcriptome; Botany; Gene; Gene expression","score_opus":0.029734239144336885,"score_gpt":0.26384104144540427,"score_spread":0.2341068023010674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387389354","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":[0.99171597,0.00006221956,0.00021225515,0.00043146705,0.0014624958,0.00043839516,0.0016685212,0.00014839589,0.0038602985],"genre_scores_gemma":[0.97555584,0.000017574816,0.0010497896,0.00022309452,0.000018589097,0.000023866456,0.0041383654,0.00001621499,0.018956657],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983463,0.00004289431,0.00024893082,0.00063448,0.0003711678,0.00035618164],"domain_scores_gemma":[0.99860305,0.000026246358,0.0000735664,0.0012172571,0.000009492869,0.00007041405],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0010880514,0.00010859773,0.00012840438,0.00008915844,0.00023797103,0.000054764645,0.0012520376,0.000057476955,0.0030173978],"category_scores_gemma":[0.00006911128,0.00009815181,0.00002975224,0.0010217179,0.0005228488,0.00041324133,0.0010177138,0.00009337904,0.0023158304],"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":[0.000009298729,0.00008602213,0.005070162,0.000023485893,0.00001787248,0.000007940019,0.0002867908,0.00014054653,0.22288479,0.00017965582,0.7686253,0.0026680976],"study_design_scores_gemma":[0.000585074,0.0000916509,0.15006468,0.000021371305,0.000058924143,0.000002860926,0.00020601395,0.003757171,0.027190566,0.001578118,0.8160504,0.00039318032],"about_ca_topic_score_codex":0.00022742843,"about_ca_topic_score_gemma":0.0003389461,"teacher_disagreement_score":0.19569422,"about_ca_system_score_codex":0.000026452388,"about_ca_system_score_gemma":0.000015697145,"threshold_uncertainty_score":0.998461},"labels":[],"label_agreement":null},{"id":"W4387502842","doi":"10.1038/s41597-023-02584-3","title":"The 10-m cotton maps in Xinjiang, China during 2018–2021","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"Remote Sensing in Agriculture","field":"Environmental Science","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":"University of Toronto","funders":"Youth Innovation Promotion Association; Youth Innovation Promotion Association of the Chinese Academy of Sciences; Xinjiang Production and Construction Corps; National Natural Science Foundation of China","keywords":"China; Phenology; Remote sensing; Cartography; Geography; Mathematics; Forestry; Agronomy; Biology","score_opus":0.017986716668803852,"score_gpt":0.23649426800612575,"score_spread":0.2185075513373219,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387502842","genre_codex":"empirical","genre_gemma":"other","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":[0.9613167,0.00009421868,0.0000055768273,0.003097708,0.0034762279,0.00034366007,0.0005286782,0.00013260647,0.031004593],"genre_scores_gemma":[0.4032147,0.00014045357,0.000910134,0.000047181886,0.0002879128,0.000004522122,0.003702435,0.00004359251,0.59164906],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979228,0.000074829295,0.00019521735,0.000776518,0.0005558504,0.00047483045],"domain_scores_gemma":[0.9977605,0.000045434943,0.000059872822,0.0020509565,0.000004982479,0.000078258345],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0014725325,0.00011654778,0.00008645206,0.00005031703,0.00067158934,0.00045497934,0.0017855492,0.000048256086,0.00078136433],"category_scores_gemma":[0.00023614925,0.00007331458,0.000024965037,0.0016673268,0.00048368055,0.00040283898,0.002322248,0.00016353447,0.013927788],"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":[0.0000037710684,0.000016510636,0.0015547533,0.000004483198,0.0000025033814,0.000028459963,0.0002967893,0.000300506,0.021751259,0.0000065647,0.9689507,0.0070837247],"study_design_scores_gemma":[0.00013170094,0.0000037140403,0.36259902,0.00002677104,0.0000033244091,0.00000993832,0.00021383665,0.0035719392,0.0012181059,0.0002752975,0.6318001,0.0001462613],"about_ca_topic_score_codex":0.00019770523,"about_ca_topic_score_gemma":0.0012060516,"teacher_disagreement_score":0.5606445,"about_ca_system_score_codex":0.00010664834,"about_ca_system_score_gemma":0.000014600953,"threshold_uncertainty_score":0.98684},"labels":[],"label_agreement":null},{"id":"W4387642549","doi":"10.1038/s41597-023-02594-1","title":"A high-quality chromosome-level wild rice genome of Oryza coarctata","year":2023,"lang":"en","type":"article","venue":"Scientific Data","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":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Biotechnology Research Institute","funders":"Ministry of Science and Technology of the People's Republic of China","keywords":"Oryza; Biology; Oryza sativa; Genome; Chromosome; Botany; Genetics; Gene","score_opus":0.10197041917225738,"score_gpt":0.31836293382451614,"score_spread":0.21639251465225876,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387642549","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":[0.9780034,0.00069973135,0.00015094025,0.00018658397,0.00092835876,0.00017145523,0.019490631,0.000009666964,0.00035924345],"genre_scores_gemma":[0.9849653,0.00019834352,0.0012781292,0.00005597304,0.00015015248,0.000009150761,0.009982534,0.000016708116,0.003343678],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983017,0.000054337772,0.00030823008,0.0007909212,0.00024246027,0.00030235187],"domain_scores_gemma":[0.9972814,0.000023971614,0.00012675121,0.0023653684,0.00012801633,0.000074509284],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011447368,0.00013164734,0.00019114617,0.00007424961,0.00018521852,0.00005604242,0.0013571024,0.00006384812,0.000028106093],"category_scores_gemma":[0.0002351235,0.00012398328,0.00004856695,0.00043725534,0.000373981,0.0000025372533,0.0021443176,0.000049889415,0.0001038686],"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":[0.000014480537,0.000039574817,0.00042309836,0.00004768799,0.00006302778,0.0000015931068,0.000065005406,0.000021117037,0.9625237,0.00011777623,0.035968974,0.00071398885],"study_design_scores_gemma":[0.0012247406,0.0001977729,0.22525132,0.000028191911,0.00008313561,0.0000084546955,0.00056145724,0.00012435671,0.25360656,0.001208158,0.5169883,0.00071759376],"about_ca_topic_score_codex":0.00009387604,"about_ca_topic_score_gemma":0.00010580919,"teacher_disagreement_score":0.70891714,"about_ca_system_score_codex":0.0000062116005,"about_ca_system_score_gemma":0.00011822543,"threshold_uncertainty_score":0.5055891},"labels":[],"label_agreement":null},{"id":"W4387692943","doi":"10.1038/s41597-023-02610-4","title":"Fully resolved assembly of Fusarium proliferatum DSM106835 genome","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"Plant Pathogens and Fungal Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Agriculture and Agri-Food Canada","funders":"United Arab Emirates University","keywords":"Fusarium proliferatum; Sequence assembly; Genome; Biology; Contig; Fusarium; Genetics; Gene; Reference genome; Genome size; Computational biology; Transcriptome","score_opus":0.04040575584233469,"score_gpt":0.2769645422456526,"score_spread":0.2365587864033179,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387692943","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":[0.9206061,0.000733435,0.00025810924,0.00017940968,0.0012274575,0.000298765,0.07454167,0.000056926165,0.0020981224],"genre_scores_gemma":[0.8581935,0.00006902601,0.00025036302,0.00007702505,0.00020832548,0.000011390326,0.13189997,0.000020273965,0.009270108],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99855804,0.000039666804,0.00019179624,0.00065524434,0.00023750523,0.00031773918],"domain_scores_gemma":[0.9980982,0.0000069120742,0.000049118767,0.0016428347,0.00009931501,0.00010363486],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000682917,0.00010588287,0.00011654977,0.00009477199,0.00013946973,0.00009328603,0.00095757656,0.00007160496,0.00002648232],"category_scores_gemma":[0.00012797189,0.000085703985,0.00004900054,0.00030586965,0.00013872833,0.000010398492,0.0010164853,0.0000471054,0.0001686377],"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":[0.000032308075,0.000043049527,0.00030206796,0.000027546337,0.000023359687,0.000010540531,0.000012237443,0.000010811886,0.926812,0.000022355822,0.07247528,0.00022843132],"study_design_scores_gemma":[0.00034498775,0.00010721036,0.016738063,0.000015577622,0.00005339972,0.000010913433,0.000082595616,0.00071136514,0.3304755,0.000055763492,0.6511126,0.00029201934],"about_ca_topic_score_codex":0.0000039500055,"about_ca_topic_score_gemma":0.000015933087,"teacher_disagreement_score":0.5963365,"about_ca_system_score_codex":0.000003263721,"about_ca_system_score_gemma":0.00012926948,"threshold_uncertainty_score":0.34949073},"labels":[],"label_agreement":null},{"id":"W4387844510","doi":"10.1038/s41597-023-02638-6","title":"Non-pharmaceutical interventions to combat COVID-19 in the Americas described through daily sub-national data","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"COVID-19 epidemiological studies","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Inter-American Development Bank","keywords":"Coronavirus disease 2019 (COVID-19); 2019-20 coronavirus outbreak; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Psychological intervention; Pandemic; Geography; Medicine; Virology; Outbreak; Nursing; Internal medicine; Infectious disease (medical specialty)","score_opus":0.8428128399512812,"score_gpt":0.6118075745123546,"score_spread":0.23100526543892663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387844510","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":[0.12031848,0.00093078444,0.33601105,0.42458203,0.0077259047,0.008002977,0.09506971,0.0019217972,0.0054372577],"genre_scores_gemma":[0.8389106,0.00027056786,0.05002365,0.04964719,0.0006899669,0.0006443165,0.05611252,0.00011616023,0.003585042],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99601173,0.00040208336,0.0007066745,0.0013670118,0.0009372781,0.0005752097],"domain_scores_gemma":[0.988589,0.0070057474,0.00015250753,0.003944119,0.00010933001,0.00019933435],"candidate_categories":["metaresearch","open_science","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.013305044,0.00020379577,0.000358554,0.00018791221,0.0006456607,0.0003158528,0.0058918563,0.000057152884,0.0002330037],"category_scores_gemma":[0.055301696,0.00013952736,0.000085856045,0.002709989,0.00067841844,0.000516385,0.008506398,0.00031618972,0.001124305],"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":[0.000014217218,0.00023544247,0.0015530079,0.0001453183,0.00003064224,0.000023516499,0.0007935127,0.00003706436,0.00014185459,0.009429253,0.98696023,0.00063596433],"study_design_scores_gemma":[0.0006866385,0.000043227254,0.013124511,0.000112648406,0.000099081575,0.000009447793,0.0018686248,0.013465633,0.000028272869,0.14357767,0.82661927,0.00036500013],"about_ca_topic_score_codex":0.00022857833,"about_ca_topic_score_gemma":0.0012949358,"teacher_disagreement_score":0.7185921,"about_ca_system_score_codex":0.00018884719,"about_ca_system_score_gemma":0.00026080426,"threshold_uncertainty_score":0.99965346},"labels":[],"label_agreement":null},{"id":"W4387875155","doi":"10.1038/s41597-023-02566-5","title":"1-km resolution rebound surfaces and paleotopography of glaciated North America since the Last Glacial Maximum","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"Geology and Paleoclimatology Research","field":"Earth and Planetary Sciences","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":"Université du Québec à Montréal; Geological Survey of Canada; Natural Resources Canada","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Resources Canada; Natural Sciences and Engineering Research Council of Canada; Government of Canada; Université du Québec à Montréal","keywords":"Glacial period; Geology; Physical geography; Earth science; Geomorphology; Geography","score_opus":0.04252116280405769,"score_gpt":0.26417593035425047,"score_spread":0.22165476755019278,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387875155","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":[0.99425966,0.0004943117,0.000007487863,0.0009423089,0.0006504957,0.00017280044,0.0025747921,0.000044494936,0.0008536372],"genre_scores_gemma":[0.99142385,0.00014409843,0.00009626115,0.000027756052,0.000021870042,8.679791e-7,0.00804463,0.0000016784335,0.0002389773],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9983012,0.00025027248,0.0001986319,0.00051522907,0.00033134848,0.00040329865],"domain_scores_gemma":[0.99855167,0.00034316056,0.00009082563,0.00087174727,0.00006502568,0.00007758166],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015074166,0.0000939356,0.00014758033,0.00019401174,0.0007964899,0.0001230417,0.0009789381,0.00005912472,0.00022245641],"category_scores_gemma":[0.00022240267,0.000064296604,0.000024406983,0.0018256257,0.0026104336,0.00025472784,0.0002077163,0.00017210598,0.00044467015],"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":[0.000032462096,0.000008775392,0.99122083,0.0000165596,0.000015823878,0.000008922599,0.00017574051,0.00013141884,0.000013518965,0.000014442866,0.006458627,0.0019028893],"study_design_scores_gemma":[0.00011294334,0.00003719823,0.9626396,0.0000067874494,0.000011513947,0.000007397015,0.0002601991,0.009002339,0.000008233661,0.00045292228,0.027387587,0.000073328694],"about_ca_topic_score_codex":0.00043697437,"about_ca_topic_score_gemma":0.045389656,"teacher_disagreement_score":0.04495268,"about_ca_system_score_codex":3.6467378e-7,"about_ca_system_score_gemma":0.00007500468,"threshold_uncertainty_score":0.9720295},"labels":[],"label_agreement":null},{"id":"W4387879092","doi":"10.1038/s41597-023-02549-6","title":"High-resolution (1 km) Köppen-Geiger maps for 1901–2099 based on constrained CMIP6 projections","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"Climate variability and models","field":"Environmental Science","cited_by":718,"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":"Centrum fÖr Personcentrerad Vård","keywords":"Climatology; Geiger counter; Coupled model intercomparison project; Climate model; Environmental science; Precipitation; Climate change; Representative Concentration Pathways; Climate system; Meteorology; Physical geography; Geography; Geology; Physics","score_opus":0.08465940337462678,"score_gpt":0.29728748149711537,"score_spread":0.21262807812248857,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387879092","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":[0.4947998,0.00002763654,0.0738288,0.028961748,0.029979775,0.013484862,0.291318,0.0034190472,0.06418035],"genre_scores_gemma":[0.9230788,0.000003979293,0.013417568,0.00048597026,0.00015662792,0.0002753999,0.04925799,0.000044234814,0.013279425],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976709,0.0000630031,0.00025361075,0.0010790323,0.000455365,0.0004780889],"domain_scores_gemma":[0.9977878,0.00019865563,0.00006902524,0.0018122445,0.000018566425,0.00011376359],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0023371363,0.00014084506,0.0001325582,0.00013818589,0.0007699585,0.00022680996,0.0008485333,0.00007307643,0.0015116319],"category_scores_gemma":[0.00038447572,0.0001293417,0.000054075284,0.0010012698,0.0006086259,0.00041679127,0.00058434124,0.0001003869,0.0023690008],"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":[0.00006577038,0.00042146456,0.000582324,0.00005421023,0.000011902997,0.0000040659406,0.00022383187,0.034027416,0.01714303,0.0022083079,0.93992335,0.005334345],"study_design_scores_gemma":[0.00093633233,0.000102987855,0.003993369,0.000036578815,0.000037358644,0.0000020613406,0.00014151202,0.72266,0.0007375223,0.007594323,0.26341987,0.0003380718],"about_ca_topic_score_codex":0.00034974012,"about_ca_topic_score_gemma":0.0006159175,"teacher_disagreement_score":0.6886326,"about_ca_system_score_codex":0.0001273695,"about_ca_system_score_gemma":0.00007108033,"threshold_uncertainty_score":0.9994011},"labels":[],"label_agreement":null},{"id":"W4387880964","doi":"10.1038/s41597-023-02651-9","title":"A geospatial database of close-to-reality travel times to obstetric emergency care in 15 Nigerian conurbations","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"Global Maternal and Child Health","field":"Medicine","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario; Women's College Hospital; University of Toronto","funders":"Fundação para a Ciência e a Tecnologia; Balliol College, University of Oxford; Fonds Wetenschappelijk Onderzoek; Nuffield College, University of Oxford; Bundesministerium für Gesundheit; Royal Society; Wellcome Trust; Google; Vlaamse regering; Bill and Melinda Gates Foundation","keywords":"Geospatial analysis; Geography; Database; Computer science; Cartography","score_opus":0.057429287489141036,"score_gpt":0.3576735155331557,"score_spread":0.3002442280440146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387880964","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":[0.94575673,0.00020413326,0.000072797884,0.0027277758,0.002490188,0.0008382691,0.045847442,0.000052488853,0.0020102013],"genre_scores_gemma":[0.97814417,0.0000209104,0.00033152176,0.00017566483,0.000096498654,0.000012438027,0.017884774,0.000010241264,0.0033238037],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9982109,0.000043385833,0.00040231098,0.0005761031,0.0004482815,0.00031903555],"domain_scores_gemma":[0.99799085,0.00002402184,0.00005633133,0.0014886183,0.00014980498,0.0002903792],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006044658,0.00009667949,0.00022024721,0.00039838182,0.00010512869,0.000022236187,0.0005423289,0.00003275602,0.00048509656],"category_scores_gemma":[0.0005498544,0.00008552815,0.000027160118,0.0023294024,0.000049745715,0.00011247103,0.0005111378,0.00008532095,0.00066410215],"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":[0.00016157454,0.00031055853,0.06194703,0.0008303519,0.000024911309,0.00006431765,0.0047625084,0.000025760079,0.0068372823,0.0007129186,0.9157678,0.008554996],"study_design_scores_gemma":[0.0009756116,0.00018480798,0.90919644,0.00033118034,0.000046770794,0.0000050808035,0.0028439132,0.00045440302,0.0010062732,0.00023614636,0.08451339,0.00020599006],"about_ca_topic_score_codex":0.0020558636,"about_ca_topic_score_gemma":0.004984777,"teacher_disagreement_score":0.8472494,"about_ca_system_score_codex":0.000050374572,"about_ca_system_score_gemma":0.00023626181,"threshold_uncertainty_score":0.8535911},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W4388077294","doi":"10.1038/s41597-023-02670-6","title":"Author Correction: Non-pharmaceutical interventions to combat COVID-19 in the Americas described through daily sub-national data","year":2023,"lang":"en","type":"erratum","venue":"Scientific Data","topic":"Pharmaceutical Practices and Patient Outcomes","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Instituto Tecnológico y de Estudios Superiores de Monterrey; University of Miami","keywords":"Coronavirus disease 2019 (COVID-19); 2019-20 coronavirus outbreak; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Psychological intervention; Pandemic; MEDLINE; Geography; Data science; Medicine; Virology; Computer science; Political science; Outbreak; Internal medicine; Nursing; Infectious disease (medical specialty)","score_opus":0.6615557178082387,"score_gpt":0.5739378310531165,"score_spread":0.08761788675512228,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388077294","genre_codex":"editorial","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00038376937,0.0031766586,0.021627307,0.29229996,0.51255214,0.009677264,0.11599855,0.0008316255,0.043452725],"genre_scores_gemma":[0.004525303,0.00051619974,0.002123461,0.033695277,0.0035854469,0.0002563132,0.50305563,0.00018002538,0.45206237],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9930946,0.00050333113,0.0010477825,0.0022087882,0.0024013193,0.0007441611],"domain_scores_gemma":[0.99139225,0.0018997476,0.00038712795,0.005370942,0.00027409493,0.00067582855],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.007253203,0.00044730332,0.0006786797,0.000536042,0.0006763352,0.00080540794,0.005071397,0.00027472398,0.0009925265],"category_scores_gemma":[0.015735239,0.00033760452,0.00020032593,0.0031038139,0.00068106863,0.0011225594,0.0045349966,0.0024181218,0.0021802383],"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":[0.00017043836,0.0006173527,0.00046063878,0.0006410089,0.00013187654,0.00015436535,0.00051555317,0.000010107686,0.000024489542,0.00008946104,0.9953861,0.0017985569],"study_design_scores_gemma":[0.0009552279,0.00010081154,0.0016561644,0.00053782423,0.0006213441,0.00010404638,0.0007751325,0.019938538,0.0000057829384,0.0001723924,0.97478616,0.00034659344],"about_ca_topic_score_codex":0.00037653433,"about_ca_topic_score_gemma":0.0010142677,"teacher_disagreement_score":0.5089667,"about_ca_system_score_codex":0.00040851062,"about_ca_system_score_gemma":0.0022840104,"threshold_uncertainty_score":0.9999207},"labels":[],"label_agreement":null},{"id":"W4388305010","doi":"10.1038/s41597-023-02523-2","title":"CreelCat, a Catalog of United States Inland Creel and Angler Survey Data","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"Archaeology and Natural History","field":"Social Sciences","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":"Memorial University of Newfoundland","funders":"U.S. Geological Survey; U.S. Department of the Interior","keywords":"Geography","score_opus":0.17752624405968445,"score_gpt":0.37486289223184516,"score_spread":0.1973366481721607,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388305010","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":[0.8737855,0.0049790367,0.00013523488,0.0023245118,0.003861016,0.0005567394,0.11118013,0.00027726582,0.0029005636],"genre_scores_gemma":[0.6781252,0.0015206782,0.00073444395,0.00013311431,0.00010715696,0.00000306384,0.29713973,0.000015895495,0.022220744],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99823725,0.00037803964,0.00016585363,0.0006030841,0.00032846804,0.00028731156],"domain_scores_gemma":[0.9974156,0.00052651746,0.000080562415,0.0017577438,0.000112500646,0.000107085434],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.006881113,0.00007178711,0.00012900091,0.0002865378,0.00075304846,0.000021519347,0.002233843,0.00007514445,0.000072179835],"category_scores_gemma":[0.0017748409,0.00006395096,0.000008180512,0.0016380138,0.0035596953,0.0005863931,0.0026787831,0.00011884493,0.000092442446],"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":[0.000021735339,0.000020331512,0.03886218,0.000014220082,0.000015764734,0.0000066546236,0.0055205203,0.0000010212932,0.00003846316,0.0002767992,0.9510454,0.0041769175],"study_design_scores_gemma":[0.00015304437,0.000011399795,0.10963879,0.000012855958,0.000013557365,6.860524e-7,0.001163575,0.0011507578,0.000008546746,0.0017183737,0.88601637,0.00011204331],"about_ca_topic_score_codex":0.013929268,"about_ca_topic_score_gemma":0.048473064,"teacher_disagreement_score":0.19566032,"about_ca_system_score_codex":0.000012961165,"about_ca_system_score_gemma":0.00020327597,"threshold_uncertainty_score":0.99915206},"labels":[],"label_agreement":null},{"id":"W4388490712","doi":"10.1038/s41597-023-02719-6","title":"Publisher Correction: 1-km resolution rebound surfaces and paleotopography of glaciated North America since the Last Glacial Maximum","year":2023,"lang":"en","type":"erratum","venue":"Scientific Data","topic":"Geology and Paleoclimatology Research","field":"Earth and Planetary Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université du Québec à Montréal; Geological Survey of Canada; Natural Resources Canada","funders":"","keywords":"Glacial period; Physical geography; Geology; Last Glacial Maximum; Geography; Geomorphology","score_opus":0.03695853775976452,"score_gpt":0.2562997780948711,"score_spread":0.21934124033510657,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388490712","genre_codex":"editorial","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1391657,0.018943613,0.00005905696,0.0068714144,0.69323057,0.0028038893,0.0337549,0.00060363876,0.10456721],"genre_scores_gemma":[0.13194883,0.003925537,0.00034223121,0.00025183265,0.0016001789,0.000018277815,0.48447073,0.000049364764,0.377393],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99636614,0.00053777976,0.0004416362,0.0012158762,0.0007712464,0.0006672902],"domain_scores_gemma":[0.9969412,0.00050736126,0.0003558616,0.0018141221,0.00023840123,0.00014306094],"candidate_categories":["sts"],"consensus_categories":["sts"],"category_scores_codex":[0.0021690964,0.0002716094,0.0004247082,0.00045877628,0.0013100805,0.0006160352,0.002198125,0.00038327562,0.0005985009],"category_scores_gemma":[0.0007099435,0.00019545041,0.000071469316,0.0025920281,0.004377085,0.0005813571,0.00043473626,0.0010807335,0.00042828673],"study_design_candidate":"not_applicable","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":[0.000027908907,0.000009475811,0.46566504,0.000038833965,0.00003788338,0.00000965235,0.000075664866,0.000026461237,1.2711466e-7,0.0000010653766,0.53310615,0.0010017349],"study_design_scores_gemma":[0.00009168621,0.00005022063,0.51683545,0.000037834467,0.00004121817,0.000017971184,0.00020626794,0.0026431635,1.6535064e-7,0.00021917757,0.4797038,0.0001530485],"about_ca_topic_score_codex":0.0018516814,"about_ca_topic_score_gemma":0.2420038,"teacher_disagreement_score":0.6916304,"about_ca_system_score_codex":0.0000018571815,"about_ca_system_score_gemma":0.00043871216,"threshold_uncertainty_score":0.9999901},"labels":[],"label_agreement":null},{"id":"W4388592011","doi":"10.1038/s41597-023-02633-x","title":"Global dataset of soil organic carbon in tidal marshes","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"Coastal wetland ecosystem dynamics","field":"Environmental Science","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":"Simon Fraser University; McGill University","funders":"Agencia Estatal de Investigación; Fundação para a Ciência e a Tecnologia; South African Agency for Science and Technology Advancement; Sight Research UK; Xunta de Galicia; Deutsche Forschungsgemeinschaft; National Research Foundation; Ministerio de Ciencia e Innovación; Higher Education Funding Council for Wales; Nelson Mandela University; U.S. Department of Defense; Department of Science and Innovation, South Africa; Fundación Séneca; Natural Environment Research Council","keywords":"Marsh; Soil carbon; Environmental science; Total organic carbon; Oceanography; Carbon fibers; Wetland; Ecology; Soil science; Geology; Soil water; Biology; Computer science","score_opus":0.02164637414739909,"score_gpt":0.25003930628751136,"score_spread":0.22839293214011228,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388592011","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":[0.9561049,0.0000069899675,0.00001538817,0.0000666026,0.00065615046,0.000111152214,0.041078813,0.00003348421,0.0019265594],"genre_scores_gemma":[0.9700817,0.000003502977,0.000087059656,0.000008092558,0.000012053606,0.0000020189777,0.029030334,0.0000069138096,0.000768357],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99837404,0.000037208734,0.00026141846,0.0006108923,0.0004123971,0.0003040281],"domain_scores_gemma":[0.99809355,0.000023364018,0.000066564135,0.0017458173,0.000003608727,0.00006710891],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012604032,0.00008765041,0.00012364796,0.00005660559,0.0000576268,0.00006771069,0.0014310798,0.00003480297,0.00068859727],"category_scores_gemma":[0.00010072973,0.00008198457,0.000012171351,0.0017279856,0.00019620902,0.0002815763,0.0038792482,0.000046322857,0.0011631934],"study_design_candidate":"observational","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":[0.00001829181,0.00012511146,0.54140353,0.00006553846,0.000009702604,0.000056342185,0.0001425292,0.0023973417,0.0059071807,0.000030817384,0.44353107,0.0063125785],"study_design_scores_gemma":[0.00058686396,0.00003342106,0.44409907,0.00005899637,0.000020836413,0.000018744882,0.00040269,0.49823245,0.00027911074,0.0010755968,0.054782044,0.00041017757],"about_ca_topic_score_codex":0.0027829972,"about_ca_topic_score_gemma":0.103783295,"teacher_disagreement_score":0.4958351,"about_ca_system_score_codex":0.00010324241,"about_ca_system_score_gemma":0.000029216648,"threshold_uncertainty_score":0.99961454},"labels":[],"label_agreement":null},{"id":"W4388729121","doi":"10.1038/s41597-023-02732-9","title":"Canada Source Watershed Polygons (Can-SWaP): A dataset for the protection of Canada’s municipal water supply","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"Hydrology and Watershed Management Studies","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":true,"ca_institutions":"Natural Resources Canada; Pacific Salmon Foundation; Ontario Forest Research Institute; Canadian Forest Service","funders":"Natural Resources Canada; U.S. Forest Service; Indigenous Services Canada","keywords":"Swap (finance); Watershed; Environmental science; Water supply; Surface water; Water resource management; STREAMS; Hydrology (agriculture); Environmental resource management; Business; Environmental engineering; Computer science; Engineering","score_opus":0.035135982471503416,"score_gpt":0.23212180834235696,"score_spread":0.19698582587085356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388729121","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":[0.5864483,0.00005541863,0.0011441116,0.1647041,0.0068983035,0.005039454,0.23452392,0.00014731288,0.0010390569],"genre_scores_gemma":[0.9582328,0.000003276433,0.00004377261,0.00051720435,0.0000280875,0.00008225849,0.025681568,0.000011349988,0.0153996665],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982961,0.000047930276,0.00019500771,0.0005288954,0.0003980733,0.0005339898],"domain_scores_gemma":[0.9983773,0.000056886278,0.00004838781,0.0014506197,0.000007948761,0.000058808124],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011927502,0.00011555481,0.000118185846,0.000036500947,0.0010387059,0.00004640561,0.0014527343,0.000023757535,0.00036840304],"category_scores_gemma":[0.00007124284,0.00006761491,0.000016315576,0.00024768568,0.00043108917,0.0001553935,0.00219144,0.00007783863,0.00004481154],"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":[0.00001816122,0.00001012923,0.00046569444,0.000015017602,0.0000402158,0.0000034775749,0.00035576013,0.0013934078,0.0014584691,0.000005570523,0.9956487,0.00058538927],"study_design_scores_gemma":[0.0001787945,0.00001287962,0.0020906879,0.0000035913315,0.00003866983,0.0000011246871,0.00058486924,0.011489417,0.004067455,0.0000804475,0.98134285,0.00010923166],"about_ca_topic_score_codex":0.9896568,"about_ca_topic_score_gemma":0.99913245,"teacher_disagreement_score":0.3717845,"about_ca_system_score_codex":0.00010832719,"about_ca_system_score_gemma":0.00014580898,"threshold_uncertainty_score":0.7988992},"labels":[],"label_agreement":null},{"id":"W4389224631","doi":"10.1038/s41597-023-02762-3","title":"EarSet: A Multi-Modal Dataset for Studying the Impact of Head and Facial Movements on In-Ear PPG Signals","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"Non-Invasive Vital Sign Monitoring","field":"Engineering","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bell (Canada)","funders":"","keywords":"Computer science; Photoplethysmogram; Computer vision; Artificial intelligence; Motion (physics); Head (geology); Modal; Face (sociological concept); Acoustics; Geology; Materials science; Physics","score_opus":0.15494409441810533,"score_gpt":0.3776348428945414,"score_spread":0.22269074847643608,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389224631","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":[0.9179697,0.00004993908,0.00039401485,0.000011115594,0.00077141484,0.00057832355,0.08016628,0.000043714645,0.00001550547],"genre_scores_gemma":[0.99243903,0.0000057214015,0.00026447157,0.0000036318906,0.000060114,0.000024364315,0.0071393847,0.000021053154,0.000042199143],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9988316,0.000024297502,0.00020544903,0.00037809552,0.0002459704,0.00031457236],"domain_scores_gemma":[0.99884135,0.0001531604,0.000033031396,0.0008984238,0.000019891548,0.000054119406],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010851293,0.00012277778,0.00014297065,0.00019115364,0.00013398386,0.00015309876,0.0006879787,0.000028382463,0.00001222552],"category_scores_gemma":[0.00015934343,0.00009302392,0.00002688421,0.000523968,0.00008954396,0.00030169534,0.000485105,0.000093640556,0.000034374156],"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":[0.00006517613,0.00019201048,0.029683359,0.00019073322,0.00019226962,0.000018560515,0.0015861325,0.027272502,0.8289454,0.000011153956,0.09423911,0.017603606],"study_design_scores_gemma":[0.008204168,0.00065379683,0.46469322,0.0008651838,0.00007956061,0.000004323083,0.0031768463,0.40868986,0.09504594,0.00082627503,0.016252007,0.0015088051],"about_ca_topic_score_codex":0.00016318762,"about_ca_topic_score_gemma":0.00011079525,"teacher_disagreement_score":0.7338995,"about_ca_system_score_codex":0.000041925898,"about_ca_system_score_gemma":0.000024582268,"threshold_uncertainty_score":0.37934053},"labels":[],"label_agreement":null},{"id":"W4389306898","doi":"10.1038/s41597-023-02752-5","title":"Introducing MEG-MASC a high-quality magneto-encephalography dataset for evaluating natural speech processing","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Baycrest Hospital","funders":"Agence Nationale de la Recherche","keywords":"Computer science; Replicate; Magnetoencephalography; Metadata; Decoding methods; Natural language processing; Speech recognition; Active listening; Artificial intelligence; Electroencephalography; Psychology; Communication; World Wide Web","score_opus":0.20122518404499928,"score_gpt":0.4144129988181525,"score_spread":0.21318781477315324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389306898","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":[0.67773795,0.0006442237,0.0029555804,0.02937683,0.025595967,0.0034072916,0.25851902,0.0014962251,0.00026686586],"genre_scores_gemma":[0.9258217,0.000008861398,0.013716616,0.0013516349,0.0007704549,0.0001673339,0.055187337,0.00005728395,0.002918775],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99473256,0.0002756915,0.00042988904,0.002649104,0.0012315798,0.0006811797],"domain_scores_gemma":[0.9932275,0.0037150611,0.00023081935,0.0025147682,0.00022442432,0.00008746253],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.008278781,0.0002267015,0.00027522756,0.00041492342,0.0019108253,0.0009022498,0.0019318393,0.00004506903,0.00005124093],"category_scores_gemma":[0.05851364,0.00020698435,0.000058513768,0.0030996287,0.00066110387,0.0016143421,0.0022077018,0.00024128579,0.00019427585],"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":[0.000044167893,0.000063692096,0.00019495712,0.00015829304,0.0000108981085,0.000007058506,0.0001807739,0.00007434348,0.30524522,0.00043609747,0.6541236,0.039460912],"study_design_scores_gemma":[0.002977672,0.000426991,0.016608251,0.00031190304,0.00021688474,0.000065601445,0.0015933146,0.19084086,0.10091271,0.021289768,0.6626315,0.002124559],"about_ca_topic_score_codex":0.000063460095,"about_ca_topic_score_gemma":0.00014549319,"teacher_disagreement_score":0.24808373,"about_ca_system_score_codex":0.00005258999,"about_ca_system_score_gemma":0.00018767647,"threshold_uncertainty_score":0.9993886},"labels":[],"label_agreement":null},{"id":"W4389426225","doi":"10.1038/s41597-023-02809-5","title":"A dataset of proteomic changes during human heat stress and heat acclimation","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"Thermoregulation and physiological responses","field":"Medicine","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":"Université de Montréal; Montreal Heart Institute","funders":"Fondation Institut de Cardiologie de Montréal; Institut de Cardiologie de Montréal; Canada Foundation for Innovation; Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Acclimatization; Heat stress; Context (archaeology); Biology; Multiplex; Medicine; Bioinformatics; Ecology; Animal science","score_opus":0.1357171603890788,"score_gpt":0.381036359776381,"score_spread":0.2453191993873022,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389426225","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":[0.97595775,0.000027858061,0.0000040724,0.0002870557,0.00007398218,0.00026059,0.023338838,0.000034414577,0.000015460044],"genre_scores_gemma":[0.9291868,0.000011155772,0.00008841799,0.000020389802,0.000033176693,0.0000070436117,0.070086114,0.0000046824666,0.0005621869],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9992428,0.000036596466,0.000119901706,0.00030945148,0.00017260421,0.00011867521],"domain_scores_gemma":[0.999051,0.000031686635,0.000023831635,0.0008112493,0.000023995959,0.000058260623],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039095114,0.000055256078,0.00011334371,0.000116864874,0.00013706161,0.000040963656,0.0001860962,0.000024581648,0.00019058383],"category_scores_gemma":[0.00014930175,0.000040826595,0.000008427309,0.00026961564,0.00017327468,0.000109096276,0.0003801289,0.000040176845,0.000032600452],"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":[0.00013646287,0.00003038498,0.00053039956,0.00018197601,0.000005963273,0.00000323262,0.00009219348,0.000002900676,0.99118143,0.000020143603,0.0069808476,0.00083406887],"study_design_scores_gemma":[0.0006905842,0.000078713994,0.9024972,0.0002266451,0.000026895139,0.0000059235085,0.00016376,0.0022424194,0.08945192,0.000108617154,0.0044154404,0.00009188471],"about_ca_topic_score_codex":0.000018645329,"about_ca_topic_score_gemma":0.00002590268,"teacher_disagreement_score":0.9019668,"about_ca_system_score_codex":0.00000642231,"about_ca_system_score_gemma":0.000016506197,"threshold_uncertainty_score":0.20867594},"labels":[],"label_agreement":null},{"id":"W4389482760","doi":"10.1038/s41597-023-02759-y","title":"Canadian Covid-19 pandemic public health mitigation measures at the province level","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"COVID-19 epidemiological studies","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"York University","funders":"","keywords":"Pandemic; Public health; Coronavirus disease 2019 (COVID-19); Range (aeronautics); Implementation; Scale (ratio); Geography; 2019-20 coronavirus outbreak; Work (physics); Psychological intervention; Data science; Computer science; Medicine; Cartography; Outbreak; Nursing; Engineering; Virology","score_opus":0.7576683147232829,"score_gpt":0.49529430542492964,"score_spread":0.26237400929835325,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389482760","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":[0.09811772,0.0016220205,0.0127715515,0.8235721,0.0038859418,0.0039148647,0.05284262,0.0017958884,0.0014773047],"genre_scores_gemma":[0.7892917,0.00046514848,0.0044985246,0.04974455,0.00062561966,0.00039033827,0.029225038,0.0001297589,0.12562934],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99655545,0.0005569394,0.00044939143,0.00096236885,0.0006270478,0.0008487795],"domain_scores_gemma":[0.99400705,0.002618463,0.00021324935,0.0023982134,0.00009823027,0.0006648228],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.018809132,0.00016167083,0.00026235482,0.00018195633,0.0024961827,0.000278141,0.0019451547,0.00006821631,0.0002091092],"category_scores_gemma":[0.04947897,0.000102940496,0.00004836691,0.0010140382,0.00060132856,0.00023486915,0.0016379846,0.00018672914,0.00084304163],"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":[0.0000015255765,0.0000116771835,0.011200016,0.00007470307,0.000018792247,0.000004326884,0.00042535714,0.000008324723,0.000023898358,0.0035799292,0.97586215,0.008789287],"study_design_scores_gemma":[0.00012180869,0.000009923486,0.009457475,0.000013708958,0.000009054866,0.000004666386,0.0003729588,0.0009991056,0.0000026955922,0.03986231,0.94900596,0.00014034749],"about_ca_topic_score_codex":0.06606721,"about_ca_topic_score_gemma":0.88223004,"teacher_disagreement_score":0.8161628,"about_ca_system_score_codex":0.0018130017,"about_ca_system_score_gemma":0.003840484,"threshold_uncertainty_score":0.9999349},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":true,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":true,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":true,"confidence":"high"}],"label_agreement":"agree"},{"id":"W4389628449","doi":"10.1038/s41597-023-02805-9","title":"Deep learning downscaled high-resolution daily near surface meteorological datasets over East Asia","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"Climate variability and models","field":"Environmental Science","cited_by":42,"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 Education and Child Care","funders":"National Key Research and Development Program of China","keywords":"Shortwave radiation; Downscaling; Environmental science; Shortwave; Coupled model intercomparison project; Climatology; Precipitation; Wind speed; Climate change; East Asia; Relative humidity; Climate model; Meteorology; Humidity; Longwave; Atmospheric sciences; Geography; Radiation; Radiative transfer; Geology; China","score_opus":0.04810556784158295,"score_gpt":0.2743167713279881,"score_spread":0.22621120348640514,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389628449","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":[0.9893256,0.000021868518,0.0014979162,0.0006242258,0.00095448724,0.00028774716,0.005933187,0.00030420395,0.0010507961],"genre_scores_gemma":[0.95115626,0.000012366517,0.0033735165,0.00006216879,0.000038293783,0.0000062503013,0.04355288,0.000016603868,0.0017816781],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99681693,0.00022852911,0.0002845636,0.0013633365,0.0007040832,0.0006025483],"domain_scores_gemma":[0.997478,0.00012176895,0.00008546946,0.0021196287,0.000008621599,0.00018649857],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.003507919,0.00016722568,0.00017901484,0.000031128373,0.0008980112,0.0004682073,0.0015859182,0.000105834624,0.006390186],"category_scores_gemma":[0.0004717393,0.00014540012,0.00003977865,0.001042301,0.0008616379,0.0009929108,0.0039689215,0.00025563576,0.009243751],"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":[0.00009772124,0.00034794433,0.023344642,0.00003318848,0.00003323282,0.000053103264,0.0006455496,0.28879988,0.05845836,0.00050130475,0.62022084,0.007464233],"study_design_scores_gemma":[0.00032797325,0.00003109409,0.04679056,0.0000072731177,0.000027523341,0.000004135121,0.00009942895,0.7284052,0.00006871447,0.0006774679,0.22332563,0.00023504964],"about_ca_topic_score_codex":0.0004702199,"about_ca_topic_score_gemma":0.00046843925,"teacher_disagreement_score":0.43960527,"about_ca_system_score_codex":0.00008641746,"about_ca_system_score_gemma":0.000018936908,"threshold_uncertainty_score":0.9945181},"labels":[],"label_agreement":null},{"id":"W4389894118","doi":"10.1038/s41597-023-02745-4","title":"Global inventory of species categorized by known underwater sonifery","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"Marine animal studies overview","field":"Environmental Science","cited_by":31,"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; University of Victoria; Simon Fraser University","funders":"Vlaamse regering; Fonds Wetenschappelijk Onderzoek; Vlaams Instituut voor de Zee; LifeWatch – Niclas Öberg Foundation; Richard Lounsbery Foundation","keywords":"Biodiversity; Invertebrate; Underwater; Marine life; Ecology; Subspecies; Marine biodiversity; Environmental resource management; Biology; Marine species; Geography; Environmental science","score_opus":0.06800758008801995,"score_gpt":0.2791835503204395,"score_spread":0.21117597023241957,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389894118","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":[0.80335176,0.0006210748,0.00018775514,0.0017758958,0.0033230577,0.0006792303,0.008736389,0.00034583375,0.18097901],"genre_scores_gemma":[0.89236313,0.0002251103,0.00042088647,0.00022554628,0.00008727656,0.000015074675,0.0046759374,0.000024643257,0.1019624],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.998055,0.000045398847,0.00024895658,0.00068713777,0.00059046707,0.00037306908],"domain_scores_gemma":[0.99850875,0.000021216249,0.00008112367,0.0012894702,0.000010718318,0.00008873916],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00095273246,0.00012374036,0.000174129,0.000028167582,0.00021085134,0.000095398085,0.0015381929,0.000032549422,0.0053798975],"category_scores_gemma":[0.00008397963,0.000104425344,0.00004006519,0.0011136744,0.00073672767,0.00036607202,0.0056535983,0.000047947302,0.0039132396],"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":[0.0000050466147,0.00004161562,0.035011284,0.000019949013,0.000012603319,0.0000033542874,0.000051116273,0.000008010398,0.0016937947,0.00012640143,0.96007556,0.0029512476],"study_design_scores_gemma":[0.00016901865,0.000016492906,0.059133016,0.000007780419,0.000015018227,0.0000010475867,0.0001414813,0.0006069801,0.00035649366,0.000950574,0.9384613,0.00014081433],"about_ca_topic_score_codex":0.0017600905,"about_ca_topic_score_gemma":0.0036629515,"teacher_disagreement_score":0.08901136,"about_ca_system_score_codex":0.000117526986,"about_ca_system_score_gemma":0.000021621632,"threshold_uncertainty_score":0.99686235},"labels":[],"label_agreement":null},{"id":"W4390007241","doi":"10.1038/s41597-023-02812-w","title":"A dataset of formulation compositions for self-emulsifying drug delivery systems","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"Analytical Chemistry and Chromatography","field":"Chemistry","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Structural Genomics Consortium; University of Toronto","funders":"Canada First Research Excellence Fund; University of Toronto; Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Drug delivery; Drug; Computer science; Chemistry; Pharmacology; Medicine; Organic chemistry","score_opus":0.05732461586954081,"score_gpt":0.3054587720831645,"score_spread":0.24813415621362372,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390007241","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":[0.53157693,0.00018916314,0.0016192461,0.000090993104,0.00049736665,0.00025007213,0.4639228,0.00034757893,0.0015058353],"genre_scores_gemma":[0.71209055,0.0000046251666,0.0005742821,0.000003964624,0.00005508187,0.000012557545,0.28681365,0.000008337545,0.00043696855],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99875754,0.0000068260933,0.0003035726,0.0004425143,0.00025379678,0.0002357477],"domain_scores_gemma":[0.9982229,0.00014324974,0.00011403618,0.0013560255,0.000084234685,0.000079545774],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004941788,0.00008876052,0.00013576064,0.00007730561,0.00029020166,0.00013890507,0.0007867293,0.000046342022,0.00008604659],"category_scores_gemma":[0.000041759915,0.000087113476,0.00005217635,0.0005015216,0.000091733564,0.00030935614,0.0003594054,0.00005810574,0.000045583784],"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":[0.000019847745,0.0001674092,0.00074866007,0.0020765779,0.00013783667,0.000004709998,0.000134731,0.00014209849,0.1965793,0.00064179243,0.7991682,0.000178778],"study_design_scores_gemma":[0.0008233197,0.0000073782144,0.0001016826,0.00031200895,0.0003080036,0.000009253529,0.0012145853,0.55063295,0.106535144,0.0007159189,0.33894396,0.00039576803],"about_ca_topic_score_codex":0.000017931476,"about_ca_topic_score_gemma":0.0000048884926,"teacher_disagreement_score":0.55049086,"about_ca_system_score_codex":0.000015611316,"about_ca_system_score_gemma":0.00004189017,"threshold_uncertainty_score":0.35523847},"labels":[],"label_agreement":null},{"id":"W4390545674","doi":"10.1038/s41597-023-02784-x","title":"Global fine-resolution data on springtail abundance and community structure","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Collembola Taxonomy and Ecology Studies","field":"Agricultural and Biological Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Forest Service; Western University; Université du Québec à Montréal; Université du Québec en Outaouais; Natural Resources Canada; Université Laval","funders":"Natural Resources Canada; Natural Sciences and Engineering Research Council of Canada; Deutsches Zentrum für integrative Biodiversitätsforschung Halle-Jena-Leipzig; Agencia Estatal de Investigación; Higher Education Commision, Pakistan; Universität Leipzig; Russian Science Foundation; Agence Nationale pour la Gestion des Déchets Radioactifs; Office of Energy Research and Development; Latvijas Zinātnes Padome; Centre National de la Recherche Scientifique; Canadian Forest Service; Japan Society for the Promotion of Science; Vedecká Grantová Agentúra MŠVVaŠ SR a SAV; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Ministério da Ciência, Tecnologia e Inovação; Russian Foundation for Basic Research; National Natural Science Foundation of China; Deutsche Forschungsgemeinschaft; National Research Foundation; Austrian Science Fund; Ministerio de Ciencia e Innovación; Eesti Teadusfondi; Massey University; Royal Society Te Apārangi; Nanyang Technological University; Biodiversa+; U.S. Forest Service; Government of Alberta; Department of Science and Technology, Ministry of Science and Technology, India; Carl Tryggers Stiftelse för Vetenskaplig Forskning; Alberta Environment and Parks; Marsden Fund; Bundesministerium für Bildung und Forschung; Ural Branch, Russian Academy of Sciences; Agentúra na Podporu Výskumu a Vývoja; Alexander von Humboldt-Stiftung; Klima- und Energiefonds; St. John's University; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Russian Academy of Sciences; Agence Nationale de la Recherche; Ministry of Natural Resources; Conseil Régional, Île-de-France; American Association of University Women; National Science Foundation","keywords":"Springtail; Abundance (ecology); Ecology; Geography; Database; Woodland; Habitat; Biology","score_opus":0.09691553568951436,"score_gpt":0.2835592502376938,"score_spread":0.18664371454817943,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390545674","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":[0.9642621,0.0011605982,0.000006404894,0.002276488,0.0014651418,0.00013384214,0.029627822,0.00008991067,0.0009776733],"genre_scores_gemma":[0.9938635,0.000016556389,0.00011830927,0.000065478736,0.00013871488,0.0000018301871,0.005242172,3.445317e-7,0.00055307854],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99882066,0.00010554542,0.00011479832,0.00061484793,0.00013286839,0.00021128292],"domain_scores_gemma":[0.9990259,0.00020045451,0.000025012601,0.00067770167,0.000019642908,0.000051307044],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0009137816,0.00009824487,0.00010108516,0.000009562543,0.0014036084,0.0004805488,0.0015501993,0.000050252158,0.00017426409],"category_scores_gemma":[0.00020748598,0.000039641356,0.00001205951,0.00044560587,0.00033600815,0.00041182456,0.0030003435,0.00020502783,0.00005052214],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029041388,0.00010990449,0.01019269,0.0000419162,0.000054118434,0.0000100441275,0.00009781679,0.0000073015576,0.001935109,0.0012540204,0.6748717,0.31139636],"study_design_scores_gemma":[0.000045992292,0.00005790597,0.19619873,0.00003449762,0.000017152499,0.000006961675,0.0002806063,0.002514462,0.000017310756,0.0011253121,0.7995801,0.000120946344],"about_ca_topic_score_codex":0.0004413328,"about_ca_topic_score_gemma":0.05740264,"teacher_disagreement_score":0.31127542,"about_ca_system_score_codex":0.000023638053,"about_ca_system_score_gemma":0.000016149079,"threshold_uncertainty_score":0.9998964},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W4390583429","doi":"10.1038/s41597-023-02866-w","title":"FISHGLOB_data: an integrated dataset of fish biodiversity sampled with scientific bottom-trawl surveys","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Marine and fisheries research","field":"Environmental Science","cited_by":29,"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; Fisheries and Oceans Canada","funders":"National Marine Fisheries Service; Fondation pour la Recherche sur la Biodiversite; European Commission; Cooperative Institute for the North Atlantic Region; National Oceanic and Atmospheric Administration; Villum Fonden","keywords":"Geography; Biodiversity; Context (archaeology); Fishery; Abundance (ecology); Marine protected area; Fishing; Marine ecosystem; Environmental resource management; Ecosystem; Oceanography; Ecology; Environmental science; Habitat; Biology; Geology","score_opus":0.0694030363355991,"score_gpt":0.29348390382763295,"score_spread":0.22408086749203385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390583429","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18680555,0.000019477351,0.002140538,0.0006611577,0.001878418,0.0006340049,0.8028813,0.00019031494,0.004789264],"genre_scores_gemma":[0.06455668,0.000015627378,0.004348597,0.00011569273,0.000048639977,0.000009424773,0.9214148,0.000026323121,0.009464216],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99581474,0.00031104992,0.00031521122,0.0018010812,0.0012118489,0.0005460547],"domain_scores_gemma":[0.99540657,0.00009162347,0.00006807404,0.0041020084,0.000055194403,0.000276528],"candidate_categories":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0063300054,0.00020201546,0.00021239585,0.00020164595,0.00058015814,0.002008911,0.0038696856,0.00006843051,0.019368922],"category_scores_gemma":[0.00021155895,0.00015514503,0.000029310837,0.0027530428,0.0029263822,0.0032933704,0.004113053,0.0003119538,0.00090772397],"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":[0.00002374899,0.00014336218,0.02711297,0.000043135056,0.000023926505,0.000043784,0.00010760024,0.0000037091602,0.00086948194,0.000010785586,0.944848,0.026769476],"study_design_scores_gemma":[0.00017158735,0.000079707796,0.011242264,0.00001634275,0.000026597469,0.00000946726,0.00017185495,0.0038466249,0.00032967035,0.000030498086,0.9838543,0.00022109046],"about_ca_topic_score_codex":0.0059443186,"about_ca_topic_score_gemma":0.015610378,"teacher_disagreement_score":0.122248866,"about_ca_system_score_codex":0.000085941916,"about_ca_system_score_gemma":0.00019982766,"threshold_uncertainty_score":0.9998702},"labels":[],"label_agreement":null},{"id":"W4390672990","doi":"10.1038/s41597-023-02824-6","title":"A database of mapped global fishing activity 1950–2017","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Marine and fisheries research","field":"Environmental Science","cited_by":42,"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":"","keywords":"Fishing; Tonnage; Marine conservation; Computer science; Range (aeronautics); Database; Identification (biology); Automatic Identification System; Environmental science; Fishery; Environmental resource management; Oceanography; Data mining; Ecology; Engineering; Geology","score_opus":0.08081955254806912,"score_gpt":0.33877929819720226,"score_spread":0.25795974564913315,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390672990","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34210974,0.000090764304,0.0028442116,0.001977956,0.002772688,0.00048711017,0.025215663,0.00016277109,0.6243391],"genre_scores_gemma":[0.9777979,0.000021140037,0.0018214615,0.00003120312,0.00007017395,0.0000066153834,0.0026457987,0.000010927388,0.017594757],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981203,0.000044616623,0.000128777,0.0007625868,0.00065171934,0.0002920177],"domain_scores_gemma":[0.99774635,0.000046523797,0.000027256803,0.0020647696,0.0000070186293,0.00010806341],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0013495192,0.00008311921,0.00009386506,0.00003234448,0.00015804409,0.00047821717,0.00173964,0.0000298093,0.009429246],"category_scores_gemma":[0.00023130764,0.00007149556,0.000027180446,0.000787507,0.00056883885,0.0014531305,0.005321427,0.0001310961,0.0008080054],"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":[0.000017444874,0.00008270747,0.01580198,0.000098157805,0.000012639393,0.000058026882,0.000091320966,0.000002409612,0.010190989,0.00015062497,0.80426586,0.16922785],"study_design_scores_gemma":[0.00008350237,0.000015652784,0.009950654,0.000024406254,0.0000106055795,0.000010264318,0.000051985364,0.019900916,0.0006620907,0.0003142517,0.96884644,0.00012925586],"about_ca_topic_score_codex":0.0013364287,"about_ca_topic_score_gemma":0.0014190997,"teacher_disagreement_score":0.6356882,"about_ca_system_score_codex":0.00006777435,"about_ca_system_score_gemma":0.000058490114,"threshold_uncertainty_score":0.99996996},"labels":[],"label_agreement":null},{"id":"W4390673179","doi":"10.1038/s41597-023-02796-7","title":"Measuring the presence and incidence of cholera in Hindustan: New data from primary sources for the colonial era","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Vibrio bacteria research studies","field":"Biochemistry, Genetics and Molecular Biology","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":"Center for Interuniversity Research and Analysis on Organizations","funders":"Agence Nationale de la Recherche","keywords":"Harmonization; Cholera; Data collection; Colonialism; Geography; Incidence (geometry); Data science; Regional science; Computer science; Statistics; Mathematics; Biology","score_opus":0.10411196234134029,"score_gpt":0.33325454022855044,"score_spread":0.22914257788721015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390673179","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":[0.96175694,0.021581538,0.00081777107,0.0054493034,0.000812527,0.00062847143,0.008897549,0.000008502303,0.00004742254],"genre_scores_gemma":[0.99370515,0.0005065153,0.00076260895,0.00005719079,0.00038627902,0.000020739137,0.003308537,0.000012316903,0.0012406441],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987278,0.000051012146,0.00014599576,0.0006495639,0.00024366325,0.00018195638],"domain_scores_gemma":[0.9976587,0.00022945463,0.00003417909,0.0020045103,0.000039937222,0.00003317725],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015830551,0.00007553347,0.000087208304,0.000027074566,0.00018314598,0.0003765714,0.002346168,0.0000365433,0.0000096772965],"category_scores_gemma":[0.0010173733,0.00004410196,0.000012733176,0.00016181686,0.0004872302,0.000039144958,0.0048613464,0.000113197886,0.000002034895],"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":[0.00011288204,0.0000232974,0.0013936854,0.00008637032,0.00011132293,0.0000033556544,0.0010167058,0.000016070495,0.75513005,0.000020275069,0.22292441,0.019161543],"study_design_scores_gemma":[0.00050862646,0.00006429121,0.044082366,0.00022177248,0.000057784087,0.0000048970996,0.00045476187,0.010001666,0.049655095,0.00025244904,0.89449996,0.00019634757],"about_ca_topic_score_codex":0.00048067133,"about_ca_topic_score_gemma":0.0015380007,"teacher_disagreement_score":0.705475,"about_ca_system_score_codex":0.000008284528,"about_ca_system_score_gemma":0.0003513221,"threshold_uncertainty_score":0.60593206},"labels":[],"label_agreement":null},{"id":"W4390740994","doi":"10.1038/s41597-023-02855-z","title":"An ensemble of bias-adjusted CMIP6 climate simulations based on a high-resolution North American reanalysis","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Climate variability and models","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":"Ouranos","funders":"Environment and Climate Change Canada","keywords":"Quantile; Climate model; Coupled model intercomparison project; Climatology; Climate change; Computer science; Environmental science; Multivariate statistics; Precipitation; Econometrics; Statistics; Meteorology; Mathematics; Machine learning; Geography","score_opus":0.07410897584124482,"score_gpt":0.30279054523550447,"score_spread":0.22868156939425965,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390740994","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":[0.9820929,0.00000586618,0.005842308,0.00024681515,0.00032053443,0.00018922011,0.010631609,0.00010594681,0.00056475983],"genre_scores_gemma":[0.9882349,0.000003833461,0.002713285,0.000046212037,0.000017282606,0.0000038419157,0.008857919,0.000011698892,0.00011104907],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99769765,0.00014323024,0.000314635,0.00096972496,0.00057568686,0.0002990999],"domain_scores_gemma":[0.9970594,0.00018976787,0.000094650255,0.0025201342,0.000019189012,0.000116862895],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0013626205,0.0001230254,0.00017440057,0.00018779129,0.0002719817,0.00021558197,0.0007690153,0.000026906098,0.0009234043],"category_scores_gemma":[0.00015982057,0.00010766217,0.000052044736,0.0021215954,0.0005661803,0.0005692722,0.00037532015,0.000092569324,0.00030288546],"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":[0.00004227146,0.00051905814,0.02201171,0.00005540474,0.000022153778,0.000005244542,0.00025671054,0.93947124,0.015606643,0.0002837919,0.006500234,0.015225513],"study_design_scores_gemma":[0.00008078831,0.000060110047,0.025944881,0.000019836794,0.00008013337,2.7838047e-7,0.000035767556,0.9696714,0.00028259848,0.00011496363,0.0035888928,0.0001202945],"about_ca_topic_score_codex":0.0019759655,"about_ca_topic_score_gemma":0.0102873165,"teacher_disagreement_score":0.030200189,"about_ca_system_score_codex":0.00010318176,"about_ca_system_score_gemma":0.000038141086,"threshold_uncertainty_score":0.99998987},"labels":[],"label_agreement":null},{"id":"W4390782248","doi":"10.1038/s41597-023-02902-9","title":"Enhanced U-Pb detrital zircon, Lu-Hf zircon, δ18O zircon, and Sm-Nd whole rock global databases","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Geological and Geochemical Analysis","field":"Earth and Planetary Sciences","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Natural Environment Research Council; Sight Research UK","keywords":"Zircon; Database; Geology; Geochemistry; Computer science","score_opus":0.03478651441941164,"score_gpt":0.25313005438975256,"score_spread":0.21834353997034092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390782248","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":[0.74886906,0.034224264,0.05187521,0.0051093088,0.0073902947,0.00075971097,0.12685558,0.0007810289,0.024135549],"genre_scores_gemma":[0.96121776,0.00008203389,0.0053826333,0.00026446983,0.0002665803,0.0000020812581,0.028708303,0.000005011239,0.0040711476],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9964185,0.00008181111,0.00042889372,0.0017764604,0.00060909725,0.00068524777],"domain_scores_gemma":[0.99782556,0.0002256579,0.000070448106,0.0013638741,0.00008917304,0.00042527207],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0009021178,0.00029148202,0.0003385167,0.0001291464,0.00045551607,0.0011091168,0.0013630558,0.00008992751,0.01063451],"category_scores_gemma":[0.00042657307,0.00021447273,0.00009146097,0.0014821896,0.00050445675,0.0012458072,0.0005530864,0.00023437612,0.0033279285],"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":[0.00009174385,0.0002361943,0.03724093,0.00039373775,0.00038717597,0.0003567267,0.00023329235,0.00034331155,0.23831034,0.0010241808,0.48384425,0.23753811],"study_design_scores_gemma":[0.0006933396,0.00016844265,0.0252454,0.00021229577,0.00042544978,0.00013110516,0.00087659474,0.029106194,0.060300704,0.020277815,0.86114943,0.0014132336],"about_ca_topic_score_codex":0.001485103,"about_ca_topic_score_gemma":0.008902309,"teacher_disagreement_score":0.37730518,"about_ca_system_score_codex":0.0000078072435,"about_ca_system_score_gemma":0.00011113783,"threshold_uncertainty_score":0.9999278},"labels":[],"label_agreement":null},{"id":"W4390815635","doi":"10.1038/s41597-023-02616-y","title":"Plant macrofossil data for 48-0 ka in the USGS North American Packrat Midden Database, version 5.0","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Geology and Paleoclimatology Research","field":"Earth and Planetary Sciences","cited_by":2,"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":"U.S. Geological Survey; National Oceanic and Atmospheric Administration; U.S. Department of the Interior","keywords":"Macrofossil; Midden; Archaeology; Radiocarbon dating; Geography; Physical geography; Holocene","score_opus":0.08891087125449199,"score_gpt":0.3149814654156725,"score_spread":0.22607059416118053,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390815635","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":[0.6874479,0.0034393775,0.00013474953,0.004889893,0.0041875243,0.0008069917,0.29685354,0.000077218974,0.0021628097],"genre_scores_gemma":[0.6984375,0.000108439504,0.00067958626,0.00017477054,0.00012731981,0.000003490688,0.2994301,0.000003530744,0.0010352733],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974195,0.0002391092,0.00021027582,0.0011437979,0.00040456024,0.00058276864],"domain_scores_gemma":[0.99577326,0.000851042,0.00004103019,0.0032154142,0.000024690333,0.0000945529],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0037321646,0.00013262901,0.00016603174,0.00020180331,0.0005333136,0.0004930928,0.0047959504,0.00004235059,0.0006766851],"category_scores_gemma":[0.00030824586,0.000083853214,0.0000228779,0.0011107231,0.0009926728,0.00083612255,0.0005310511,0.00032685444,0.0020233975],"study_design_candidate":"not_applicable","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":[0.000036930243,0.000013200067,0.5833697,0.000042540418,0.000011658552,0.000087963956,0.0001166665,0.0000051758934,0.0000026173623,0.00002499709,0.41240233,0.0038862599],"study_design_scores_gemma":[0.00018957484,0.00004752665,0.25636262,0.00003331091,0.000033055112,0.00007820879,0.0006555912,0.06479464,0.0000063964158,0.00011735262,0.6775104,0.00017133489],"about_ca_topic_score_codex":0.0009646834,"about_ca_topic_score_gemma":0.13318332,"teacher_disagreement_score":0.32700706,"about_ca_system_score_codex":0.0000014070266,"about_ca_system_score_gemma":0.00022242682,"threshold_uncertainty_score":0.99875367},"labels":[],"label_agreement":null},{"id":"W4390817161","doi":"10.1038/s41597-023-02689-9","title":"The Pelagic Species Trait Database, an open data resource to support trait-based ocean research","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Marine and fisheries research","field":"Environmental Science","cited_by":9,"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 Alberta","funders":"Government of Canada; Marine Environmental Observation Prediction and Response Network","keywords":"Pelagic zone; Trait; Food web; Ecology; Biology; Habitat; Predation; Apex predator; Population; Invertebrate; Computer science","score_opus":0.2983281128450758,"score_gpt":0.41775939093007336,"score_spread":0.11943127808499754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390817161","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":[0.015351371,0.00008334284,0.00068973744,0.023876827,0.0018425903,0.0033091882,0.11089238,0.00028402187,0.84367055],"genre_scores_gemma":[0.094960235,0.00003196608,0.006271542,0.000989598,0.00076550385,0.00007937108,0.20054471,0.00018048605,0.6961766],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.992746,0.000490769,0.0003860187,0.0027294613,0.002509832,0.0011379273],"domain_scores_gemma":[0.9864356,0.00045778556,0.000029692716,0.012486014,0.000038297738,0.0005525932],"candidate_categories":["sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.021170313,0.00020158009,0.00017400441,0.0001856641,0.0019423502,0.009136424,0.031770524,0.00005669388,0.029096266],"category_scores_gemma":[0.0009803518,0.00014196066,0.000023812343,0.0028145155,0.002154493,0.0032849305,0.04894717,0.0006484291,0.0022895355],"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":[0.000045162855,0.000093067196,0.00028843596,0.000018950677,0.000007979878,0.00006483953,0.00022210414,0.000006194464,0.001159422,0.000366085,0.909635,0.08809274],"study_design_scores_gemma":[0.00012393505,0.00014648159,0.001489544,0.00001584734,0.000008335947,0.000007333971,0.0009942851,0.012136628,0.0001036312,0.00018200703,0.98458904,0.00020292783],"about_ca_topic_score_codex":0.002008597,"about_ca_topic_score_gemma":0.009129399,"teacher_disagreement_score":0.14749397,"about_ca_system_score_codex":0.00013176027,"about_ca_system_score_gemma":0.00041365906,"threshold_uncertainty_score":0.999357},"labels":[{"model":"gemma","categories":["open_science"],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["open_science"],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W4391138155","doi":"10.1038/s41597-024-02930-z","title":"Urban water and electricity demand data for understanding climate change impacts on the water-energy nexus","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Water-Energy-Food Nexus Studies","field":"Environmental Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"United Nations University Institute for Water, Environment, and Health","funders":"Purdue Climate Change Research Center, Purdue University; National Socio-Environmental Synthesis Center; Purdue University; National Science Foundation","keywords":"Nexus (standard); Electricity; Water-energy nexus; Climate change; Electricity demand; Natural resource economics; Environmental science; Consumption (sociology); Electricity system; Electricity generation; Economics; Ecology; Computer science; Engineering","score_opus":0.15815554639560336,"score_gpt":0.28292850732302405,"score_spread":0.12477296092742068,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391138155","genre_codex":"dataset","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":[0.14642312,0.015488024,0.09606993,0.23359816,0.047009367,0.011967161,0.2469704,0.0040301317,0.19844371],"genre_scores_gemma":[0.9928444,0.000045544082,0.00005971254,0.00041503034,0.00018384884,0.000038478916,0.004915492,0.000033646174,0.0014638149],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99676603,0.000086284,0.00023048834,0.0014973052,0.00046232398,0.00095759064],"domain_scores_gemma":[0.99714524,0.00016312601,0.00003082046,0.0024989026,0.000006857731,0.00015502906],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0023876757,0.00024872142,0.00018109946,0.00010273938,0.0013722143,0.00097156456,0.0019123532,0.0000564839,0.00019227387],"category_scores_gemma":[0.000071958704,0.000110417175,0.000029330267,0.00030082202,0.0005617224,0.0012982626,0.0059054014,0.000109239336,0.00013666488],"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":[0.000081388454,0.00011435994,0.0001217413,0.00013119794,0.00012801251,0.00004273789,0.0027070874,0.000014641382,0.02839245,0.051253267,0.912343,0.0046700924],"study_design_scores_gemma":[0.00047870452,0.0002423878,0.00018464947,0.0001493387,0.00019340622,0.00003747715,0.00077866495,0.06553635,0.041280475,0.16248114,0.72785646,0.0007809311],"about_ca_topic_score_codex":0.00030617812,"about_ca_topic_score_gemma":0.0013874165,"teacher_disagreement_score":0.8464213,"about_ca_system_score_codex":0.00018941642,"about_ca_system_score_gemma":0.000010356398,"threshold_uncertainty_score":0.9999279},"labels":[],"label_agreement":null},{"id":"W4391229880","doi":"10.1038/s41597-024-02948-3","title":"Global seasonal prediction of fire danger","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Fire effects on ecosystems","field":"Environmental Science","cited_by":16,"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":"Joint Research Centre; European Commission","keywords":"Environmental science; Climatology; Geography; Geology","score_opus":0.019007074035609677,"score_gpt":0.24858858525618993,"score_spread":0.22958151122058026,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391229880","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":[0.9350762,0.00075481506,0.00091876544,0.0003161405,0.010868147,0.00041102452,0.033018384,0.00025572174,0.018380834],"genre_scores_gemma":[0.99514496,0.0000017293294,0.0003350622,0.000010258272,0.000072701645,0.000004499994,0.0014824672,0.000006578743,0.0029417395],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99844563,0.00004035988,0.00015300539,0.00063684344,0.0005430691,0.00018109195],"domain_scores_gemma":[0.9987292,0.000029801073,0.000029227424,0.0011353872,0.0000055946475,0.00007077124],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0010371318,0.00007572825,0.00007695766,0.000017410504,0.00008614465,0.0001783088,0.00084083586,0.00003639751,0.0019087179],"category_scores_gemma":[0.00007466502,0.000064689295,0.00002645104,0.00070229394,0.00027208854,0.00067898433,0.00084158184,0.00004807399,0.002022525],"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":[0.0000029258767,0.000038798484,0.013729227,0.000064776534,0.000011873096,0.0000098964565,0.000074293464,0.00003632986,0.0031109396,0.000066636305,0.8824776,0.10037675],"study_design_scores_gemma":[0.000067414,0.000021963791,0.044561367,0.000082062434,0.000019428124,0.000017956942,0.000015374128,0.39428648,0.00022414702,0.00016674462,0.5604541,0.00008299269],"about_ca_topic_score_codex":0.00027224232,"about_ca_topic_score_gemma":0.00017474357,"teacher_disagreement_score":0.39425015,"about_ca_system_score_codex":0.00011617481,"about_ca_system_score_gemma":0.000025661857,"threshold_uncertainty_score":0.99900365},"labels":[],"label_agreement":null},{"id":"W4391308957","doi":"10.1038/s41597-023-02788-7","title":"Multidimensional well-being of US households at a fine spatial scale using fused household surveys","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Urban, Neighborhood, and Segregation Studies","field":"Social 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":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Institute of Child Health and Human Development; National Science Foundation; RTI International; Canadian Institute for Advanced Research; University of Pennsylvania; U.S. Environmental Protection Agency","keywords":"Microdata (statistics); Survey data collection; Limiting; Scale (ratio); American Community Survey; General Social Survey; Government (linguistics); Consumer Expenditure Survey; Data science; Geography; Business; Environmental economics; Computer science; Public economics; Economics; Environmental health; Statistics; Engineering; Cartography; Medicine","score_opus":0.10187748787511886,"score_gpt":0.3263173078517201,"score_spread":0.22443981997660123,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391308957","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":[0.98175687,0.0011133231,0.0026209196,0.00038187113,0.0062501943,0.0003252672,0.0027544089,0.00026396743,0.0045331805],"genre_scores_gemma":[0.9878407,0.000033702327,0.0010342681,0.000022578914,0.0003634196,0.000002084019,0.0006526661,0.000024338637,0.010026236],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99684364,0.0004036063,0.00038994863,0.0008490793,0.001075815,0.00043791835],"domain_scores_gemma":[0.99826366,0.00040320243,0.00010880081,0.0009397562,0.00014786095,0.00013670062],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0047508464,0.0001600975,0.00025203457,0.00018888744,0.0013970877,0.00033670166,0.0007606266,0.00008955328,0.00048680676],"category_scores_gemma":[0.00034477722,0.00014539623,0.00009992191,0.0010442653,0.0011022942,0.0006143965,0.0008992545,0.00012379626,0.000118411575],"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":[0.000100525525,0.0007139403,0.3322464,0.00046591804,0.0006975633,0.00014998479,0.06932683,0.0015582154,0.041516524,0.0062787603,0.5111859,0.03575944],"study_design_scores_gemma":[0.0011541608,0.00005861313,0.055904634,0.00051276403,0.00032296812,0.000008448251,0.002164537,0.068469234,0.005487263,0.0008369706,0.86403376,0.0010466755],"about_ca_topic_score_codex":0.008491988,"about_ca_topic_score_gemma":0.029123854,"teacher_disagreement_score":0.3528478,"about_ca_system_score_codex":0.00011656117,"about_ca_system_score_gemma":0.0003850487,"threshold_uncertainty_score":0.99990296},"labels":[],"label_agreement":null},{"id":"W4391351012","doi":"10.1038/s41597-024-02969-y","title":"TrackdAT, an acoustic telemetry metadata dataset to support aquatic animal tracking research","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Fish Ecology and Management Studies","field":"Environmental Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor; Dalhousie University","funders":"Great Lakes Fishery Commission","keywords":"Metadata; Computer science; Data science; Stakeholder; Telemetry; Key (lock); Ecology; Abiotic component; Data sharing; Citizen science; World Wide Web; Environmental resource management; Biology; Environmental science","score_opus":0.20699486369023426,"score_gpt":0.42036780401303503,"score_spread":0.21337294032280077,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391351012","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":[0.67988,0.0005190142,0.01338009,0.01600621,0.015466363,0.0054411157,0.23177198,0.0012443457,0.03629089],"genre_scores_gemma":[0.9439114,0.000011615603,0.0026733156,0.000575628,0.00013263717,0.00004273686,0.040504813,0.000031561252,0.012116304],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.995867,0.00019548374,0.00030918713,0.0018738513,0.00097655633,0.0007778978],"domain_scores_gemma":[0.99639106,0.0002457021,0.000027868708,0.003102455,0.000011713933,0.00022121858],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.008840811,0.00017292875,0.00017612921,0.00030020296,0.0009582193,0.0014069047,0.0034587989,0.00004436466,0.00695901],"category_scores_gemma":[0.00079248025,0.0001536843,0.000021478922,0.0017886445,0.00082336075,0.003097839,0.00658657,0.00034297133,0.011240891],"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":[0.000010678265,0.000118492986,0.0012524051,0.000036346537,0.00003240661,0.00011146013,0.0002144234,0.000036649984,0.0027185546,0.00010176317,0.98734677,0.008020068],"study_design_scores_gemma":[0.00010320951,0.00022705826,0.020466242,0.000024435643,0.00009817407,0.000011731128,0.00071579247,0.008439216,0.00020504202,0.0004145892,0.96901363,0.00028087304],"about_ca_topic_score_codex":0.00021309168,"about_ca_topic_score_gemma":0.014466712,"teacher_disagreement_score":0.26403138,"about_ca_system_score_codex":0.00010289011,"about_ca_system_score_gemma":0.00005289836,"threshold_uncertainty_score":0.99962974},"labels":[],"label_agreement":null},{"id":"W4391566575","doi":"10.1038/s41597-024-02981-2","title":"Preoperative CT and survival data for patients undergoing resection of colorectal liver metastases","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Hepatocellular Carcinoma Treatment and Prognosis","field":"Medicine","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"National Cancer Institute; National Institutes of Health; Memorial Sloan-Kettering Cancer Center; Division of Cancer Epidemiology and Genetics, National Cancer Institute; U.S. Department of Health and Human Services","keywords":"Medicine; Colorectal cancer; Resection; Radiology; Hepatectomy; Overall survival; Curative treatment; Internal medicine; Oncology; Cancer; Surgery; Disease","score_opus":0.15467646260189458,"score_gpt":0.32486564361019016,"score_spread":0.17018918100829558,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391566575","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":[0.9722969,0.0022995977,0.0002700999,0.000092090624,0.0010441634,0.0008624812,0.022878438,0.000034726207,0.0002215041],"genre_scores_gemma":[0.95296574,0.00006223402,0.0018224429,0.000003823229,0.0000411319,0.000013332084,0.044390142,0.0000117566915,0.0006893767],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987052,0.000059288548,0.00016827973,0.00068029336,0.0002455375,0.00014141847],"domain_scores_gemma":[0.9986033,0.00027238237,0.000032051532,0.00093130744,0.00009624745,0.00006470488],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008781427,0.00009298859,0.0001638126,0.00012022908,0.0001358108,0.00016701582,0.00025975486,0.000016392927,0.0000625896],"category_scores_gemma":[0.0004494179,0.000070919676,0.000026540174,0.0002694056,0.0001544201,0.00054613623,0.0005496009,0.000052386677,0.000011742736],"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":[0.00091129215,0.0015090132,0.70839924,0.0031061023,0.0014730694,0.00018028115,0.0010559228,5.232766e-7,0.003697648,0.0008537487,0.22912358,0.049689565],"study_design_scores_gemma":[0.011742613,0.009990584,0.088650405,0.0026355896,0.0071707354,0.00014758222,0.0019113788,0.474608,0.06650872,0.00054399663,0.33489487,0.0011955368],"about_ca_topic_score_codex":0.000055145778,"about_ca_topic_score_gemma":0.000278189,"teacher_disagreement_score":0.61974883,"about_ca_system_score_codex":0.000022197037,"about_ca_system_score_gemma":0.00017976947,"threshold_uncertainty_score":0.28920206},"labels":[],"label_agreement":null},{"id":"W4391606134","doi":"10.1038/s41597-024-03011-x","title":"Chromosome level genome assembly of the Etruscan shrew Suncus etruscus","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"National Institute of General Medical Sciences; Rockefeller University; National Science Foundation; National Institutes of Health; U.S. Department of Health and Human Services; Howard Hughes Medical Institute","keywords":"Biology; Genome; Sequence assembly; Genetics; Genomics; Gene; Chromosome; Reference genome; Genome project; Computational biology; Transcriptome","score_opus":0.05750344690567299,"score_gpt":0.28238233709022753,"score_spread":0.22487889018455454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391606134","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":[0.9772348,0.008973386,0.00011676787,0.00034751053,0.003146788,0.00019318785,0.008250528,0.0000066932153,0.0017303579],"genre_scores_gemma":[0.99369127,0.00012423725,0.0003229656,0.000044696095,0.00016588844,0.000005173146,0.00077190524,0.000017602,0.004856274],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986064,0.000036558613,0.00020589546,0.0006900316,0.00022267934,0.00023847443],"domain_scores_gemma":[0.99782,0.000013639194,0.000049729973,0.0020019237,0.000064731845,0.00004993568],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058705645,0.00012846848,0.00012066653,0.00004752995,0.00017854467,0.00014282577,0.0014665658,0.00006432138,0.000034721437],"category_scores_gemma":[0.000086183965,0.00008862238,0.00008093174,0.00031757096,0.00032657525,0.0000025537113,0.0017784239,0.00007412444,0.00003259042],"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":[0.0000033806766,0.000019286153,0.00019177613,0.00003693709,0.00007499555,0.0000012997997,0.000064834516,0.000009778535,0.9782449,0.00024122468,0.018737186,0.0023744171],"study_design_scores_gemma":[0.00015423572,0.000058684866,0.020733798,0.000033419496,0.000060059243,0.0000147509545,0.00008465885,0.00020510255,0.24284787,0.00031055827,0.73526126,0.00023559456],"about_ca_topic_score_codex":0.00003275411,"about_ca_topic_score_gemma":0.0001937211,"teacher_disagreement_score":0.735397,"about_ca_system_score_codex":0.000010483947,"about_ca_system_score_gemma":0.00022191799,"threshold_uncertainty_score":0.36139157},"labels":[],"label_agreement":null},{"id":"W4391670666","doi":"10.1038/s41597-024-03739-6","title":"MAPLES-DR: MESSIDOR Anatomical and Pathological Labels for Explainable Screening of Diabetic Retinopathy","year":2024,"lang":"en","type":"preprint","venue":"Scientific Data","topic":"Retinal Imaging and Analysis","field":"Medicine","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; Université de Montréal; Hôpital Maisonneuve-Rosemont; Polytechnique Montréal","funders":"Université de Montréal; Diabetes Action Research and Education Foundation","keywords":"Pathological; Diabetic retinopathy; Medicine; Ophthalmology; Pathology; Diabetes mellitus; Endocrinology","score_opus":0.10410165174014922,"score_gpt":0.3696656813168617,"score_spread":0.2655640295767125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391670666","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":[0.96553284,0.008557882,0.004056197,0.00550313,0.0015295976,0.0010723245,0.01275741,0.0001806347,0.00080995535],"genre_scores_gemma":[0.9412335,0.00010133689,0.034565683,0.00009134429,0.00024527937,0.0000602188,0.012971889,0.00005286486,0.010677889],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99688137,0.00008748622,0.00052806415,0.0016459498,0.00047097128,0.000386186],"domain_scores_gemma":[0.9970499,0.0001609927,0.00019160604,0.002199693,0.00020703401,0.00019077645],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029785638,0.00025540453,0.0007585915,0.00035999645,0.00014798014,0.00036118028,0.0007446274,0.00019210183,0.000073869734],"category_scores_gemma":[0.0010984994,0.00019490332,0.00017237123,0.00037836036,0.0006805839,0.00006834297,0.0043258984,0.0005826759,0.000016169972],"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":[0.0007186741,0.0010564013,0.019066583,0.025182404,0.0014532965,0.0017274526,0.0015533894,0.000054113756,0.07919959,0.0018991198,0.7371035,0.13098547],"study_design_scores_gemma":[0.0063867425,0.0010206169,0.01287054,0.025493693,0.017350648,0.0008056568,0.004647825,0.60347265,0.04550462,0.07304681,0.2058635,0.0035366926],"about_ca_topic_score_codex":0.00002733651,"about_ca_topic_score_gemma":0.0000024636838,"teacher_disagreement_score":0.6034185,"about_ca_system_score_codex":0.00002593046,"about_ca_system_score_gemma":0.00018803982,"threshold_uncertainty_score":0.7947927},"labels":[],"label_agreement":null},{"id":"W4391685687","doi":"10.1038/s41597-023-02872-y","title":"PLAS-20k: Extended Dataset of Protein-Ligand Affinities from MD Simulations for Machine Learning Applications","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":22,"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":"Science and Engineering Research Board; International Institute of Information Technology, Hyderabad; Indian Institute of Technology Delhi; Department of Science and Technology, Ministry of Science and Technology, India","keywords":"Binding affinities; Affinities; Drug discovery; Computer science; Docking (animal); Pipeline (software); Artificial intelligence; Machine learning; Computational biology; Chemistry; Stereochemistry; Biology; Biochemistry","score_opus":0.0871256239288214,"score_gpt":0.3650666403697066,"score_spread":0.2779410164408852,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391685687","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":[0.0016994178,0.0007953117,0.86507696,0.00024178562,0.0005509027,0.00057998556,0.1308662,0.00012311438,0.00006630524],"genre_scores_gemma":[0.24493253,0.000007718431,0.5464003,0.000034834608,0.00017713637,0.00015897714,0.20730545,0.000025899433,0.0009571573],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99799925,0.000098176744,0.00034981963,0.0009582756,0.00040128117,0.00019316752],"domain_scores_gemma":[0.996652,0.0012211335,0.00010339926,0.001853033,0.00010831586,0.00006210446],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011693473,0.000121301644,0.00014416983,0.00023403527,0.00035295237,0.0010109986,0.0023251714,0.00003081046,0.000037203474],"category_scores_gemma":[0.00034904116,0.000116008116,0.000038547016,0.0008245812,0.00017898431,0.001399134,0.0014398751,0.00012523189,0.000048695998],"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":[0.000044110675,0.00055303844,0.000064984415,0.00058971025,0.0002977633,0.000011004328,0.0021533973,0.13402922,0.039592188,0.3645521,0.16972929,0.28838316],"study_design_scores_gemma":[0.00009203297,0.000010630496,0.00002843073,0.000035395755,0.000014644715,9.673543e-7,0.000019702278,0.6709683,0.0020760794,0.031980094,0.29467908,0.00009466862],"about_ca_topic_score_codex":0.00004667524,"about_ca_topic_score_gemma":0.000063404914,"teacher_disagreement_score":0.536939,"about_ca_system_score_codex":0.000021955851,"about_ca_system_score_gemma":0.00030525652,"threshold_uncertainty_score":0.97490823},"labels":[],"label_agreement":null},{"id":"W4391743207","doi":"10.1038/s41597-023-02832-6","title":"The bii4africa dataset of faunal and floral population intactness estimates across Africa’s major land uses","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Ecology and Vegetation Dynamics Studies","field":"Environmental Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary; Vancouver Island University","funders":"Natural Environment Research Council; Sight Research UK","keywords":"Geography; Population; Ecology; Biology; Demography; Sociology","score_opus":0.03607999813467442,"score_gpt":0.3171929596664338,"score_spread":0.28111296153175935,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391743207","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":[0.9611395,0.0012549217,0.0007827937,0.00087581284,0.0018311184,0.00023403439,0.03340853,0.000054062108,0.00041923948],"genre_scores_gemma":[0.9931741,0.000018218927,0.0005467973,0.0000073629535,0.000011921777,0.000004906527,0.005735293,0.000004108424,0.000497341],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9990881,0.000027530172,0.00016348969,0.00037836746,0.00016802177,0.00017448499],"domain_scores_gemma":[0.9992051,0.00020264769,0.0000443927,0.0005115522,0.0000066008283,0.000029714318],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009110537,0.000068721674,0.00007538061,0.000021050875,0.00068367977,0.00027485308,0.00047143764,0.000024914227,0.00009070435],"category_scores_gemma":[0.0001466314,0.000044121705,0.00000934392,0.0002590207,0.000761937,0.0005113597,0.0012018437,0.000060772763,0.000096436415],"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":[0.000028534398,0.000078201534,0.7224111,0.00009592895,0.00008145288,0.000011051725,0.0021836741,0.00043094892,0.0008903288,0.0020044213,0.25628766,0.015496736],"study_design_scores_gemma":[0.00016692052,0.000029236862,0.7504468,0.000032212407,0.000060970404,0.000011378131,0.0005150521,0.13249062,0.000085500484,0.008255474,0.107715406,0.00019042633],"about_ca_topic_score_codex":0.00018973155,"about_ca_topic_score_gemma":0.0030861415,"teacher_disagreement_score":0.14857225,"about_ca_system_score_codex":0.000018716559,"about_ca_system_score_gemma":0.000006914829,"threshold_uncertainty_score":0.52583814},"labels":[],"label_agreement":null},{"id":"W4391778775","doi":"10.1038/s41597-024-02996-9","title":"U.S. cereal rye winter cover crop growth database","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Soil Carbon and Nitrogen Dynamics","field":"Agricultural and Biological Sciences","cited_by":14,"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":"Natural Resources Conservation Service; National Institute of Food and Agriculture; U.S. Department of Agriculture","keywords":"Cover crop; Secale; Biomass (ecology); Agronomy; Hardiness (plants); Environmental science; Crop; Hordeum vulgare; Biology; Poaceae; Cultivar","score_opus":0.042711798139851403,"score_gpt":0.2603312968689096,"score_spread":0.2176194987290582,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391778775","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":[0.96707106,0.0006440512,0.00002342092,0.001572846,0.0038665326,0.00014460048,0.019074919,0.00026998328,0.0073326156],"genre_scores_gemma":[0.9673904,0.000028688402,0.00013585927,0.0002891068,0.000460035,0.000004363579,0.021585781,0.0000020815662,0.01010367],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982866,0.000039670747,0.00015881698,0.00084583386,0.00035587966,0.0003132067],"domain_scores_gemma":[0.99927646,0.000087892535,0.000022214488,0.00042763798,0.00005228259,0.00013349645],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0007047476,0.0001238606,0.00009872808,0.000024517816,0.00021031496,0.0010173144,0.0012579308,0.00004919651,0.0021968451],"category_scores_gemma":[0.000086768196,0.00004569051,0.00005683776,0.0006687166,0.00020455803,0.0005809013,0.00094739813,0.00013528137,0.0018005004],"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":[0.00001834161,0.00008457226,0.0014833855,0.000031750093,0.000031571744,0.0000786517,0.000058362966,5.7892896e-7,0.07834373,0.0019148903,0.8831864,0.034767784],"study_design_scores_gemma":[0.00010063584,0.000049493687,0.007588446,0.000071035,0.000044415716,0.000037407317,0.000101422935,0.026186973,0.0024051557,0.0011369878,0.96190995,0.0003680964],"about_ca_topic_score_codex":0.0002830165,"about_ca_topic_score_gemma":0.000976624,"teacher_disagreement_score":0.07872355,"about_ca_system_score_codex":0.000022045237,"about_ca_system_score_gemma":0.000028326465,"threshold_uncertainty_score":0.9989767},"labels":[],"label_agreement":null},{"id":"W4391998772","doi":"10.1038/s41597-024-02980-3","title":"Plant trait and vegetation data along a 1314 m elevation gradient with fire history in Puna grasslands, Perú","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Ecology and Vegetation Dynamics Studies","field":"Environmental Science","cited_by":7,"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; Université de Montréal; University of British Columbia","funders":"Senter for Internasjonalisering av Utdanning; Universitetet i Bergen","keywords":"Ecosystem; Vegetation (pathology); Grassland; Biodiversity; Biomass (ecology); Ecology; Trait; Specific leaf area; Growing season; Environmental science; Plant functional type; Climate change; Geography; Threatened species; Biology; Agronomy; Botany","score_opus":0.03511588098095743,"score_gpt":0.24053489864654767,"score_spread":0.20541901766559023,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391998772","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":[0.9913451,0.0023381717,0.000613286,0.0008110824,0.0012912718,0.00034540295,0.001481771,0.0000720843,0.0017018203],"genre_scores_gemma":[0.99076855,0.00005526983,0.0006044191,0.00005280753,0.00001591969,0.000012391248,0.007392111,0.000007722286,0.0010907832],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99851984,0.00004229864,0.00017452946,0.00084387383,0.00023133068,0.00018812352],"domain_scores_gemma":[0.9990539,0.000072515126,0.000042769323,0.00078168657,0.000005848959,0.000043312666],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010598613,0.000098909855,0.00009450274,0.00008118894,0.00017830291,0.00009985983,0.0005492967,0.000036023892,0.00011379249],"category_scores_gemma":[0.00006363841,0.00008027707,0.000006519658,0.00027576752,0.00043145436,0.001011156,0.0006080129,0.00011677841,0.000077900004],"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":[0.00008133539,0.00039673885,0.47005665,0.0004400658,0.00013043632,0.00024526136,0.015294545,0.0010202368,0.0018341132,0.004274437,0.44610783,0.060118347],"study_design_scores_gemma":[0.00025578128,0.000037416416,0.48260406,0.00008275857,0.000037574086,0.000024384468,0.00023363039,0.43921188,0.0000051817647,0.0006368269,0.076688506,0.00018202145],"about_ca_topic_score_codex":0.00019617182,"about_ca_topic_score_gemma":0.024403438,"teacher_disagreement_score":0.43819165,"about_ca_system_score_codex":0.00015256584,"about_ca_system_score_gemma":0.000044497763,"threshold_uncertainty_score":0.99339867},"labels":[],"label_agreement":null},{"id":"W4392044107","doi":"10.1038/s41597-024-02967-0","title":"Nature’s contribution to poverty alleviation, human wellbeing and the SDGs","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Sustainable Development and Environmental Policy","field":"Environmental 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":"McGill University","funders":"Svenska Forskningsrådet Formas; Department of Biotechnology, Ministry of Science and Technology, India; Natural Environment Research Council; Research Councils UK; Sight Research UK","keywords":"Poverty; Natural resource economics; Political science; Development economics; Geography; Environmental planning; Economic growth; Economics","score_opus":0.009768203093206035,"score_gpt":0.2580561098142185,"score_spread":0.24828790672101247,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392044107","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":[0.9311084,0.0012267858,0.0015535511,0.03680231,0.0034344387,0.0017589349,0.0006247745,0.00026881817,0.023221988],"genre_scores_gemma":[0.9762137,0.00001368981,0.00019038786,0.001316316,0.00006643181,0.000014338727,0.00090574054,0.000009462223,0.021269957],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985801,0.000042239142,0.00014696913,0.00060607895,0.0003562104,0.00026841313],"domain_scores_gemma":[0.9991408,0.000048053542,0.000021172149,0.00069861446,0.000004019914,0.000087316716],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0015920356,0.00009906683,0.000077858764,0.000048363174,0.00062179996,0.0006019486,0.00066670065,0.000046744895,0.00086903846],"category_scores_gemma":[0.00013726355,0.00006560731,0.00001748238,0.0004265575,0.00041670905,0.0005943049,0.0016918852,0.00014016153,0.0009930688],"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":[0.000016622442,0.00002126599,0.0026629558,0.0000148455,0.000020002433,0.000009288114,0.00091372035,0.000041588934,0.004991608,0.021113316,0.96251863,0.007676171],"study_design_scores_gemma":[0.0002491458,0.0000056048552,0.030408818,0.000014946472,0.000015077556,0.000004540225,0.00012532384,0.0021329813,0.0003985753,0.0053908774,0.96112365,0.00013043641],"about_ca_topic_score_codex":0.00017972445,"about_ca_topic_score_gemma":0.00011539917,"teacher_disagreement_score":0.04510528,"about_ca_system_score_codex":0.0001529604,"about_ca_system_score_gemma":0.000013010093,"threshold_uncertainty_score":0.99978477},"labels":[],"label_agreement":null},{"id":"W4392107466","doi":"10.1038/s41597-024-03064-y","title":"A deep learning dataset for sample preparation artefacts detection in multispectral high-content microscopy","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Cell Image Analysis Techniques","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":"Artificial Intelligence in Medicine (Canada)","funders":"Universität Zürich; Sächsisches Staatsministerium für Wissenschaft und Kunst; Bundesministerium für Bildung und Forschung","keywords":"Multispectral image; Microscopy; Content (measure theory); Computer science; Artificial intelligence; Sample (material); Deep learning; Remote sensing; Chemistry; Chromatography; Geology; Optics; Mathematics; Physics","score_opus":0.03355106710513036,"score_gpt":0.33986287162740697,"score_spread":0.30631180452227663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392107466","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":[0.433997,0.0009895819,0.55605316,0.00006704883,0.0005041085,0.0007259657,0.007558057,0.00008112131,0.00002396929],"genre_scores_gemma":[0.80348456,0.000034984227,0.010071976,0.00001965247,0.0000829236,0.000042057807,0.18574858,0.000013578156,0.0005017067],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99869215,0.00003947935,0.00018268595,0.0007980417,0.00009667821,0.00019097634],"domain_scores_gemma":[0.99895835,0.000024019198,0.000038453953,0.0009079801,0.000037772723,0.00003342763],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007194109,0.00009155243,0.00008368935,0.00012034742,0.00010922787,0.00036681464,0.00036295186,0.000059387745,0.000017341563],"category_scores_gemma":[0.00035315478,0.00009099997,0.000033237564,0.00019829201,0.00006460857,0.000038171493,0.00025481655,0.000076482254,0.000017018643],"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":[0.00003118602,0.000027750808,0.00005043753,0.00002190762,0.000018253344,0.000001491831,0.000028191616,0.000044511373,0.9617622,0.0000048083343,0.026218906,0.011790338],"study_design_scores_gemma":[0.00012088688,0.00006662065,0.00011289518,0.000012431391,0.00002267881,0.0000025621966,0.00003048669,0.036297873,0.71847314,0.00006050952,0.24470305,0.00009684267],"about_ca_topic_score_codex":0.0002571927,"about_ca_topic_score_gemma":0.0052771973,"teacher_disagreement_score":0.54598117,"about_ca_system_score_codex":0.000025553943,"about_ca_system_score_gemma":0.000037337857,"threshold_uncertainty_score":0.37108713},"labels":[],"label_agreement":null},{"id":"W4392132169","doi":"10.1038/s41597-024-03080-y","title":"Band-by-band spectral radiative kernels based on the ERA5 reanalysis","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Climate variability and models","field":"Environmental Science","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":"McGill University","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Radiative transfer; Radiation; Spectral bands; Environmental science; Radiative flux; Kernel (algebra); Flux (metallurgy); Broadband; Atmosphere (unit); Remote sensing; Atmospheric sciences; Computational physics; Physics; Meteorology; Mathematics; Optics; Materials science; Geology","score_opus":0.043987350714291835,"score_gpt":0.27181954459097796,"score_spread":0.22783219387668613,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392132169","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":[0.7084823,0.00046532997,0.013830939,0.041090026,0.005444426,0.0017617631,0.041343976,0.00052810775,0.18705313],"genre_scores_gemma":[0.99197775,0.000007877385,0.00016242378,0.00036617575,0.000042586715,0.0000095210635,0.0016453878,0.000011248686,0.0057770316],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99781054,0.00011805847,0.00018256178,0.0010075005,0.00057625014,0.0003050837],"domain_scores_gemma":[0.9974493,0.00031811438,0.00003155407,0.0021009573,0.0000049339355,0.00009515542],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002574766,0.0001297565,0.00011344209,0.000052440642,0.00038592186,0.00070266076,0.0012298479,0.000037416234,0.012521945],"category_scores_gemma":[0.00017746443,0.00008172432,0.0000656179,0.00079045846,0.00058093556,0.0004090611,0.0002746462,0.00016404586,0.00213625],"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":[0.000012648514,0.00014352461,0.0004957818,0.000011475475,0.000027869764,0.000008293504,0.00044020836,0.0051966803,0.015634585,0.00045529782,0.9762646,0.0013090452],"study_design_scores_gemma":[0.00013568651,0.00003426917,0.00053022674,0.000033479395,0.00008516279,0.0000012676471,0.00008572619,0.6545231,0.009500863,0.0039598043,0.33088002,0.00023043205],"about_ca_topic_score_codex":0.00022286226,"about_ca_topic_score_gemma":0.00018334288,"teacher_disagreement_score":0.6493264,"about_ca_system_score_codex":0.00012108772,"about_ca_system_score_gemma":0.000036924215,"threshold_uncertainty_score":0.9986407},"labels":[],"label_agreement":null},{"id":"W4392231253","doi":"10.1038/s41597-024-03059-9","title":"GEOWEALTH-US: Spatial wealth inequality data for the United States, 1960–2020","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Spatial and Panel Data Analysis","field":"Economics, Econometrics and Finance","cited_by":14,"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":"Microdata (statistics); Inequality; Economic inequality; Survey data collection; Spatial inequality; Disadvantage; Distribution (mathematics); Geography; Imputation (statistics); Social inequality; Demographic economics; Economics; Development economics; Population; Census; Political science; Demography; Missing data; Sociology","score_opus":0.17710370419728813,"score_gpt":0.32480729677186704,"score_spread":0.1477035925745789,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392231253","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0056171636,0.007023609,0.20504104,0.01182128,0.008138172,0.00072302896,0.76107585,0.00015162626,0.00040820817],"genre_scores_gemma":[0.20392962,0.001762058,0.0014129583,0.0013949552,0.0011250871,0.00004269429,0.7861429,0.000053833046,0.004135926],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99696255,0.000044625933,0.00077798235,0.0016424749,0.00012527034,0.00044709284],"domain_scores_gemma":[0.9928432,0.00042396475,0.00022360102,0.006321619,0.000053240798,0.00013433438],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.006546669,0.00017231097,0.0003209891,0.00029398923,0.0005764054,0.0013415805,0.0044359374,0.00006406615,0.0010666484],"category_scores_gemma":[0.0007586179,0.00013697939,0.000066438,0.0015574084,0.00020751824,0.0008089176,0.0020028995,0.00020129049,0.001259115],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024515664,0.000072067596,0.002330338,0.000208827,0.0002185872,0.0000052615005,0.00029821592,0.00014787796,0.0000029702967,0.014003062,0.9661027,0.01658558],"study_design_scores_gemma":[0.00009816541,0.000011163533,0.0009792129,0.000011869798,0.000033849203,8.8184584e-7,0.000055390523,0.38998786,0.0000013613782,0.00337142,0.60533226,0.00011660224],"about_ca_topic_score_codex":0.031101353,"about_ca_topic_score_gemma":0.008361848,"teacher_disagreement_score":0.38983998,"about_ca_system_score_codex":0.000049372346,"about_ca_system_score_gemma":0.00014077453,"threshold_uncertainty_score":0.9998465},"labels":[],"label_agreement":null},{"id":"W4392864726","doi":"10.1038/s41597-024-03109-2","title":"HYADES - A Global Archive of Annual Maxima Daily Precipitation","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Climate variability and models","field":"Environmental 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":"Global Institute for Water Security; University of Saskatchewan; University of Calgary","funders":"Grantová Agentura České Republiky","keywords":"Maxima; Precipitation; Climatology; Environmental science; Climate change; Global warming; Series (stratigraphy); Physical geography; Meteorology; Geography; Geology; History; Oceanography","score_opus":0.03728824735855933,"score_gpt":0.29464886289976727,"score_spread":0.2573606155412079,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392864726","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":[0.8592364,0.00021480359,0.013351686,0.00080832414,0.0029539776,0.00050057843,0.08672285,0.00016640539,0.036044963],"genre_scores_gemma":[0.98749375,0.0000063601965,0.0077179703,0.000024143435,0.000030109379,0.000005872015,0.0032379427,0.0000065376025,0.0014773104],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99861777,0.00004255317,0.00017885618,0.0006377253,0.0003466546,0.00017644055],"domain_scores_gemma":[0.99887985,0.00006114896,0.000029068393,0.000963354,0.0000073241827,0.000059271002],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009998846,0.00007009375,0.00007511689,0.000027825123,0.00009096386,0.00016054623,0.0007752177,0.000025590733,0.0012269329],"category_scores_gemma":[0.00011581829,0.000061027786,0.000026292439,0.00044054046,0.00055472343,0.0008147715,0.0011030602,0.000051363008,0.0007213137],"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":[0.000052558305,0.00042493505,0.008286995,0.00024719076,0.000043472297,0.000016432776,0.0061219423,0.0019362363,0.029220516,0.01312147,0.8512234,0.08930486],"study_design_scores_gemma":[0.0003341202,0.00011442854,0.041942656,0.00016643867,0.00009236976,0.000022322734,0.0010635714,0.23969233,0.0009598486,0.14754894,0.5676166,0.00044640966],"about_ca_topic_score_codex":0.00025191653,"about_ca_topic_score_gemma":0.0003785784,"teacher_disagreement_score":0.28360683,"about_ca_system_score_codex":0.00005481074,"about_ca_system_score_gemma":0.00003481786,"threshold_uncertainty_score":0.99968606},"labels":[],"label_agreement":null},{"id":"W4393007704","doi":"10.1038/s41597-024-03139-w","title":"The Arctic Plant Aboveground Biomass Synthesis Dataset","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Climate change and permafrost","field":"Earth and Planetary Sciences","cited_by":14,"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 Alberta; Université Laval; Queen's University; Alberta Biodiversity Monitoring Institute; Nova Scotia Community College; Université du Québec à Trois-Rivières; Carleton University","funders":"Biological and Environmental Research; Division of Environmental Biology; Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Office of Science; Societas pro Fauna et Flora Fennica; Nordenskiöld-samfundet; Academy of Finland; Queen's University; U.S. Department of Energy; European Commission; Office of Polar Programs; Polar Knowledge Canada; Nuclear Safety and Security Commission; Université Laval; ArcticNet; Natural Resources Canada; National Aeronautics and Space Administration; Vetenskapsrådet; National Science Foundation","keywords":"Biomass (ecology); Environmental science; The arctic; Arctic; Ecology; Oceanography; Biology; Geology","score_opus":0.10829667691575451,"score_gpt":0.28661073285618044,"score_spread":0.17831405594042593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393007704","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013703611,0.0061401427,0.000011073686,0.00185164,0.006425419,0.0001261069,0.9704541,0.00006171043,0.0012261734],"genre_scores_gemma":[0.2459763,0.0004044351,0.000048876973,0.00013815225,0.00041226915,0.0000023637162,0.75118536,0.0000067231335,0.0018255021],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99840015,0.00005610876,0.00016781414,0.0006407596,0.00036563876,0.0003695486],"domain_scores_gemma":[0.9973566,0.00079885713,0.00002572898,0.0016969506,0.000013810658,0.000108046865],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0016806545,0.000111123096,0.00008403745,0.00007959252,0.00078999944,0.0028076796,0.001654126,0.000031970034,0.0069207447],"category_scores_gemma":[0.00013998832,0.00006387025,0.0000243723,0.0004694791,0.00035845063,0.0006363504,0.00017684035,0.000102253936,0.0056496337],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008822705,0.000006454162,0.0045047663,0.000065082386,0.000022788978,0.00006802045,0.00009731178,0.0000011017506,0.00016135642,0.00007492093,0.96797067,0.027018683],"study_design_scores_gemma":[0.000020578487,0.0000067498395,0.00783627,0.00004850833,0.00002677346,0.00004149763,0.00018949715,0.013606012,0.00005719983,0.0002840636,0.9777707,0.000112138885],"about_ca_topic_score_codex":0.004287571,"about_ca_topic_score_gemma":0.057090133,"teacher_disagreement_score":0.23227268,"about_ca_system_score_codex":0.000004364639,"about_ca_system_score_gemma":0.00007121907,"threshold_uncertainty_score":0.9982275},"labels":[],"label_agreement":null},{"id":"W4393054394","doi":"10.1038/s41597-024-03116-3","title":"A comprehensive historical and geolocalized database of mining activities in Canada","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Mining and Resource Management","field":"Engineering","cited_by":9,"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":"Lunds Universitet","keywords":"Database; Geographic coordinate system; Computer science; Matching (statistics); Principal (computer security); Credibility; Standardization; Hierarchy; Geography; Selection (genetic algorithm); Data mining; Information retrieval; Cartography; Statistics; Political science; Mathematics","score_opus":0.035226128438713304,"score_gpt":0.228593163905945,"score_spread":0.1933670354672317,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393054394","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":[0.98791397,0.0066620167,0.00059392286,0.00006714479,0.002077713,0.00007828966,0.0009830679,0.000060945702,0.0015629219],"genre_scores_gemma":[0.9980999,0.000029208815,0.0005278924,0.0000058337823,0.000015854452,0.000002299898,0.0002972791,0.000007903271,0.0010138175],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993631,0.000012585485,0.000119101955,0.00023419737,0.00014783084,0.00012317693],"domain_scores_gemma":[0.9994258,0.00007400042,0.000007778423,0.00045380119,0.0000048707184,0.000033746695],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017006851,0.000057756133,0.00010057188,0.00011798677,0.00002490513,0.000048015445,0.00022390485,0.0000101342,0.000025576715],"category_scores_gemma":[0.000016192938,0.00005281252,0.000005518372,0.00020774732,0.000046055626,0.00008374683,0.0002952504,0.00006154532,0.0000013806724],"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":[0.000007795558,0.000015091834,0.0005657723,0.0017101392,0.000068019304,0.00020902263,0.002255056,0.0044508614,0.0028200948,0.000118071475,0.94792813,0.039851923],"study_design_scores_gemma":[0.00010319937,0.0000026852983,0.00020668388,0.00016159419,0.000010240172,0.0000030485485,0.0015565881,0.39874005,0.00015908544,0.00000241703,0.59897614,0.0000782771],"about_ca_topic_score_codex":0.1690956,"about_ca_topic_score_gemma":0.20710361,"teacher_disagreement_score":0.3942892,"about_ca_system_score_codex":0.00023569596,"about_ca_system_score_gemma":0.00013287488,"threshold_uncertainty_score":0.83643746},"labels":[],"label_agreement":null},{"id":"W4393258334","doi":"10.1038/s41597-024-03142-1","title":"Genome assembly of a symbiotic balantidia (Balantidium ctenopharyngodoni) in fish hindgut","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Genomics and Phylogenetic Studies","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":"Structural Genomics Consortium","funders":"National Key Research and Development Program of China; Earmarked Fund for China Agriculture Research System; China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Hindgut; Biology; Genome; Gene; Comparative genomics; Synteny; Genetics; Genomics; Evolutionary biology; Botany; Midgut","score_opus":0.024093684600011166,"score_gpt":0.2647571905508476,"score_spread":0.24066350595083646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393258334","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":[0.98939,0.004330097,0.000047766316,0.0002152172,0.0013244463,0.00016946312,0.0035022744,0.0000067714313,0.0010139657],"genre_scores_gemma":[0.99513453,0.00038445208,0.00027220973,0.00003636137,0.000107253574,0.0000043305654,0.002629473,0.000018720664,0.001412647],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99839777,0.000038379145,0.00028067562,0.00081847305,0.00016951999,0.00029517707],"domain_scores_gemma":[0.99855375,0.000018188806,0.00004584151,0.0012748948,0.000050116614,0.00005718169],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00071116636,0.0001419642,0.0001778877,0.00012644354,0.00006497873,0.00013623651,0.00091072853,0.000077043056,0.000023350483],"category_scores_gemma":[0.00007197319,0.00013240878,0.000053217864,0.00032909002,0.00017837013,0.000004104189,0.0009817308,0.000077671655,0.00003580512],"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":[0.000010035481,0.0000468343,0.0019820759,0.00007752826,0.000057696892,0.000013114815,0.000060457864,0.000013128156,0.9823308,0.00006376838,0.014612024,0.00073256274],"study_design_scores_gemma":[0.00066799676,0.00018945131,0.16831316,0.00015753094,0.00009034756,0.000044321503,0.00018168446,0.0013214034,0.27453798,0.00018702273,0.5536665,0.000642621],"about_ca_topic_score_codex":0.000041237025,"about_ca_topic_score_gemma":0.00019826378,"teacher_disagreement_score":0.70779276,"about_ca_system_score_codex":0.00000976312,"about_ca_system_score_gemma":0.00016791972,"threshold_uncertainty_score":0.53994733},"labels":[],"label_agreement":null},{"id":"W4394569876","doi":"10.1038/s41597-024-03197-0","title":"A large normative connectome for exploring the tractographic correlates of focal brain interventions","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Krembil Foundation; University of Toronto; University Health Network","funders":"National Institute of Neurological Disorders and Stroke; National Institute of Mental Health; Deutsche Forschungsgemeinschaft; National Institutes of Health; Government of Canada; Canadian Institutes of Health Research; EU Joint Programme – Neurodegenerative Disease Research; New Venture Fund; Deutsches Zentrum für Luft- und Raumfahrt; Foundation for the National Institutes of Health","keywords":"Connectome; Connectomics; Human Connectome Project; Diffusion MRI; Neuroimaging; Computer science; White matter; Context (archaeology); Resting state fMRI; Neuroscience; Psychology; Artificial intelligence; Functional connectivity; Medicine; Magnetic resonance imaging; Biology; Radiology","score_opus":0.2653553452847806,"score_gpt":0.3686404338187473,"score_spread":0.10328508853396667,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394569876","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":[0.7760283,0.0025977017,0.08091582,0.043210678,0.032662425,0.0028163109,0.059775636,0.00066927256,0.001323886],"genre_scores_gemma":[0.99835545,0.000010322629,0.00007447696,0.00020191059,0.00006130548,0.00013651462,0.00021890788,0.00001361115,0.00092747377],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99823767,0.0001271402,0.00028617497,0.0007474613,0.00033060153,0.00027097407],"domain_scores_gemma":[0.9866779,0.012198316,0.00007265023,0.00094086543,0.00007349946,0.000036795318],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0023574799,0.00011437053,0.0001456849,0.00026742887,0.00064072,0.0003371217,0.0009935793,0.000021366968,0.0000646598],"category_scores_gemma":[0.015619191,0.00008009124,0.00017341158,0.0012281215,0.00058763975,0.0010962893,0.0007396588,0.00017389182,0.000065574655],"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":[0.000094004616,0.0005886845,0.00041138617,0.0010829533,0.00021836863,0.000014933956,0.010455639,0.00005975727,0.05998914,0.22424346,0.6907845,0.012057123],"study_design_scores_gemma":[0.0011299412,0.0004333086,0.0045294426,0.0013691919,0.00022576381,0.00006037538,0.008188095,0.080136344,0.04090926,0.04119401,0.8211858,0.00063846726],"about_ca_topic_score_codex":0.0000054061256,"about_ca_topic_score_gemma":0.0001532695,"teacher_disagreement_score":0.22232722,"about_ca_system_score_codex":0.00001807554,"about_ca_system_score_gemma":0.00005997677,"threshold_uncertainty_score":0.9926727},"labels":[],"label_agreement":null},{"id":"W4394570919","doi":"10.1038/s41597-024-03141-2","title":"A monthly gridded burned area database of national wildland fire data","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Fire effects on ecosystems","field":"Environmental Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Natural Resources Canada; Canadian Forest Service","funders":"Fondo de Financiamiento de Centros de Investigación en Áreas Prioritarias; Agencia Estatal de Investigación; Fundação para a Ciência e a Tecnologia; Natural Resources Canada; Horizon 2020 Framework Programme; New South Wales Government; Ministerio de Educación, Cultura y Deporte; National Fisheries Development Board; Ministerio de Ciencia, Innovación y Universidades; Fundação Carlos Chagas Filho de Amparo à Pesquisa do Estado do Rio de Janeiro; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Ministério da Ciência, Tecnologia e Ensino Superior; European Regional Development Fund; European Commission; Agencia Nacional de Investigación y Desarrollo; European Space Agency","keywords":"Database; Government (linguistics); Resource (disambiguation); Data source; Grid cell; Metadata; Grid; Geography; Environmental science; Computer science; Environmental resource management; Meteorology; World Wide Web","score_opus":0.05093371852271682,"score_gpt":0.2793830591394934,"score_spread":0.22844934061677657,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394570919","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":[0.6341733,0.0025411546,0.0007210318,0.0011848646,0.009835955,0.0013870675,0.335767,0.00038863035,0.014001002],"genre_scores_gemma":[0.9364832,0.00001113765,0.0011838771,0.000043280146,0.00011470243,0.000010289778,0.059917066,0.00002297285,0.0022134553],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966791,0.00007644743,0.0003294291,0.0014362291,0.001190462,0.00028833465],"domain_scores_gemma":[0.9953749,0.00018619461,0.000060005586,0.0042395005,0.000018403776,0.00012098562],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0032294816,0.00015119555,0.0001650961,0.0000815402,0.00016650134,0.00037905242,0.0037813797,0.000045326648,0.0018839277],"category_scores_gemma":[0.00056031824,0.00012745167,0.000024927198,0.0008669425,0.0004121243,0.002233116,0.0047379956,0.00013074595,0.0017082534],"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":[0.000008185171,0.00008214441,0.00092800456,0.0000997784,0.000023409511,0.000028388631,0.0001063843,0.00013396719,0.009914585,0.000026527789,0.98406655,0.0045820726],"study_design_scores_gemma":[0.00014849707,0.000013906812,0.0010052274,0.00015714252,0.000019912712,0.0000115089315,0.000027211829,0.6331924,0.00031181655,0.00009463758,0.36486128,0.00015645736],"about_ca_topic_score_codex":0.000749721,"about_ca_topic_score_gemma":0.00087242806,"teacher_disagreement_score":0.6330584,"about_ca_system_score_codex":0.0000826027,"about_ca_system_score_gemma":0.000104157014,"threshold_uncertainty_score":0.99906904},"labels":[],"label_agreement":null},{"id":"W4394728517","doi":"10.1038/s41597-024-03165-8","title":"High-resolution freshwater dissolved calcium and pH data layers for Canada and the United States","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Marine and coastal ecosystems","field":"Earth and Planetary Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Fisheries and Oceans Canada","funders":"Fisheries and Oceans Canada; Crown-Indigenous Relations and Northern Affairs Canada; Government of Canada; Ministry of Natural Resources","keywords":"Calcium; Oceanography; Environmental science; Resolution (logic); Environmental chemistry; Chemistry; Mineralogy; Geology; Computer science","score_opus":0.036334851093883944,"score_gpt":0.23434452646199344,"score_spread":0.19800967536810948,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394728517","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":[0.5385611,0.004429561,0.0019507101,0.009000024,0.008380236,0.0011534308,0.43592888,0.000107458305,0.0004885785],"genre_scores_gemma":[0.80062073,0.00006189915,0.0002482547,0.0001716538,0.00012923818,0.0000022124093,0.19514172,0.000004330001,0.0036199375],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99882245,0.00005054617,0.00014532373,0.0005526194,0.00020440845,0.00022462315],"domain_scores_gemma":[0.99866915,0.00023612946,0.000025092086,0.0009596647,0.000023333125,0.00008664151],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012319185,0.00008598572,0.000098639146,0.000055228284,0.00034555118,0.0008567894,0.000749747,0.000018832165,0.000212151],"category_scores_gemma":[0.00006997892,0.00004898574,0.0000067448123,0.00023959515,0.00022855008,0.0004256878,0.00037276768,0.00006410968,0.000009026961],"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":[0.00006907795,0.00000381538,0.0027276368,0.00015818163,0.00004898868,0.000010352045,0.00015470714,0.00020484468,0.000017593773,0.00034756406,0.9761011,0.020156164],"study_design_scores_gemma":[0.00014191405,0.00000593151,0.0007493649,0.000012148812,0.000018872723,0.000003520906,0.00015520802,0.4804808,0.000006431698,0.00027246695,0.51809895,0.00005438107],"about_ca_topic_score_codex":0.9034412,"about_ca_topic_score_gemma":0.990955,"teacher_disagreement_score":0.48027593,"about_ca_system_score_codex":0.0000029057992,"about_ca_system_score_gemma":0.00014162608,"threshold_uncertainty_score":0.826204},"labels":[],"label_agreement":null},{"id":"W4394891764","doi":"10.1038/s41597-024-03235-x","title":"Towards Gender Harmony Dataset: Gender Beliefs and Gender Stereotypes in 62 Countries","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Gender Roles and Identity Studies","field":"Social 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":"University of Guelph","funders":"","keywords":"Femininity; Harmony (color); Masculinity; Perception; Psychology; Social psychology; Qualitative property; Gender studies; Sociology","score_opus":0.1683779190793405,"score_gpt":0.38049659109328043,"score_spread":0.21211867201393994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394891764","genre_codex":"review","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":[0.1861076,0.28689608,0.004266154,0.08156057,0.06024196,0.0055702883,0.2700175,0.001898901,0.10344094],"genre_scores_gemma":[0.9820451,0.002929472,0.00061171665,0.0005771582,0.00056670397,0.00002043019,0.00622367,0.0000350726,0.0069906493],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99689084,0.00014457016,0.00030411745,0.0011764716,0.00087528856,0.0006087122],"domain_scores_gemma":[0.9986029,0.000047761987,0.000043149692,0.0010728439,0.000079526515,0.00015381706],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0030294568,0.0001893488,0.00020975889,0.00028597948,0.0010241127,0.0025796867,0.0011932496,0.00008949775,0.0003594904],"category_scores_gemma":[0.00017503917,0.00017251167,0.00003185383,0.00069491577,0.00061052875,0.0014915568,0.0015473174,0.00019646472,0.00042785183],"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":[0.000005002137,0.000041987158,0.003658854,0.00020892546,0.000081362625,0.000037877548,0.027915122,0.000001298633,0.00004096737,0.010143317,0.9550216,0.002843696],"study_design_scores_gemma":[0.00015676446,0.0000057051766,0.015567189,0.000028111634,0.000051487208,0.000003398673,0.014615569,0.00020425525,0.000012514726,0.008063165,0.9610331,0.00025873064],"about_ca_topic_score_codex":0.002085749,"about_ca_topic_score_gemma":0.009983684,"teacher_disagreement_score":0.79593754,"about_ca_system_score_codex":0.000083148436,"about_ca_system_score_gemma":0.0004458736,"threshold_uncertainty_score":0.9984557},"labels":[],"label_agreement":null},{"id":"W4394987905","doi":"10.1038/s41597-024-03238-8","title":"Chromosome-level genome assembly of marine diatom Skeletonema tropicum","year":2024,"lang":"en","type":"article","venue":"Scientific Data","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":"Simon Fraser University","funders":"Chinese Academy of Sciences; Institute of Oceanology, Chinese Academy of Sciences; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Genome; Biology; Gene; Polyploid; Genetics; Evolutionary biology; Diatom; Computational biology; Ecology","score_opus":0.038496672889657385,"score_gpt":0.2769623112537986,"score_spread":0.23846563836414122,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394987905","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":[0.98389333,0.00535292,0.00056999165,0.00019372281,0.0017091712,0.00016181624,0.0061446736,0.000008807522,0.0019655873],"genre_scores_gemma":[0.98851913,0.00026846118,0.0015734768,0.000027739648,0.0002781401,0.0000067970973,0.0038842964,0.000019412475,0.005422543],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99864167,0.000022148935,0.00022088485,0.00071651355,0.00016689631,0.0002318884],"domain_scores_gemma":[0.998372,0.000011779679,0.000043650958,0.001446462,0.00006555855,0.000060506285],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037080498,0.00012714928,0.0001427145,0.00006765596,0.000094797,0.00011504944,0.00083542493,0.000058880203,0.00006779102],"category_scores_gemma":[0.000053491563,0.000112011956,0.00005864664,0.00020613635,0.00019715763,0.000002707565,0.0017084171,0.00005107868,0.000052287774],"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":[0.000005868999,0.000035535682,0.00038795106,0.00006800941,0.000101985876,0.0000043337213,0.000038345897,0.0000072541407,0.9715944,0.00021999955,0.021749299,0.005787047],"study_design_scores_gemma":[0.00021051285,0.00010408187,0.018562537,0.00001821902,0.000053244443,0.00001287308,0.000054021162,0.0003108215,0.13002272,0.0002438881,0.8501569,0.00025018994],"about_ca_topic_score_codex":0.000028129441,"about_ca_topic_score_gemma":0.00009039487,"teacher_disagreement_score":0.8415716,"about_ca_system_score_codex":0.0000075582734,"about_ca_system_score_gemma":0.00013570135,"threshold_uncertainty_score":0.45677152},"labels":[],"label_agreement":null},{"id":"W4395038839","doi":"10.1038/s41597-024-03190-7","title":"RASMI: Global ranges of building material intensities differentiated by region, structure, and function","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Environmental Impact and Sustainability","field":"Environmental Science","cited_by":55,"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":"HORIZON EUROPE Framework Programme; International Institute for Applied Systems Analysis; Israel Science Foundation; Ministry of Economy, Trade and Industry; Canada Research Chairs; European Commission","keywords":"Demolition; Resource (disambiguation); Metric (unit); Environmental science; Function (biology); Computer science; Environmental resource management; Civil engineering; Engineering; Operations management","score_opus":0.014555602065107615,"score_gpt":0.24681710996722409,"score_spread":0.23226150790211647,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4395038839","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":[0.99366015,0.00025821352,0.0008372546,0.000105188046,0.0011937462,0.0001291021,0.0036404897,0.000042705065,0.0001331686],"genre_scores_gemma":[0.99784076,0.000011005982,0.00015761655,0.00001933507,0.000020291474,0.0000010932187,0.0013294873,0.0000064219957,0.0006140141],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9987663,0.00004678576,0.0001674795,0.0005583061,0.0002600625,0.00020105191],"domain_scores_gemma":[0.9992559,0.000014713071,0.000036652484,0.00061611756,0.000005215849,0.00007138467],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029233706,0.00011429251,0.00011579555,0.000024600105,0.00013502162,0.00028603157,0.00033467374,0.000047027654,0.000903465],"category_scores_gemma":[0.000043163836,0.0000919134,0.000018960249,0.00020273143,0.00088277634,0.00065297924,0.0009433261,0.00005573932,0.0000139394715],"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":[0.00019575616,0.00011901114,0.09482626,0.0002909756,0.00007914161,0.00001755782,0.0006152638,0.00001970983,0.43494856,0.00052397617,0.41368195,0.054681834],"study_design_scores_gemma":[0.0010100473,0.00027577174,0.68742895,0.00019366978,0.00034675084,0.00011392966,0.0022735277,0.012114868,0.12053693,0.037908744,0.13674326,0.0010535474],"about_ca_topic_score_codex":0.0003000745,"about_ca_topic_score_gemma":0.000044037843,"teacher_disagreement_score":0.59260267,"about_ca_system_score_codex":0.0001145846,"about_ca_system_score_gemma":0.000008778176,"threshold_uncertainty_score":0.9892309},"labels":[],"label_agreement":null},{"id":"W4395081664","doi":"10.1038/s41597-024-03265-5","title":"Author Correction: Neurocognitive aging data release with behavioral, structural and multi-echo functional MRI measures","year":2024,"lang":"en","type":"erratum","venue":"Scientific Data","topic":"Brain Tumor Detection and Classification","field":"Neuroscience","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; McGill University; Douglas Mental Health University Institute; McGill Genome Centre; University of Toronto; Toronto Metropolitan University; Montreal Neurological Institute and Hospital","funders":"","keywords":"Neurocognitive; Echo (communications protocol); Neuroscience; Psychology; Computer science; Cognition; Computer security","score_opus":0.21425257817395657,"score_gpt":0.35676817750834694,"score_spread":0.14251559933439037,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4395081664","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0027896792,0.0025167502,0.017598117,0.0067955437,0.82707363,0.003962414,0.12835276,0.0027897595,0.008121339],"genre_scores_gemma":[0.045544386,0.00010580896,0.00067725376,0.00045385107,0.0022511655,0.000079500904,0.06030064,0.0001942316,0.89039314],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9932775,0.00029793906,0.00043473634,0.004177907,0.0013441042,0.00046782973],"domain_scores_gemma":[0.99488807,0.0001405925,0.0003245108,0.004148613,0.00022520972,0.00027302347],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00094880996,0.00048094813,0.00031458368,0.0005071761,0.0013599904,0.0027542769,0.0022155463,0.00023031939,0.00028053593],"category_scores_gemma":[0.0011159721,0.00040703552,0.000043525306,0.0013266217,0.0011909577,0.0016155392,0.0021395143,0.0017852412,0.000277649],"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":[0.000041717478,0.000056536683,0.000011709174,0.000068374815,0.00001316414,0.00007311456,0.000118894786,0.0000033715403,0.0026494598,0.000019354498,0.97511655,0.021827739],"study_design_scores_gemma":[0.0003624477,0.0000671946,0.0007997547,0.00029738457,0.00029163933,0.00063962396,0.0004755722,0.09633051,0.0011364936,0.000046356483,0.89894474,0.0006082712],"about_ca_topic_score_codex":0.00007062959,"about_ca_topic_score_gemma":0.0008042845,"teacher_disagreement_score":0.8822718,"about_ca_system_score_codex":0.000089171226,"about_ca_system_score_gemma":0.00071563973,"threshold_uncertainty_score":0.9999401},"labels":[],"label_agreement":null},{"id":"W4395081723","doi":"10.1038/s41597-024-03230-2","title":"HiMIC-Monthly: A 1 km high-resolution atmospheric moisture index collection over China, 2003–2020","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Climate variability and models","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":"Public Health Ontario; University of Toronto","funders":"Natural Science Foundation of Guangdong Province; National Natural Science Foundation of China","keywords":"Environmental science; Land cover; Water content; Moisture; Climatology; Atmospheric sciences; Scale (ratio); Meteorology; Geography; Land use; Cartography; Geology","score_opus":0.015646973276605015,"score_gpt":0.24264317704420568,"score_spread":0.22699620376760066,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4395081723","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":[0.93270105,0.000858164,0.012022773,0.003242,0.01868025,0.0015342332,0.010597123,0.0007990444,0.019565355],"genre_scores_gemma":[0.9734378,0.00003130694,0.002792981,0.00011409209,0.00015065666,0.00002778911,0.0045291656,0.000028347778,0.018887851],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99745935,0.00007150099,0.00024896284,0.0012735778,0.00056653126,0.00038005953],"domain_scores_gemma":[0.998232,0.000028016544,0.00004880768,0.0015516382,0.000014006017,0.000125506],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0011204875,0.0001714745,0.000139844,0.00002092511,0.00049013126,0.0005824033,0.0008644698,0.00011548037,0.0058231535],"category_scores_gemma":[0.00014953977,0.00015365663,0.00003831969,0.002295986,0.000355181,0.001107287,0.0012435865,0.0002291379,0.0013147293],"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":[0.000023363402,0.00013247582,0.002443865,0.00003776244,0.000016754657,0.000013092844,0.00039229103,0.009043393,0.0030755592,0.0003022489,0.9814904,0.003028849],"study_design_scores_gemma":[0.00014371645,0.000020526448,0.039679397,0.000027021915,0.00002885114,0.000005299251,0.000025886908,0.5990917,0.00003994455,0.0017252548,0.35903054,0.00018182046],"about_ca_topic_score_codex":0.003145853,"about_ca_topic_score_gemma":0.0028546008,"teacher_disagreement_score":0.62245977,"about_ca_system_score_codex":0.0003672561,"about_ca_system_score_gemma":0.00008177288,"threshold_uncertainty_score":0.99946284},"labels":[],"label_agreement":null},{"id":"W4395112800","doi":"10.1038/s41597-024-03275-3","title":"A new commercial boundary dataset for metropolitan areas in the USA and Canada, built from open data","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Human Mobility and Location-Based Analysis","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"University of Toronto","keywords":"Metropolitan area; Boundary (topology); Geography; Regional science; Cluster analysis; Data collection; Data science; Segmentation; Economic geography; Cartography; Computer science; Statistics","score_opus":0.16116477062218248,"score_gpt":0.41821989254241393,"score_spread":0.25705512192023144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4395112800","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019807573,0.0015736591,0.0029340533,0.032036744,0.0020397669,0.001239804,0.93851286,0.000021753896,0.001833754],"genre_scores_gemma":[0.48390505,0.000026748652,0.0011272738,0.0011901805,0.00063348096,0.000022689148,0.51042473,0.000010822678,0.0026590526],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977898,0.00027983083,0.00022056425,0.00092716195,0.0005109115,0.0002717313],"domain_scores_gemma":[0.99602544,0.00069884193,0.00003669285,0.0030743184,0.000031361862,0.00013336493],"candidate_categories":["sts","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.005894681,0.00008598957,0.00014161355,0.00008114128,0.0013215567,0.004202702,0.0074726576,0.000034630626,0.0008108633],"category_scores_gemma":[0.0008856926,0.00006705217,0.000012988846,0.0006386616,0.000561861,0.001192918,0.0019195857,0.00012330391,0.000022886012],"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":[0.000004941337,0.000020114057,0.0012405055,0.000008473719,0.000021944235,0.0000037973327,0.0011059573,3.5329217e-7,0.000002016558,0.0029520395,0.97333443,0.021305429],"study_design_scores_gemma":[0.00009730473,0.0000037693735,0.0032509898,0.000020572641,0.00007003261,1.6415196e-7,0.0058494043,0.0018429479,0.0000011491793,0.0036219829,0.9851487,0.00009295443],"about_ca_topic_score_codex":0.9967331,"about_ca_topic_score_gemma":0.99990445,"teacher_disagreement_score":0.46409747,"about_ca_system_score_codex":0.00017231336,"about_ca_system_score_gemma":0.0050178384,"threshold_uncertainty_score":0.9999786},"labels":[],"label_agreement":null},{"id":"W4395112828","doi":"10.1038/s41597-024-03262-8","title":"Chromosome-level genome assembly of the yellow-cheek carp Elopichthys bambusa","year":2024,"lang":"en","type":"article","venue":"Scientific Data","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":"Ministry of Agriculture","funders":"","keywords":"Genome; Carp; Biology; Chromosome; Sequence assembly; Genome size; Gene; Genetics; Evolutionary biology; Fish <Actinopterygii>; Transcriptome; Fishery","score_opus":0.04989781057585496,"score_gpt":0.273890589885207,"score_spread":0.22399277930935202,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4395112828","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":[0.98023707,0.007411658,0.00016454524,0.00031888386,0.003058804,0.0002029852,0.006006009,0.0000062689905,0.0025937632],"genre_scores_gemma":[0.9909201,0.00013879078,0.0003913397,0.000048231817,0.00020773709,0.000005642018,0.0007920483,0.000015811465,0.0074802665],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.998706,0.00003390882,0.00019817438,0.00064838893,0.00019358103,0.00021995758],"domain_scores_gemma":[0.9980081,0.000012611206,0.00004676537,0.0018164965,0.00007226012,0.00004377009],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047287077,0.00012231186,0.000114744544,0.0000364827,0.00016247915,0.0001195008,0.0012859125,0.000059726823,0.000023118206],"category_scores_gemma":[0.00006927076,0.000087446046,0.00007353664,0.00025621016,0.00030870782,0.0000025317206,0.0015725533,0.00006550686,0.000036977883],"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":[0.0000029116359,0.000016693064,0.0002695547,0.00004483222,0.00008352213,0.0000014559511,0.00008245232,0.000014087075,0.96820027,0.00011099562,0.0301414,0.0010318179],"study_design_scores_gemma":[0.000120877856,0.000036617384,0.019353226,0.000029510138,0.000053730317,0.000007906073,0.00008659006,0.0001491761,0.16840103,0.00014860739,0.8114316,0.00018112063],"about_ca_topic_score_codex":0.00001695813,"about_ca_topic_score_gemma":0.000102927246,"teacher_disagreement_score":0.79979926,"about_ca_system_score_codex":0.000008771637,"about_ca_system_score_gemma":0.00019871692,"threshold_uncertainty_score":0.35659462},"labels":[],"label_agreement":null},{"id":"W4396618987","doi":"10.1038/s41597-024-03258-4","title":"A regionally refined quarter-degree global atmospheric rivers database based on ERA5","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Climate variability and models","field":"Environmental Science","cited_by":37,"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 California, San Diego; Jet Propulsion Laboratory; Nuclear Safety and Security Commission; National Aeronautics and Space Administration; California Institute of Technology; Department of Water Resources; Environment and Climate Change Canada","keywords":"Thresholding; Environmental science; Database; Polar; Block (permutation group theory); Computer science; Meteorology; Water cycle; Water vapor; Tracking (education); Degree (music); Geography; Mathematics; Artificial intelligence; Image (mathematics)","score_opus":0.0682208969313054,"score_gpt":0.2872415749504418,"score_spread":0.21902067801913638,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396618987","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":[0.49573523,0.0004519511,0.091400504,0.03536821,0.021191504,0.0029222514,0.12532361,0.002431854,0.22517489],"genre_scores_gemma":[0.919355,0.000014080901,0.0496689,0.0020160088,0.00016972392,0.0000368511,0.020791885,0.000047210564,0.007900383],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970545,0.000077639124,0.00022610952,0.0014972778,0.0007553179,0.00038914],"domain_scores_gemma":[0.9966823,0.00010131422,0.000036447433,0.0029911979,0.000009055598,0.00017968193],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0014425224,0.00017527911,0.00012418257,0.000014691798,0.00028973474,0.00047748614,0.001529393,0.000053958905,0.0046026087],"category_scores_gemma":[0.00013032592,0.00015039294,0.00005553559,0.000954558,0.0005471251,0.0008178979,0.0009936515,0.00013373392,0.004251545],"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":[0.000060702743,0.00026833775,0.0011615637,0.000051639498,0.000012552644,0.00008733066,0.0000826183,0.0032159141,0.0013436446,0.0015686112,0.9785729,0.013574203],"study_design_scores_gemma":[0.00024231206,0.000050575058,0.0022175084,0.000076956894,0.000028041544,0.0000065786735,0.00003044036,0.585466,0.000015601958,0.0015741321,0.41006592,0.00022592522],"about_ca_topic_score_codex":0.00029885638,"about_ca_topic_score_gemma":0.0008507108,"teacher_disagreement_score":0.58225006,"about_ca_system_score_codex":0.00027167675,"about_ca_system_score_gemma":0.00010546027,"threshold_uncertainty_score":0.99652374},"labels":[],"label_agreement":null},{"id":"W4396624749","doi":"10.1038/s41597-024-03282-4","title":"High resolution Tibetan Plateau regional reanalysis 1961-present","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Cryospheric studies and observations","field":"Earth and Planetary Sciences","cited_by":16,"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 Education and Child Care","funders":"National Key Research and Development Program of China; Jiangsu Collaborative Innovation Center for Climate Change; National Natural Science Foundation of China","keywords":"Plateau (mathematics); Climatology; Precipitation; Environmental science; Weather Research and Forecasting Model; Glacier; Permafrost; Global warming; Initialization; Climate change; Atmospheric sciences; Physical geography; Meteorology; Geology; Geography","score_opus":0.08346350337635322,"score_gpt":0.26992819772547094,"score_spread":0.18646469434911772,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396624749","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":[0.6521417,0.08788621,0.011855867,0.06926938,0.054951366,0.00180892,0.089952044,0.0019498166,0.030184688],"genre_scores_gemma":[0.85449255,0.0006288834,0.009590843,0.0003454619,0.0016520334,0.000004043683,0.087695934,0.000014446327,0.045575827],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981826,0.000037291753,0.00022167161,0.00074630935,0.00052914175,0.0002829726],"domain_scores_gemma":[0.9984816,0.00012873925,0.000036005,0.0012118386,0.000045970828,0.00009587867],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0008675715,0.00010364118,0.00011996043,0.00008140618,0.0006057709,0.0006119436,0.00080191303,0.00003464592,0.0044092215],"category_scores_gemma":[0.0000669057,0.00008021472,0.000051910803,0.0011790249,0.00022436686,0.00052107306,0.00014978195,0.00010633467,0.0013837841],"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":[0.0000064291835,0.0000104452965,0.0038926397,0.000014947441,0.0000719892,0.00001891292,0.00012189189,0.0020344781,0.00001738963,0.0006031917,0.9532492,0.039958492],"study_design_scores_gemma":[0.000042722844,0.000009863999,0.07107496,0.000019899066,0.00005179946,0.0000040574832,0.00016252919,0.16382307,0.0000036784684,0.0009655771,0.76373863,0.0001032311],"about_ca_topic_score_codex":0.0053685955,"about_ca_topic_score_gemma":0.00913402,"teacher_disagreement_score":0.20235083,"about_ca_system_score_codex":0.00000915934,"about_ca_system_score_gemma":0.00008892134,"threshold_uncertainty_score":0.99939376},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"observational","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W4396646579","doi":"10.1038/s41597-024-03300-5","title":"The phased Solanum okadae genome and Petota pangenome analysis of 23 other potato wild relatives and hybrids","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Plant Pathogens and Resistance","field":"Agricultural and Biological Sciences","cited_by":9,"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 New Brunswick; Agriculture and Agri-Food Canada; McGill University","funders":"Agriculture and Agri-Food Canada; Government of Canada; Compute Canada; Direktoratet for Utviklingssamarbeid; Génome Québec; U.S. Department of Agriculture","keywords":"Polyploid; Genome; Biology; Introgression; Ploidy; Germplasm; Solanum tuberosum; Hybrid; Genetics; Solanum; Phylogenetic tree; Gene; Botany","score_opus":0.03343120371711719,"score_gpt":0.24376960080837823,"score_spread":0.21033839709126104,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396646579","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":[0.94992024,0.026987744,0.000012411984,0.0010351896,0.000264498,0.00009787878,0.02102992,0.000024069855,0.00062807096],"genre_scores_gemma":[0.9867976,0.000634971,0.00007225245,0.000022899452,0.0000647856,0.0000024618641,0.0015878805,0.0000010486939,0.010816126],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99896157,0.00005043264,0.00015260183,0.0004825918,0.00017462001,0.00017818318],"domain_scores_gemma":[0.9994394,0.00021053404,0.000045505145,0.00022220996,0.000023464949,0.00005884157],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00086540566,0.0000814178,0.00013313442,0.000033574473,0.00036354025,0.0004024321,0.00041346662,0.000026463107,0.00006863216],"category_scores_gemma":[0.000032100015,0.000025657244,0.000037726906,0.00082615024,0.0004298907,0.00016954176,0.00018550722,0.00005665315,0.00000791098],"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":[0.0000124570515,0.000023465436,0.0009539655,0.00001625697,0.00023053578,0.000009956121,0.00012281701,0.0000010973878,0.976059,0.0005356551,0.004319747,0.017715031],"study_design_scores_gemma":[0.000044893604,0.0000314414,0.12115956,0.000029500372,0.0002422596,0.000008296928,0.000411261,0.0012659488,0.00028977118,0.00036185465,0.8760126,0.00014257296],"about_ca_topic_score_codex":0.00004887519,"about_ca_topic_score_gemma":0.0008480292,"teacher_disagreement_score":0.9757692,"about_ca_system_score_codex":0.000004496669,"about_ca_system_score_gemma":0.00000906942,"threshold_uncertainty_score":0.3880662},"labels":[],"label_agreement":null},{"id":"W4396736647","doi":"10.1038/s41597-024-03280-6","title":"Getting your DUCs in a row - standardising the representation of Digital Use Conditions","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Research Data Management Practices","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; Ontario Brain Institute","funders":"Institut National de la Santé et de la Recherche Médicale; European Commission","keywords":"Computer science; Context (archaeology); Ambiguity; Asset (computer security); Data science; Granularity; Representation (politics); Task (project management); Diversity (politics); Knowledge management; Risk analysis (engineering); Business; Systems engineering","score_opus":0.3149498459064001,"score_gpt":0.45547181828544675,"score_spread":0.14052197237904662,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396736647","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":[0.136902,0.0006791307,0.81628436,0.018951239,0.004000316,0.001183033,0.015239706,0.00032129764,0.006438941],"genre_scores_gemma":[0.9901949,0.000030792875,0.0045277374,0.000020637788,0.00003748972,0.000007971275,0.0023651328,0.000007125457,0.0028082158],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979354,0.00011812018,0.0002425831,0.00073539146,0.00075282156,0.00021564448],"domain_scores_gemma":[0.9960769,0.00057328615,0.00007430889,0.003169679,0.00006967733,0.00003619494],"candidate_categories":["scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0030451478,0.0000603908,0.00007082365,0.00029975604,0.00021181529,0.023637502,0.0037773266,0.000012324519,0.000012214654],"category_scores_gemma":[0.0025956216,0.000044850407,0.000021785405,0.0020089624,0.00021908572,0.07460989,0.0037995481,0.00013997983,0.00003260143],"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":[0.00001817498,0.0002912475,0.0070631998,0.00032196904,0.00018525007,0.00040626718,0.0046760472,0.0012710881,0.008216658,0.43118498,0.42376408,0.12260103],"study_design_scores_gemma":[0.00029228895,0.00002970369,0.013401678,0.00036621225,0.000032310865,0.00002548402,0.0021772191,0.4775335,0.001222851,0.012702272,0.49191564,0.00030085404],"about_ca_topic_score_codex":0.00007893944,"about_ca_topic_score_gemma":0.0000617239,"teacher_disagreement_score":0.8532929,"about_ca_system_score_codex":0.000031390562,"about_ca_system_score_gemma":0.00014813164,"threshold_uncertainty_score":0.97737604},"labels":[],"label_agreement":null},{"id":"W4396749763","doi":"10.1038/s41597-024-03279-z","title":"Common conditions of use elements. Atomic concepts for consistent and effective information governance","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Research Data Management Practices","field":"Computer Science","cited_by":7,"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 Brain Institute","funders":"Institut National de la Santé et de la Recherche Médicale","keywords":"Corporate governance; Information retrieval; Business; Computer science","score_opus":0.09817008775534806,"score_gpt":0.40416528018941256,"score_spread":0.3059951924340645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396749763","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":[0.09792817,0.0012209413,0.7999005,0.00457568,0.0053525916,0.0057489146,0.08291299,0.00034409453,0.0020161308],"genre_scores_gemma":[0.97197074,0.0001861202,0.01822226,0.00012199973,0.000019322068,0.00011683675,0.008104933,0.0000066718085,0.0012511121],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99857634,0.000078449586,0.00027020465,0.00047866546,0.00040681573,0.00018950609],"domain_scores_gemma":[0.99724555,0.00072072283,0.00014572106,0.0017184842,0.000112983886,0.00005652031],"candidate_categories":["scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.002136967,0.00007645558,0.00010357867,0.00013312999,0.00018852348,0.005781039,0.0019051487,0.000014965131,0.000009228705],"category_scores_gemma":[0.0008146486,0.00006928159,0.000020587577,0.00045100984,0.0002993982,0.058846656,0.0022444017,0.000072570714,0.00003327446],"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":[0.000011935146,0.0000435174,0.0004607289,0.0003971506,0.00009437958,0.000004468769,0.00023893552,0.0000067468773,0.0005771268,0.74663526,0.20900556,0.042524192],"study_design_scores_gemma":[0.00033734002,0.000056648816,0.0057250103,0.00011850836,0.000027938771,0.000004808006,0.00007299234,0.12115881,0.00074212946,0.0018879559,0.86975557,0.00011227799],"about_ca_topic_score_codex":0.000048165093,"about_ca_topic_score_gemma":0.00003914347,"teacher_disagreement_score":0.8740426,"about_ca_system_score_codex":0.000039000563,"about_ca_system_score_gemma":0.00009487615,"threshold_uncertainty_score":0.99525106},"labels":[],"label_agreement":null},{"id":"W4396799260","doi":"10.1038/s41597-024-03306-z","title":"How accurate are existing land cover maps for agriculture in Sub-Saharan Africa?","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Land Use and Ecosystem Services","field":"Environmental Science","cited_by":43,"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","funders":"National Aeronautics and Space Administration","keywords":"Land cover; Agriculture; Land use; Agricultural land; Environmental resource management; Satellite; Work (physics); Monitoring and evaluation; Remote sensing; Geography; Environmental science; Ecology; Economic growth","score_opus":0.05920618791904884,"score_gpt":0.2583645116580236,"score_spread":0.19915832373897477,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396799260","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":[0.9354371,0.00873334,0.00057224365,0.004553655,0.0074231904,0.0017236785,0.031089896,0.0003361416,0.0101307845],"genre_scores_gemma":[0.9904572,0.000040983665,0.00017771122,0.00003429161,0.0001590559,0.000030269497,0.0030919993,0.000013470292,0.005995062],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.998577,0.000022347253,0.00013932615,0.00071371265,0.00023847938,0.00030912002],"domain_scores_gemma":[0.9992094,0.000043527638,0.00004831337,0.00062597875,0.000006738119,0.00006603419],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007667767,0.000109096065,0.000117610514,0.000041145508,0.00018554424,0.0012553403,0.0008072424,0.00004893981,0.00014162216],"category_scores_gemma":[0.000045938374,0.00007027168,0.000027606953,0.0005246617,0.000027663316,0.0011166442,0.0005254738,0.000076243494,0.0008696436],"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":[0.000008365366,0.00003829387,0.0057998006,0.00026626835,0.000011604383,0.000035295536,0.0002716316,0.00026279961,0.004387576,0.0000135305245,0.98660463,0.0023001868],"study_design_scores_gemma":[0.00014707615,0.000006607312,0.0029787142,0.00018262006,0.000013231697,0.0000042967354,0.000076762604,0.016389785,0.00043453925,0.00025801192,0.9793559,0.00015246823],"about_ca_topic_score_codex":0.00007550903,"about_ca_topic_score_gemma":0.0044818963,"teacher_disagreement_score":0.055020086,"about_ca_system_score_codex":0.000045800618,"about_ca_system_score_gemma":0.000010244291,"threshold_uncertainty_score":0.99990827},"labels":[],"label_agreement":null},{"id":"W4396890157","doi":"10.1038/s41597-024-03327-8","title":"Analysis of AlphaMissense data in different protein groups and structural context","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Genomics and Rare Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":120,"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 Research, Development and Innovation Office; Semmelweis Egyetem","keywords":"Context (archaeology); Computer science; Information retrieval; Computational biology; Biology; Paleontology","score_opus":0.026816436164746913,"score_gpt":0.29135570214338696,"score_spread":0.26453926597864,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396890157","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":[0.9820703,0.003883969,0.00006817989,0.000067147834,0.0002007551,0.00011944187,0.013563196,0.000003857851,0.000023125427],"genre_scores_gemma":[0.9677446,0.000025512487,0.00005733644,0.000009725421,0.00003060568,0.0000018619079,0.03179184,0.000005619239,0.00033289014],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99885815,0.00002793555,0.00016217344,0.00072553864,0.00010508486,0.00012109122],"domain_scores_gemma":[0.9980998,0.000007943444,0.000029226423,0.0017889143,0.000021444233,0.00005266802],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000280231,0.00008392722,0.00013033484,0.00013937555,0.00003842574,0.00014228479,0.00069490564,0.000034186727,0.000034680645],"category_scores_gemma":[0.0000743851,0.00006299034,0.000028056513,0.00028445484,0.00015584103,0.000011191309,0.0013136588,0.00003521247,0.0000013829213],"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":[0.00008273681,0.00010547292,0.009102241,0.0002279879,0.0010698729,0.00006019261,0.00022497408,0.000016578753,0.9411827,0.00037774563,0.01767153,0.029878022],"study_design_scores_gemma":[0.0018792193,0.0002719791,0.32849017,0.0003531161,0.0028966537,0.00005135366,0.0024694833,0.39349297,0.079926014,0.0011770297,0.1873747,0.00161733],"about_ca_topic_score_codex":0.00006253655,"about_ca_topic_score_gemma":0.00082388497,"teacher_disagreement_score":0.86125666,"about_ca_system_score_codex":0.000003563613,"about_ca_system_score_gemma":0.00005088554,"threshold_uncertainty_score":0.25686714},"labels":[],"label_agreement":null},{"id":"W4396890326","doi":"10.1038/s41597-024-03295-z","title":"ReMIND: The Brain Resection Multimodal Imaging Database","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":32,"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 Ottawa","funders":"National Institutes of Health; Brigham and Women's Hospital; National Institute of Biomedical Imaging and Bioengineering; U.S. Department of Health and Human Services","keywords":"Neuronavigation; Magnetic resonance imaging; Interventional magnetic resonance imaging; Medicine; Intraoperative MRI; Workflow; Database; Radiology; Brain tumor; Computer science; Pathology","score_opus":0.03263658663287678,"score_gpt":0.35931578249153895,"score_spread":0.3266791958586622,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396890326","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":[0.18159033,0.018693164,0.11250758,0.5893998,0.05235756,0.0025731537,0.0055191484,0.00200914,0.035350118],"genre_scores_gemma":[0.927093,0.00005723917,0.009525623,0.0035532995,0.0022978678,0.000018181136,0.015565097,0.00008344003,0.041806232],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982493,0.00006500511,0.00018627883,0.00074735505,0.00048458626,0.00026748076],"domain_scores_gemma":[0.997581,0.0002297834,0.000026527287,0.0019972578,0.000039644703,0.00012578175],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0040005473,0.00009594407,0.00010204784,0.00015880517,0.00036756392,0.0006483699,0.00065835315,0.000021361826,0.00026904984],"category_scores_gemma":[0.0019243796,0.000059807146,0.00003834254,0.00053041603,0.0004008165,0.00040352653,0.0005990312,0.0005618252,0.000259868],"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":[0.000014263493,0.000023084318,0.00036063086,0.000080189224,0.000019682486,0.00013872547,0.00020763134,0.000004535399,0.023811724,0.0003046001,0.83917564,0.1358593],"study_design_scores_gemma":[0.00016014611,0.000006362093,0.00041781575,0.00019622655,0.00003692649,0.0001827434,0.0001054131,0.40033993,0.00028211193,0.000111705274,0.59810567,0.000054934804],"about_ca_topic_score_codex":0.0001343323,"about_ca_topic_score_gemma":0.000019401015,"teacher_disagreement_score":0.7455027,"about_ca_system_score_codex":0.000039646107,"about_ca_system_score_gemma":0.0001800691,"threshold_uncertainty_score":0.6252246},"labels":[],"label_agreement":null},{"id":"W4396930028","doi":"10.1038/s41597-024-03350-9","title":"A multi-institutional meningioma MRI dataset for automated multi-sequence image segmentation","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Meningioma and schwannoma management","field":"Medicine","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":"University of Manitoba; University of Toronto; University of Ottawa","funders":"National Cancer Institute; National Institutes of Health; Perelman School of Medicine, University of Pennsylvania; Instituto Tecnológico de Costa Rica; American Society of Neuroradiology; University of Pennsylvania; Foundation for the National Institutes of Health","keywords":"Meningioma; Fluid-attenuated inversion recovery; Segmentation; Sequence (biology); Contrast (vision); Radiology; Medicine; Computer science; Magnetic resonance imaging; Medical physics; Artificial intelligence","score_opus":0.1666244615822458,"score_gpt":0.4157804038618527,"score_spread":0.2491559422796069,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396930028","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":[0.039037514,0.0012558628,0.6259125,0.0031341927,0.008723542,0.004685742,0.3147229,0.0021207638,0.0004069803],"genre_scores_gemma":[0.052778665,0.0000027454255,0.51886195,0.000068614005,0.00011729423,0.00011760391,0.42338598,0.000022996397,0.0046441765],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976716,0.000031526848,0.00035051545,0.0011250939,0.00047638078,0.00034490507],"domain_scores_gemma":[0.99817806,0.0000530542,0.00005722915,0.0014583091,0.00009902582,0.00015429338],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014333207,0.00018498172,0.00018395194,0.00032342316,0.00040548373,0.00071981683,0.00061071536,0.000046552326,0.00019815941],"category_scores_gemma":[0.00022458474,0.00014923025,0.000056692443,0.00058580184,0.0003018597,0.0010025128,0.00048402115,0.00009339798,0.00055926334],"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":[0.000043288837,0.00017765636,0.00003498305,0.00048021434,0.00013431476,0.0008626008,0.00019178141,0.000024955012,0.21495852,0.00040813745,0.7800304,0.0026531396],"study_design_scores_gemma":[0.0011146982,0.00004154227,0.00035280985,0.00018188,0.00017848716,0.00020456463,0.000102585145,0.7567011,0.0029699858,0.000016640102,0.23797314,0.00016258591],"about_ca_topic_score_codex":0.000030430016,"about_ca_topic_score_gemma":0.000015075595,"teacher_disagreement_score":0.75667614,"about_ca_system_score_codex":0.000109152366,"about_ca_system_score_gemma":0.00027482235,"threshold_uncertainty_score":0.7188385},"labels":[],"label_agreement":null},{"id":"W4397005444","doi":"10.1038/s41597-024-03345-6","title":"LNDb v4: pulmonary nodule annotation from medical reports","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Lung Cancer Diagnosis and Treatment","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Fundação para a Ciência e a Tecnologia; Centre hospitalier universitaire Sainte-Justine","keywords":"Annotation; Nodule (geology); Computer science; Medicine; Information retrieval; Computational biology; Biology; Artificial intelligence; Paleontology","score_opus":0.040594619729269886,"score_gpt":0.3490781918351679,"score_spread":0.30848357210589805,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4397005444","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":[0.78332454,0.044910524,0.0014002722,0.065056056,0.05268898,0.001962387,0.01479012,0.0012479081,0.03461921],"genre_scores_gemma":[0.95514613,0.00013131596,0.00088574074,0.0003106939,0.0006547797,0.000030086318,0.036094014,0.000021719625,0.0067255157],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99778664,0.000018886245,0.00025344163,0.0009535063,0.00081063807,0.00017689097],"domain_scores_gemma":[0.99793816,0.00006952447,0.00003476621,0.0017129319,0.00004767759,0.00019695504],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00071107806,0.00009607128,0.00014270395,0.00009027285,0.00010061088,0.00023259336,0.00022733133,0.00005883167,0.0024512426],"category_scores_gemma":[0.00015230906,0.000070811184,0.000042275595,0.00034329738,0.00012920998,0.0002825125,0.0002747381,0.00011582811,0.0005853703],"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":[0.000012728553,0.00027961025,0.009871765,0.00009572041,0.00011615353,0.006093925,0.0001374152,3.723436e-7,0.00041073505,0.00012505373,0.8904087,0.09244781],"study_design_scores_gemma":[0.00020399583,0.000030977637,0.02193477,0.00069662195,0.00021797595,0.0002832178,0.000047758298,0.0049652513,0.0008148159,0.0006864716,0.97001106,0.00010708949],"about_ca_topic_score_codex":0.000273035,"about_ca_topic_score_gemma":0.000097232434,"teacher_disagreement_score":0.17182158,"about_ca_system_score_codex":0.00010102223,"about_ca_system_score_gemma":0.0004366765,"threshold_uncertainty_score":0.99846065},"labels":[],"label_agreement":null},{"id":"W4398238439","doi":"10.1038/s41597-024-03319-8","title":"Typical and extreme weather datasets for studying the resilience of buildings to climate change and heatwaves","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Wind and Air Flow Studies","field":"Environmental Science","cited_by":87,"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; National Research Council Canada","funders":"Energiteknologisk udviklings- og demonstrationsprogram; Fraunhofer-Gesellschaft; European Commission; U.S. Department of Energy","keywords":"Resilience (materials science); Extreme weather; Climate change; Climate extremes; Environmental science; Climatology; Extreme heat; Geography; Ecology; Geology; Biology","score_opus":0.1085341305823821,"score_gpt":0.3079705183688564,"score_spread":0.19943638778647432,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398238439","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":[0.97506666,0.0027601346,0.0006058112,0.0052830405,0.00089631864,0.0009596741,0.014129519,0.000042433774,0.0002563849],"genre_scores_gemma":[0.996134,0.00010751178,0.0028783246,0.00017773591,0.000079632846,0.000030255918,0.00018773942,0.000009453261,0.0003953751],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989877,0.000014091273,0.000100504716,0.0005389087,0.00016969355,0.00018913325],"domain_scores_gemma":[0.99931824,0.000088032706,0.000014252123,0.0005276713,0.0000031285265,0.000048691152],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009372818,0.00006909728,0.000078113,0.000025169547,0.0003225641,0.00018289693,0.00043508146,0.000011943477,0.000047199934],"category_scores_gemma":[0.00006447907,0.000041913467,0.000008888386,0.00020858344,0.00048159534,0.00033553247,0.0020464333,0.000034907014,0.000025076728],"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":[0.00008758665,0.00010435724,0.027148424,0.00025847,0.00003401951,0.0000081998905,0.007874165,0.000006170207,0.040542588,0.001883246,0.54119873,0.38085407],"study_design_scores_gemma":[0.00020215758,0.000103103695,0.10846865,0.00025166856,0.00005901554,0.000009629831,0.0016105282,0.0056330515,0.0008902425,0.00085706334,0.88166016,0.0002547231],"about_ca_topic_score_codex":0.000024469507,"about_ca_topic_score_gemma":0.000085110725,"teacher_disagreement_score":0.38059935,"about_ca_system_score_codex":0.0000067899778,"about_ca_system_score_gemma":0.0000029181506,"threshold_uncertainty_score":0.25507328},"labels":[],"label_agreement":null},{"id":"W4399179273","doi":"10.1038/s41597-024-03410-0","title":"Global Spore Sampling Project: A global, standardized dataset of airborne fungal DNA","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Indoor Air Quality and Microbial Exposure","field":"Environmental Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Center for Northern Studies; Université de Moncton; University of Guelph; Saint Mary's University; MacEwan University","funders":"Biotechnology and Biological Sciences Research Council; Natural Sciences and Engineering Research Council of Canada; Nature; Natural Environment Research Council; Mushroom Research Foundation; Vetenskapsrådet; Eesti Teadusagentuur; Svenska Forskningsrådet Formas; Novo Nordisk Fonden; Norges Forskningsråd; Academy of Finland; National Natural Science Foundation of China; Fundação de Amparo à Pesquisa do Estado de São Paulo; European Commission; Sight Research UK; Hrvatska Zaklada za Znanost; Novo Nordisk; Polar Knowledge Canada; Jane ja Aatos Erkon Säätiö; National Science Foundation","keywords":"Sampling (signal processing); Spore; Biology; Environmental science; Geography; Botany; Computer science","score_opus":0.05739459153731757,"score_gpt":0.33950596873200195,"score_spread":0.2821113771946844,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399179273","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10324598,0.000530242,0.005943202,0.00036658105,0.003296305,0.00065679604,0.88107115,0.00017066248,0.004719094],"genre_scores_gemma":[0.79828584,0.0000357173,0.019040832,0.00032353168,0.00026379427,0.000013747485,0.18020709,0.000036695048,0.001792719],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99721634,0.00007972282,0.0004428303,0.001139635,0.00069180544,0.00042965024],"domain_scores_gemma":[0.99777704,0.000027176227,0.000087885484,0.0019911,0.000017949982,0.000098846205],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0025460261,0.00017810354,0.00022082144,0.00003439612,0.000250053,0.00043582154,0.0017160005,0.000080440375,0.0014355091],"category_scores_gemma":[0.00014045586,0.00015492424,0.000060538398,0.0014127721,0.0008066325,0.0008654597,0.0021199738,0.00010960766,0.00060573005],"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":[0.0000546256,0.00008790487,0.0007347236,0.000098779434,0.000029717727,0.000036888527,0.00016842136,0.000045417895,0.0034050036,0.0009808913,0.9707643,0.023593333],"study_design_scores_gemma":[0.0002737795,0.000033345277,0.0012162694,0.00009080058,0.00005304044,0.00004370059,0.0001764972,0.00069458067,0.00058017793,0.0006920065,0.9959309,0.00021489606],"about_ca_topic_score_codex":0.0009945851,"about_ca_topic_score_gemma":0.0017920374,"teacher_disagreement_score":0.700864,"about_ca_system_score_codex":0.00024762633,"about_ca_system_score_gemma":0.0002412899,"threshold_uncertainty_score":0.9994773},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W4399241163","doi":"10.1038/s41597-024-03384-z","title":"A labelled dataset to classify direct deforestation drivers from Earth Observation imagery in Cameroon","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Remote Sensing in Agriculture","field":"Environmental Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"International Institute for Sustainable Development","funders":"Natural Environment Research Council; Research Councils UK","keywords":"Deforestation (computer science); Earth (classical element); Remote sensing; Geography; Geology; Environmental science; Earth science; Physical geography; Computer science; Mathematics","score_opus":0.036656666155668864,"score_gpt":0.2699228151220721,"score_spread":0.23326614896640324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399241163","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":[0.96714276,0.00005616569,0.00061983994,0.001286016,0.0023390893,0.0004611657,0.026134256,0.00012882258,0.0018318845],"genre_scores_gemma":[0.62667096,0.00002545936,0.046767306,0.0006100459,0.0001892215,0.0000069625257,0.3160356,0.000046444446,0.009647985],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978916,0.00007867674,0.00020718334,0.0010627297,0.0005039653,0.00025582325],"domain_scores_gemma":[0.9985481,0.000087134234,0.00003737933,0.0012217164,0.00000792656,0.00009772699],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00071041426,0.00012472284,0.00010784099,0.000089782094,0.00013282245,0.0005683169,0.00072528876,0.000051898867,0.00045667178],"category_scores_gemma":[0.00020452532,0.00010050185,0.000016650421,0.0013153485,0.00015978994,0.0011396082,0.00079142,0.00014249,0.0034519047],"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":[0.000006601575,0.000029780565,0.0038040134,0.0000067997953,0.000005978909,0.00004178314,0.00054266053,0.0011442126,0.08887637,0.000005370377,0.880475,0.025061427],"study_design_scores_gemma":[0.00015398844,0.0000139059575,0.16875008,0.000117593445,0.000021631542,0.0000025384586,0.00019323907,0.071639046,0.002810315,0.00020866918,0.7558266,0.00026237516],"about_ca_topic_score_codex":0.0021950398,"about_ca_topic_score_gemma":0.013083554,"teacher_disagreement_score":0.3404718,"about_ca_system_score_codex":0.00014353047,"about_ca_system_score_gemma":0.000028842129,"threshold_uncertainty_score":0.99732405},"labels":[],"label_agreement":null},{"id":"W4399335878","doi":"10.1038/s41597-024-03416-8","title":"Publication, funding, and experimental data in support of Human Reference Atlas construction and usage","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"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":"Common Fund; NIH Office of the Director; National Institute of Diabetes and Digestive and Kidney Diseases; National Cancer Institute; National Institutes of Health; Canadian Institute for Advanced Research","keywords":"Metadata; Computer science; Atlas (anatomy); Information retrieval; Data science; World Wide Web; Digital library; Medicine","score_opus":0.08935916613375858,"score_gpt":0.33606086493482396,"score_spread":0.24670169880106538,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399335878","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":[0.9952562,0.00091309164,0.00015604279,0.00009032186,0.00035922782,0.0000809385,0.0023961954,0.000007644261,0.000740327],"genre_scores_gemma":[0.98388475,0.000033929577,0.0006068256,0.000014227749,0.000029310704,0.0000014881427,0.014788345,0.000004924778,0.00063618],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990973,0.000016491718,0.00014901585,0.00056533644,0.00008152451,0.00009036654],"domain_scores_gemma":[0.9990365,0.000004302016,0.000026703483,0.00087356305,0.000022472499,0.000036469042],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046466562,0.000055903958,0.000058850474,0.000061744126,0.00006391293,0.00019475826,0.0004057162,0.000042999833,0.00004011292],"category_scores_gemma":[0.000034620618,0.000053780783,0.00000461544,0.00010416281,0.00032716955,0.000038888025,0.0005357437,0.000042112883,0.0000020474304],"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":[0.000005738146,0.00002782497,0.0033685088,0.00003374905,0.0000073173155,8.0855364e-7,0.00007006395,6.018323e-8,0.97513145,0.0004695125,0.018858923,0.002026043],"study_design_scores_gemma":[0.00051528506,0.00014294243,0.003161861,0.00004713632,0.000024027058,0.0000435593,0.00038258082,0.00085018226,0.4365063,0.00013934883,0.5579381,0.0002486679],"about_ca_topic_score_codex":0.00004734711,"about_ca_topic_score_gemma":0.0001483979,"teacher_disagreement_score":0.5390792,"about_ca_system_score_codex":0.0000038166236,"about_ca_system_score_gemma":0.000050570892,"threshold_uncertainty_score":0.21931167},"labels":[],"label_agreement":null},{"id":"W4399362984","doi":"10.1038/s41597-024-03390-1","title":"Individual Brain Charting dataset extension, third release for movie watching and retinotopy data","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Canada First Research Excellence Fund; European Commission; University of Minnesota","keywords":"Retinotopy; Computer science; Functional magnetic resonance imaging; Neuroscience; Visual cortex; Task (project management); Artificial intelligence; Psychology","score_opus":0.20730925246454832,"score_gpt":0.36652595026983376,"score_spread":0.15921669780528544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399362984","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.049252823,0.0027751133,0.00416616,0.11505548,0.010752969,0.0022218537,0.8146833,0.0006943778,0.00039793545],"genre_scores_gemma":[0.55522674,0.0002475722,0.015272138,0.030732352,0.0024462799,0.00022527398,0.3876268,0.00022882485,0.007994014],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9952817,0.00019650582,0.00035894802,0.0030382462,0.000678058,0.0004465553],"domain_scores_gemma":[0.98513,0.010277775,0.000101073034,0.0043066996,0.00005224808,0.00013220533],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.007906462,0.00020566047,0.0002469365,0.00018916135,0.0011867667,0.0016517137,0.002385983,0.000049198195,0.000034124234],"category_scores_gemma":[0.07715827,0.00017330147,0.000028591707,0.0005733438,0.00085570914,0.0023170393,0.007877643,0.00025897042,0.00012612909],"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":[0.000067460496,0.000027647053,0.00001488886,0.00011929406,0.000016436083,0.000027460883,0.0002708481,0.0000024974936,0.012897666,0.0027997722,0.9710198,0.012736221],"study_design_scores_gemma":[0.0007081636,0.000022369175,0.000118178046,0.00013606496,0.000061637795,0.000050959596,0.0001421948,0.06723882,0.0030298054,0.004528838,0.9237012,0.000261746],"about_ca_topic_score_codex":0.00004235108,"about_ca_topic_score_gemma":0.00008657998,"teacher_disagreement_score":0.50597394,"about_ca_system_score_codex":0.000018604806,"about_ca_system_score_gemma":0.00014940463,"threshold_uncertainty_score":0.99938464},"labels":[],"label_agreement":null},{"id":"W4399390779","doi":"10.1038/s41597-024-03443-5","title":"The Pan-Canadian Chemical Library: A Mechanism to Open Academic Chemistry to High-Throughput Virtual Screening","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":10,"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 Winnipeg; University of Alberta; Structural Genomics Consortium; University of Toronto","funders":"National Institute of General Medical Sciences; Genentech; European Federation of Pharmaceutical Industries and Associations; University of Toronto; Ontario Genomics Institute; Merck KGaA; Alliance de recherche numérique du Canada; National Institutes of Health; Ontario Genomics; Genome Canada; McGill University; Bayer; Pfizer; Bristol-Myers Squibb","keywords":"Chemical space; Drug discovery; Workflow; Virtual screening; Computer science; Chemical library; Data science; Cheminformatics; Chemical database; Process (computing); Mechanism (biology); Chemistry; Chemical biology; Resource (disambiguation); Nanotechnology; Small molecule; Database; Physics; Materials science; Computational chemistry; Organic chemistry","score_opus":0.06922418333834772,"score_gpt":0.3512207175254694,"score_spread":0.2819965341871217,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399390779","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":[0.012613918,0.0002387344,0.92222667,0.053168505,0.005261929,0.00090116047,0.0030745175,0.00038874277,0.002125855],"genre_scores_gemma":[0.29750136,0.000011070296,0.6698908,0.0049290024,0.0009479158,0.00014830445,0.0024846476,0.00009471123,0.023992201],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9963288,0.000118272976,0.00033632302,0.0018438186,0.0007133027,0.0006595083],"domain_scores_gemma":[0.9957167,0.00051916693,0.000037912683,0.0030375936,0.00004774689,0.00064086],"candidate_categories":["scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.0029368105,0.00020133937,0.00016564633,0.0001659364,0.000640145,0.008770937,0.01697648,0.000085767206,0.000100273915],"category_scores_gemma":[0.00053094234,0.00016551367,0.000040830455,0.0024227554,0.00011724587,0.003298231,0.018442383,0.00041192604,0.00086887437],"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":[0.000008673074,0.000011482642,0.0000018762956,0.000012047744,0.000029678647,0.000036015605,0.00054676534,0.000554123,0.011185032,0.23251404,0.52751696,0.22758332],"study_design_scores_gemma":[0.00008850065,0.000015150297,0.000051820345,0.00013148114,0.000008671461,0.000022009894,0.00007974558,0.17645729,0.019771375,0.04400361,0.75902724,0.00034310072],"about_ca_topic_score_codex":0.0013052608,"about_ca_topic_score_gemma":0.00036135115,"teacher_disagreement_score":0.28488743,"about_ca_system_score_codex":0.0001088179,"about_ca_system_score_gemma":0.0016249714,"threshold_uncertainty_score":0.99990904},"labels":[{"model":"gemma","categories":["open_science"],"domain":null,"study_design":"not_applicable","genre":"methods","about_ca_system":true,"about_ca_topic":false,"confidence":"medium"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":true,"about_ca_topic":true,"confidence":"low"}],"label_agreement":"split"},{"id":"W4399437290","doi":"10.1038/s41597-024-03396-9","title":"Three-dimensional reconstruction of high latitude bamboo coral via X-ray microfocus Computed Tomography","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Bamboo properties and applications","field":"Agricultural and Biological Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université Laval; ArcticNet","funders":"Fisheries and Oceans Canada; Memorial University of Newfoundland; Research Councils UK; Université Laval","keywords":"Bamboo; Coral; Computed tomography; Tomography; Latitude; Geology; Radiology; Biology; Geodesy; Medicine; Oceanography; Botany","score_opus":0.03660706357985551,"score_gpt":0.2273520553715746,"score_spread":0.19074499179171908,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399437290","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":[0.9903985,0.0009795735,0.00069697003,0.0014266036,0.0019099044,0.00024223675,0.0041256784,0.0001296019,0.00009090295],"genre_scores_gemma":[0.9922681,0.000003395423,0.0041404073,0.00003079963,0.00014974631,0.0000058607957,0.003180073,0.0000010896599,0.00022055766],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99882007,0.000018842433,0.00021929952,0.00056112354,0.00020897374,0.00017166494],"domain_scores_gemma":[0.99947155,0.00005326728,0.000051535066,0.00028577197,0.00007856298,0.00005930861],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003251763,0.00009176824,0.00011603236,0.000029770546,0.00026870734,0.00022070388,0.000627616,0.000049740545,0.00054143963],"category_scores_gemma":[0.0000066291154,0.0000361925,0.000052494965,0.0007710129,0.0003159047,0.00025228577,0.00035517136,0.00008749952,0.00011351036],"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":[0.00001021648,0.00008757325,0.00068032084,0.000019847912,0.000035161916,0.0000016214573,0.000014374069,0.000045338813,0.5144127,0.0013162207,0.058380544,0.4249961],"study_design_scores_gemma":[0.0003965017,0.00032470064,0.16074018,0.00051201734,0.00016712162,0.00009780839,0.00012215889,0.1347906,0.03425875,0.019503085,0.64805686,0.0010302127],"about_ca_topic_score_codex":0.0006802036,"about_ca_topic_score_gemma":0.0010423573,"teacher_disagreement_score":0.5896763,"about_ca_system_score_codex":0.0000087429,"about_ca_system_score_gemma":0.000016910803,"threshold_uncertainty_score":0.59283847},"labels":[],"label_agreement":null},{"id":"W4399514622","doi":"10.1038/s41597-024-03395-w","title":"A Global Multi-Source Tropical Cyclone Precipitation (MSTCP) Dataset","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Tropical and Extratropical Cyclones Research","field":"Earth and Planetary Sciences","cited_by":8,"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 du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Nuclear Safety and Security Commission; Université du Québec à Montréal; National Aeronautics and Space Administration","keywords":"Tropical cyclone; Precipitation; Storm; Environmental science; Climatology; Tropical cyclone scales; Quantitative precipitation estimation; Meteorology; Cyclone (programming language); Geography; Geology; Computer science","score_opus":0.07639561662460964,"score_gpt":0.33238279257025183,"score_spread":0.2559871759456422,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399514622","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":[0.53852814,0.0075229947,0.06718983,0.004956164,0.009405051,0.00095261435,0.3681629,0.0007721211,0.0025101437],"genre_scores_gemma":[0.88056713,0.000031542873,0.008251288,0.000099748715,0.00036403883,0.0000020126515,0.10940258,0.000005445994,0.0012762242],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99718875,0.0001268565,0.00026927656,0.0011246048,0.0007461383,0.00054438727],"domain_scores_gemma":[0.9981986,0.0001437023,0.000021530082,0.0012629142,0.00003274733,0.0003404881],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00036987732,0.00015284464,0.00014884955,0.00008797983,0.00032945472,0.0014165514,0.0015648442,0.00007935789,0.0035623536],"category_scores_gemma":[0.0002486644,0.000111044865,0.000044634326,0.0009677415,0.0004518329,0.00091108354,0.0002822504,0.00021961273,0.005455416],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000067046276,0.00009632997,0.228879,0.000110464585,0.000041750638,0.000121408746,0.000058545498,0.00017911753,0.000073845426,0.0007630691,0.42215636,0.34745306],"study_design_scores_gemma":[0.00013168504,0.000039843108,0.4136981,0.000017626413,0.000013265786,0.00001676186,0.000023223825,0.07629752,0.0000036680021,0.000663152,0.5089714,0.00012377133],"about_ca_topic_score_codex":0.0024606772,"about_ca_topic_score_gemma":0.017946506,"teacher_disagreement_score":0.3473293,"about_ca_system_score_codex":0.000012490555,"about_ca_system_score_gemma":0.00012771499,"threshold_uncertainty_score":0.9999734},"labels":[],"label_agreement":null},{"id":"W4399694734","doi":"10.1038/s41597-024-03455-1","title":"3D atlas of the human fetal chondrocranium in the middle trimester","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Bone Tumor Diagnosis and Treatments","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Vysoké Učení Technické v Brně; Grantová Agentura České Republiky; Ministerstvo Školství, Mládeže a Tělovýchovy","keywords":"Endochondral ossification; Anatomy; Biology; Craniofacial; Skull; Atlas (anatomy); Cartilage","score_opus":0.10400742827335764,"score_gpt":0.32918538283790905,"score_spread":0.22517795456455142,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399694734","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":[0.9866414,0.0015080415,0.000001948384,0.0022898135,0.0015577099,0.0004720498,0.0008044338,0.00002023861,0.006704369],"genre_scores_gemma":[0.9843375,0.0000047563467,0.00004487528,0.00008489927,0.00005430126,0.000010713701,0.00062924455,0.000008415772,0.014825258],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988845,0.0000482785,0.00018638872,0.00038056012,0.00034699324,0.00015328338],"domain_scores_gemma":[0.99817497,0.00005310621,0.000028775617,0.0016976545,0.000017848837,0.000027660593],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00066203275,0.00007953461,0.00012403456,0.00007255536,0.00011233467,0.00014053736,0.0006535675,0.00002187692,0.00015043038],"category_scores_gemma":[0.00003900017,0.000036587102,0.000060156708,0.00054775836,0.00021646272,0.00013673077,0.00027611147,0.00013069222,0.00015166297],"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":[0.0000336625,0.002150824,0.04920459,0.0005113551,0.00020260141,0.0003808742,0.004419912,0.0000013607807,0.012092109,0.0020249826,0.91496307,0.01401465],"study_design_scores_gemma":[0.0025272286,0.00016409537,0.33979163,0.0014869263,0.0005961206,0.00020797335,0.00089106883,0.0008697939,0.008304696,0.00060625,0.64432037,0.00023385677],"about_ca_topic_score_codex":0.00010913672,"about_ca_topic_score_gemma":0.00016497266,"teacher_disagreement_score":0.290587,"about_ca_system_score_codex":0.000018796534,"about_ca_system_score_gemma":0.00009364383,"threshold_uncertainty_score":0.19493712},"labels":[],"label_agreement":null},{"id":"W4399886311","doi":"10.1038/s41597-024-03414-w","title":"SARS-CoV-2 viral titer measurements in Ontario, Canada wastewaters throughout the COVID-19 pandemic","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"SARS-CoV-2 detection and testing","field":"Medicine","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Children's Hospital of Eastern Ontario; Ministry of the Environment, Conservation and Parks; University of Windsor; Trent University; University of Guelph; Ontario Tech University; McMaster University; Queen's University; Western University; University of Toronto; Health Sciences North; Ottawa Hospital; Toronto Metropolitan University; Carleton University; University of Waterloo; University of Ottawa","funders":"Ministère de l’Environnement, de la Protection de la nature et des Parcs; Canadian Institutes of Health Research; University of Waterloo; University of Toronto; University of Ontario Institute of Technology; Trent University; Queen's University; McMaster University; University of Windsor; University of Ottawa","keywords":"Pandemic; Coronavirus disease 2019 (COVID-19); Virology; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); 2019-20 coronavirus outbreak; Titer; Betacoronavirus; Biology; Medicine; Virus; Outbreak; Infectious disease (medical specialty)","score_opus":0.2744851924528665,"score_gpt":0.3861850209734499,"score_spread":0.11169982852058341,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399886311","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":[0.98969835,0.00025719622,0.000106519605,0.0015908795,0.0051211477,0.00040340636,0.0002914968,0.00013824178,0.0023927507],"genre_scores_gemma":[0.9891838,6.898663e-7,0.00014073034,0.007086952,0.00008783189,0.000012343949,0.0005458841,0.000021342212,0.0029204658],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977741,0.00007064916,0.00031235968,0.00075400894,0.0007167723,0.00037207245],"domain_scores_gemma":[0.9984463,0.000086629654,0.000043033288,0.0013128804,0.000043441465,0.00006775763],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018636422,0.0001548525,0.00017051744,0.00015585887,0.0002348102,0.00033993972,0.00061711774,0.000048898302,0.00011942951],"category_scores_gemma":[0.0005038659,0.000104346436,0.00003661254,0.00053782924,0.00018228052,0.00027834103,0.0003305119,0.00039456398,0.00012527966],"study_design_candidate":"not_applicable","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":[0.000044278055,0.000042099393,0.05929903,0.0001124347,0.000078558405,0.0001732929,0.0017038697,0.000004546674,0.5316396,0.000013023725,0.40470308,0.0021862246],"study_design_scores_gemma":[0.0006232976,0.000018974517,0.001239709,0.00012868563,0.00006441214,0.00019891922,0.00020856256,0.001621925,0.058419295,0.000094118055,0.9372159,0.00016620492],"about_ca_topic_score_codex":0.8904419,"about_ca_topic_score_gemma":0.9928361,"teacher_disagreement_score":0.5325128,"about_ca_system_score_codex":0.001178784,"about_ca_system_score_gemma":0.0031343773,"threshold_uncertainty_score":0.5560251},"labels":[],"label_agreement":null},{"id":"W4399920911","doi":"10.1038/s41597-024-03477-9","title":"Spatially distributed atmospheric boundary layer properties in Houston – A value-added observational dataset","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Atmospheric aerosols and clouds","field":"Environmental 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":"McGill University","funders":"Texas Commission on Environmental Quality; U.S. Department of Energy; National Science Foundation","keywords":"Planetary boundary layer; Wind speed; Meteorology; Environmental science; Convective Boundary Layer; Relative humidity; Shortwave; RADIUS; Boundary layer; Atmospheric sciences; Geology; Geography; Computer science; Turbulence; Radiative transfer; Physics; Mechanics","score_opus":0.07452173068592607,"score_gpt":0.28003448562847194,"score_spread":0.20551275494254587,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399920911","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":[0.94218755,0.0009627433,0.005987657,0.0017014752,0.002835396,0.00065542775,0.04421817,0.00023967683,0.0012119199],"genre_scores_gemma":[0.9154368,0.000016460244,0.0078105615,0.00031375675,0.000102803824,0.000038171635,0.07138692,0.000035706245,0.004858798],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974106,0.00006246531,0.00032218962,0.0010949897,0.0006990522,0.00041072804],"domain_scores_gemma":[0.99833876,0.00003152865,0.000049063106,0.0014652747,0.000008661998,0.00010673623],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000918402,0.00018404746,0.000151642,0.0000018874092,0.0002988578,0.0007656308,0.0014299048,0.00006269517,0.0038497138],"category_scores_gemma":[0.00010329765,0.00014776053,0.000029182758,0.0010669072,0.00064738403,0.0011956927,0.0017481667,0.0001827357,0.001424096],"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":[0.00002784089,0.00019283059,0.017729705,0.00004462843,0.000018368302,0.000074198084,0.0002735149,0.0036232392,0.0066004973,0.00015878104,0.95875084,0.012505536],"study_design_scores_gemma":[0.00015578589,0.000024431354,0.04284757,0.000057212663,0.000018054126,0.0000074492127,0.00007565182,0.1744679,0.00014994663,0.00032458777,0.7816114,0.0002600397],"about_ca_topic_score_codex":0.001095603,"about_ca_topic_score_gemma":0.0011104348,"teacher_disagreement_score":0.17713949,"about_ca_system_score_codex":0.00018490451,"about_ca_system_score_gemma":0.0001756815,"threshold_uncertainty_score":0.9993534},"labels":[],"label_agreement":null},{"id":"W4400041829","doi":"10.1038/s41597-024-03557-w","title":"Computed tomography reconstructions of burrow networks for the Opheliid polychaete, Armandia cirrhosa","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Marine Biology and Ecology Research","field":"Earth and Planetary Sciences","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":"Université Laval","funders":"Engineering and Physical Sciences Research Council; Research Councils UK; Natural England","keywords":"Burrow; Polychaete; Intraspecific competition; Ecology; Context (archaeology); Biology; Replicate; Range (aeronautics); Habitat; Ecosystem; Paleontology","score_opus":0.0543216792617203,"score_gpt":0.28617384848020994,"score_spread":0.23185216921848964,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400041829","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":[0.50105596,0.10379114,0.050293565,0.014683987,0.2026931,0.007501182,0.09314312,0.0011101646,0.025727812],"genre_scores_gemma":[0.98976964,0.000065370856,0.00072457583,0.000046014186,0.0002734809,0.000004249975,0.0073146825,0.00000272296,0.0017992822],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989152,0.000059079768,0.0001774848,0.00044722357,0.00010888917,0.0002921133],"domain_scores_gemma":[0.9984003,0.00070301205,0.000033494063,0.0007550679,0.000044717057,0.000063423395],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0016172808,0.00007377092,0.0001047114,0.00015528494,0.0005234297,0.00016286605,0.0010466435,0.00006688432,0.0022722234],"category_scores_gemma":[0.00006995661,0.000046944322,0.00005470492,0.00070221984,0.0008885659,0.0001921907,0.0001324979,0.00016367812,0.000088009954],"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":[0.000074034564,0.000023723162,0.31983852,0.000084900326,0.00022681025,0.0000068089366,0.000080977006,0.00088976434,0.000029680952,0.0007585009,0.41084158,0.26714468],"study_design_scores_gemma":[0.00012322137,0.00006913403,0.25609937,0.000020196232,0.000040702314,0.000035859695,0.00008550838,0.5439486,0.00002050322,0.0011635021,0.19828856,0.00010486705],"about_ca_topic_score_codex":0.00021535321,"about_ca_topic_score_gemma":0.0021642777,"teacher_disagreement_score":0.5430588,"about_ca_system_score_codex":0.0000011228359,"about_ca_system_score_gemma":0.00009245974,"threshold_uncertainty_score":0.9986398},"labels":[],"label_agreement":null},{"id":"W4400229728","doi":"10.1038/s41597-024-03570-z","title":"1 Million Segmented Red Blood Cells With 240 K Classified in 9 Shapes and 47 K Patches of 25 Manual Blood Smears","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Digital Imaging for Blood Diseases","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Spinologics (Canada)","funders":"Zagazig University","keywords":"Blood smear; Segmentation; Artificial intelligence; Computer science; Digital pathology; Microscope; Pathology; Automated method; Pattern recognition (psychology); Medicine","score_opus":0.0270678525659667,"score_gpt":0.2544679995981731,"score_spread":0.22740014703220643,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400229728","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":[0.99131143,0.0015974154,0.0013373962,0.0004751039,0.00081351405,0.0003724544,0.002596025,0.00029480614,0.0012018523],"genre_scores_gemma":[0.9880617,0.000020463614,0.010037347,0.000031880012,0.000018994382,0.000007946967,0.00044538605,0.000017766568,0.0013584928],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99745333,0.00004810556,0.00031380233,0.0012579589,0.00057310855,0.00035371113],"domain_scores_gemma":[0.9981417,0.000085617256,0.00007547452,0.0014926047,0.000062609455,0.00014197324],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006132092,0.00018602423,0.00020312055,0.00041836197,0.00008004972,0.0016074567,0.0018826831,0.00003611068,0.00001156887],"category_scores_gemma":[0.000053960077,0.00015518606,0.000031361236,0.0013610283,0.0004318836,0.0021843556,0.0015159029,0.00010915801,0.000022916027],"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":[0.00025032737,0.010395169,0.046843115,0.0045232126,0.0014875595,0.004144824,0.0085561415,0.0003295753,0.48095122,0.017273214,0.20652549,0.21872015],"study_design_scores_gemma":[0.010253189,0.001461029,0.0727078,0.006750271,0.0016266905,0.00050135836,0.0020431771,0.37625328,0.46657467,0.0126788085,0.04525412,0.003895616],"about_ca_topic_score_codex":0.00004459356,"about_ca_topic_score_gemma":0.00008171034,"teacher_disagreement_score":0.3759237,"about_ca_system_score_codex":0.000010203148,"about_ca_system_score_gemma":0.00018434637,"threshold_uncertainty_score":0.999429},"labels":[],"label_agreement":null},{"id":"W4400229831","doi":"10.1038/s41597-024-03469-9","title":"HVSMR-2.0: A 3D cardiovascular MR dataset for whole-heart segmentation in congenital heart disease","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Congenital Heart Disease Studies","field":"Medicine","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Biomedical Imaging and Bioengineering; National Heart, Lung, and Blood Institute; National Institute on Aging; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Charles H. Hood Foundation; Natural Sciences and Engineering Research Council of Canada; Harvard Catalyst; Philips; National Institutes of Health; U.S. Department of Health and Human Services; National Institute of Neurological Disorders and Stroke; American Heart Association","keywords":"Heart disease; Segmentation; Surgical planning; Magnetic resonance imaging; Medicine; Medical diagnosis; Radiology; Cardiology; Artificial intelligence; Computer science","score_opus":0.058626895430699585,"score_gpt":0.34471851026982797,"score_spread":0.28609161483912837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400229831","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23877265,0.0467645,0.00072036067,0.006312339,0.005586224,0.0051712096,0.69615996,0.00031587505,0.00019688388],"genre_scores_gemma":[0.70401144,0.000022194054,0.0029602323,0.00056241464,0.00050364924,0.00034877378,0.28847235,0.000068303474,0.0030506656],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972707,0.000059654158,0.00032273616,0.0012620651,0.00065841945,0.00042640464],"domain_scores_gemma":[0.9971608,0.000110196226,0.000012909865,0.0023045284,0.00009288163,0.00031866768],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012321754,0.00019624166,0.00033811477,0.00030635495,0.00021033028,0.0003669292,0.0003078167,0.00003808512,0.00013352498],"category_scores_gemma":[0.00038576283,0.00018174973,0.00017414012,0.00066266325,0.00030994564,0.0006867917,0.0005777538,0.00013611886,0.0006999132],"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":[0.00020023299,0.00019145996,0.0023475112,0.00078660727,0.00037173723,0.00019555197,0.00018099631,0.0000042387965,0.0026752963,0.0000130332,0.98159844,0.01143487],"study_design_scores_gemma":[0.0010870394,0.000051133484,0.007930553,0.00020679318,0.00084010407,0.000028961702,0.00029487652,0.009502132,0.00012904771,0.000100111596,0.97959507,0.00023419695],"about_ca_topic_score_codex":0.000056173852,"about_ca_topic_score_gemma":0.000103092374,"teacher_disagreement_score":0.46523878,"about_ca_system_score_codex":0.000092903065,"about_ca_system_score_gemma":0.00044157938,"threshold_uncertainty_score":0.8996202},"labels":[],"label_agreement":null},{"id":"W4400246886","doi":"10.1038/s41597-024-03559-8","title":"Motion-BIDS: an extension to the brain imaging data structure to organize motion data for reproducible research","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":23,"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":"","keywords":"Metadata; Interoperability; Motion (physics); Computer science; Motion capture; Data sharing; Modalities; Software; Information retrieval; Computer vision; World Wide Web; Programming language","score_opus":0.35466429661359333,"score_gpt":0.444939037554456,"score_spread":0.09027474094086269,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400246886","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":[0.04821606,0.0008998138,0.077084355,0.59842515,0.028054861,0.005785075,0.24041103,0.0008892006,0.00023448575],"genre_scores_gemma":[0.9161847,0.000013861842,0.009703917,0.010000616,0.0036375693,0.00008051757,0.04845073,0.000183235,0.011744849],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99023587,0.00045866962,0.00029667327,0.007006263,0.0013738635,0.00062865997],"domain_scores_gemma":[0.9648107,0.0048800386,0.000049058923,0.029599264,0.00044755772,0.00021336185],"candidate_categories":["metaresearch","sts","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.017378386,0.0001949054,0.00016590534,0.0004533652,0.0021823603,0.0027084704,0.009484498,0.000038039205,0.00012411913],"category_scores_gemma":[0.15024757,0.00014494054,0.000016793576,0.0035895708,0.00036087784,0.0035307151,0.018455235,0.00036359255,0.0004844286],"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":[0.000019888681,0.000036726087,0.00001845644,0.000034813307,0.0000050832073,0.0000063537873,0.00030080503,0.00005557569,0.18723872,0.0007274763,0.78868353,0.02287258],"study_design_scores_gemma":[0.000100951904,0.000042593103,0.0005379944,0.00007168304,0.00001793064,0.00003108499,0.0005246833,0.10470587,0.013064207,0.0029777635,0.87771285,0.00021241419],"about_ca_topic_score_codex":0.00013076549,"about_ca_topic_score_gemma":0.0007662943,"teacher_disagreement_score":0.8679686,"about_ca_system_score_codex":0.00009426095,"about_ca_system_score_gemma":0.0002829705,"threshold_uncertainty_score":0.99911666},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"reproducibility","study_design":"not_applicable","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch"],"domain":"reproducibility","study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W4400317002","doi":"10.1038/s41597-024-03585-6","title":"Author Correction: PLAS-20k: Extended Dataset of Protein-Ligand Affinities from MD Simulations for Machine Learning Applications","year":2024,"lang":"en","type":"erratum","venue":"Scientific Data","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Affinities; Binding affinities; Ligand (biochemistry); Computer science; Computational biology; Artificial intelligence; Chemistry; Biology; Stereochemistry; Biochemistry; Receptor","score_opus":0.035606005382448236,"score_gpt":0.3239491444120766,"score_spread":0.2883431390296284,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400317002","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001663232,0.0055849575,0.06727933,0.0002523505,0.030251114,0.002447688,0.89061034,0.000118883785,0.003288983],"genre_scores_gemma":[0.0012915191,0.000046013836,0.006501336,0.000019678375,0.0009675696,0.00012628852,0.7630114,0.000053471107,0.22798273],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975558,0.00006997776,0.0006564376,0.0010441623,0.00038244305,0.0002912136],"domain_scores_gemma":[0.99636817,0.000093574046,0.00051001686,0.0027282822,0.0002109485,0.00008899658],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00074471266,0.00032093315,0.00032294044,0.00020621724,0.0004824552,0.00041162476,0.0015604022,0.00040079196,0.00012623746],"category_scores_gemma":[0.0009951049,0.00031165493,0.0000921304,0.00030854403,0.00034237688,0.000026453632,0.0014479397,0.00068124203,0.00006780475],"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":[0.000026548934,0.000051947707,0.000007308477,0.00036225107,0.00013331862,4.2267624e-7,0.00006808028,0.00040025526,0.004226077,0.00006544673,0.9921429,0.0025154],"study_design_scores_gemma":[0.00016716556,0.00007710013,0.0000043285277,0.00014823583,0.00016448188,0.0000034083912,0.000081532184,0.09556891,0.0019587358,0.00021750032,0.901321,0.0002876089],"about_ca_topic_score_codex":0.00006827178,"about_ca_topic_score_gemma":0.00038655318,"teacher_disagreement_score":0.22469375,"about_ca_system_score_codex":0.00002064301,"about_ca_system_score_gemma":0.00050370564,"threshold_uncertainty_score":0.99993354},"labels":[],"label_agreement":null},{"id":"W4400356338","doi":"10.1038/s41597-024-03532-5","title":"Climate data for building simulations with urban heat island effects and nature-based solutions","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Urban Heat Island Mitigation","field":"Environmental Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"National Research Council Canada","funders":"Alliance de recherche numérique du Canada","keywords":"Urban heat island; Environmental science; Ecology; Computer science; Geography; Meteorology; Biology","score_opus":0.02888947267074084,"score_gpt":0.2857401626545027,"score_spread":0.25685068998376187,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400356338","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":[0.6218824,0.003800364,0.21985655,0.0030634347,0.0051637874,0.004128425,0.14010033,0.00065323676,0.001351518],"genre_scores_gemma":[0.9721074,0.0000037620866,0.009832107,0.00006666297,0.00007225877,0.000016146416,0.01752283,0.000018607217,0.0003602172],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99826324,0.00002986262,0.00012420125,0.0009953597,0.00026126386,0.0003260584],"domain_scores_gemma":[0.99780434,0.00032441667,0.000016417493,0.0017602913,0.000009128058,0.000085375235],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007772389,0.000113048794,0.00008752281,0.00007399566,0.00062804,0.00056410814,0.0007079507,0.000056593723,0.00009290869],"category_scores_gemma":[0.00014537679,0.000088808396,0.000011462478,0.00043052266,0.00031440821,0.0010925212,0.00090185844,0.00012377065,0.000048318114],"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":[0.000043228072,0.00012766,0.017092468,0.00040998688,0.00005225431,0.000014357824,0.00024336598,0.0029591573,0.043667708,0.0016940801,0.92608297,0.0076127746],"study_design_scores_gemma":[0.00037368952,0.000040991406,0.0035904094,0.00013645504,0.00010870076,0.0000057340994,0.000009754509,0.8028611,0.0011279475,0.0004029278,0.19115172,0.00019059358],"about_ca_topic_score_codex":0.000036921403,"about_ca_topic_score_gemma":0.00094453123,"teacher_disagreement_score":0.7999019,"about_ca_system_score_codex":0.000047653124,"about_ca_system_score_gemma":0.00003926892,"threshold_uncertainty_score":0.54397076},"labels":[],"label_agreement":null},{"id":"W4400382322","doi":"10.1038/s41597-024-03577-6","title":"40 years of forest dynamics and tree demography in an intact tropical forest at M’Baïki in central Africa","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"African Botany and Ecology Studies","field":"Agricultural and Biological Sciences","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":"FP7 International Cooperation; Agence Française de Développement; Centre de Coopération Internationale en Recherche Agronomique pour le Développement; Canadian Institute for Advanced Research","keywords":"Diameter at breast height; Geography; Forest dynamics; Forestry; Biomass (ecology); Population; Biodiversity; Tropics; Ecology; Basal area; Forest inventory; Agroforestry; Environmental science; Demography; Forest management; Biology","score_opus":0.032901281414505074,"score_gpt":0.2388499167981641,"score_spread":0.20594863538365904,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400382322","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":[0.99774736,0.0004950805,0.0000017434742,0.00031773854,0.00029555045,0.00010804132,0.0008812651,0.000018938787,0.00013428894],"genre_scores_gemma":[0.99925625,0.0000363552,0.00004644625,0.000007696807,0.000031475924,0.0000042099955,0.00045080046,7.951938e-7,0.00016597149],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9987742,0.000046134377,0.00020483576,0.00052154815,0.00012923095,0.00032408143],"domain_scores_gemma":[0.999608,0.000121375386,0.00002969076,0.00016055694,0.000010670527,0.00006973012],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025213492,0.00008447633,0.00015919661,0.000056564473,0.000102203245,0.00009121597,0.00047934277,0.0000629361,0.000037800783],"category_scores_gemma":[0.00006170795,0.000039584756,0.000028468448,0.00079332123,0.0004520906,0.0002729683,0.00054918317,0.000097363416,0.0000059808963],"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":[0.000025192014,0.00007519881,0.9793656,0.000009733972,0.0000065438026,0.000022813958,0.0002618514,0.0000037154723,0.0007353495,0.00043466396,0.001222785,0.017836588],"study_design_scores_gemma":[0.000072285766,0.00008878209,0.98728126,0.000028242932,0.0000069284774,0.000002047643,0.0006076389,0.007139364,0.000003960443,0.00076899707,0.003918045,0.00008241795],"about_ca_topic_score_codex":0.0001267352,"about_ca_topic_score_gemma":0.3468797,"teacher_disagreement_score":0.34675297,"about_ca_system_score_codex":0.00003790793,"about_ca_system_score_gemma":0.00001027479,"threshold_uncertainty_score":0.66503805},"labels":[],"label_agreement":null},{"id":"W4400535776","doi":"10.1038/s41597-024-03436-4","title":"The Canadian Fire Spread Dataset","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Fire effects on ecosystems","field":"Environmental Science","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Natural Resources Canada; Canadian Forest Service","funders":"Canadian Forest Service; U.S. Forest Service; Government of Alberta; Rocky Mountain Research Station; U.S. Department of Agriculture","keywords":"Visible Infrared Imaging Radiometer Suite; Moderate-resolution imaging spectroradiometer; Environmental science; Remote sensing; Kriging; Radiometer; Meteorology; Fire detection; Fire regime; Range (aeronautics); Suite; Satellite; Computer science; Geography; Machine learning; Ecology","score_opus":0.02323385016940095,"score_gpt":0.2577663515867854,"score_spread":0.23453250141738446,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400535776","genre_codex":"dataset","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":[0.10715522,0.0066466946,0.00017109563,0.03225031,0.0791074,0.0034199494,0.6652871,0.00090712047,0.105055116],"genre_scores_gemma":[0.94657713,0.000009207845,0.00012649689,0.00018603526,0.00014146029,0.000017649221,0.036744602,0.000024592153,0.01617283],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.998179,0.000059713966,0.00013416105,0.0007642321,0.0004406067,0.00042229408],"domain_scores_gemma":[0.996606,0.00011944599,0.000017761009,0.0030333754,0.000003072437,0.00022035014],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0024342376,0.000094193565,0.000057188885,0.000030696676,0.0011289376,0.0020493178,0.0026262875,0.000035001718,0.0017233185],"category_scores_gemma":[0.00013597126,0.00006199639,0.000015051215,0.0005553687,0.00048695403,0.0006883673,0.0011003633,0.00013065447,0.028867416],"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":[3.9779758e-7,0.0000032018381,0.00022043732,0.0000062028003,0.000004294851,0.000028047307,0.00003491992,0.0000036523852,0.00011889378,0.000083589315,0.9492567,0.050239667],"study_design_scores_gemma":[0.000017618391,0.0000041637245,0.0010936857,0.000016850317,0.0000061606956,0.000011986274,0.0000123893715,0.06428938,0.000036577407,0.000076071,0.9343512,0.000083888124],"about_ca_topic_score_codex":0.24096741,"about_ca_topic_score_gemma":0.88362396,"teacher_disagreement_score":0.8394219,"about_ca_system_score_codex":0.00022453102,"about_ca_system_score_gemma":0.00012672575,"threshold_uncertainty_score":0.99918926},"labels":[],"label_agreement":null},{"id":"W4401114855","doi":"10.1038/s41597-024-03639-9","title":"Mapping global land conversion pressure to support conservation planning","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Conservation, Biodiversity, and Resource Management","field":"Environmental Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Land cover; Environmental resource management; Scale (ratio); Climate change; Land use; Environmental science; Land use, land-use change and forestry; Biodiversity; Geography; Ecology; Cartography","score_opus":0.05460364334583896,"score_gpt":0.2708934861808216,"score_spread":0.21628984283498265,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401114855","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":[0.96121985,0.00019542334,0.0049203,0.0063079474,0.0037172602,0.0006259378,0.0035556664,0.0002857091,0.019171894],"genre_scores_gemma":[0.94839406,0.0000048051556,0.001671784,0.0014342044,0.00010439434,0.0000049626037,0.0042391256,0.000009600314,0.044137068],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985892,0.000024924753,0.00012239134,0.000651569,0.00041161283,0.00020026143],"domain_scores_gemma":[0.9991917,0.000018233386,0.000024994642,0.0006609612,0.0000093455255,0.00009473736],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00076560886,0.00008387464,0.00006376792,0.000058526788,0.00036678568,0.0004828422,0.0007448982,0.000031074902,0.0018605699],"category_scores_gemma":[0.000036274272,0.00007668946,0.000018909119,0.00064708304,0.00014290125,0.00041486384,0.0019594005,0.000048717135,0.0024553295],"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":[0.000004534468,0.00001171985,0.45609397,0.000035798563,0.000012950948,0.000016286243,0.0005318893,0.00021857132,0.0002845389,0.000006849614,0.5395443,0.0032386142],"study_design_scores_gemma":[0.00006736178,0.000010115307,0.20415726,0.000028036848,0.000017877333,0.0000021175658,0.00027951517,0.010360353,0.000025453266,0.000034015702,0.7849303,0.00008762575],"about_ca_topic_score_codex":0.00042809386,"about_ca_topic_score_gemma":0.00012758172,"teacher_disagreement_score":0.2519367,"about_ca_system_score_codex":0.00007134936,"about_ca_system_score_gemma":0.000023348064,"threshold_uncertainty_score":0.99905187},"labels":[],"label_agreement":null},{"id":"W4401283762","doi":"10.1038/s41597-024-03685-3","title":"A Global Dataset of Potential Chloride Deposits on Mars as Identified by TGO CaSSIS","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Planetary Science and Exploration","field":"Physics and Astronomy","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Space Agency; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; University of Bern; National Aeronautics and Space Administration","keywords":"Hesperian; Mars Exploration Program; Geology; Noachian; Geochemistry; Astrobiology; Chloride; Martian; Earth science; Chemistry","score_opus":0.025226119467857896,"score_gpt":0.2861489688470883,"score_spread":0.2609228493792304,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401283762","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":[0.57362264,0.00014526486,0.0039556487,0.00041538433,0.005066707,0.00023180502,0.4151471,0.00005006949,0.00136538],"genre_scores_gemma":[0.71271354,0.0000013701332,0.00007635116,0.00002221345,0.00008703626,0.0000022776505,0.2864044,0.0000035581966,0.0006892488],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983442,0.000025399782,0.00023280412,0.0007062438,0.0004580355,0.00023333376],"domain_scores_gemma":[0.99869215,0.000018539382,0.000059060992,0.0011156558,0.00002385872,0.00009074285],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00049059495,0.000111877715,0.00010927387,0.00007142414,0.00018354318,0.00073291804,0.0010072475,0.000021978552,0.00027894712],"category_scores_gemma":[0.000010110966,0.000097918724,0.00003245578,0.0005841767,0.0001354969,0.0012794713,0.0003074351,0.00006597945,0.001821064],"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":[0.000019784358,0.00006426912,0.00058809423,0.000013276776,0.00003856757,0.000015494534,0.000034970883,0.00006806352,0.0063611167,0.000941689,0.98333347,0.00852121],"study_design_scores_gemma":[0.0007826258,0.00018397276,0.0035165027,0.00029402244,0.0003562708,0.00003025621,0.00094212516,0.052555356,0.04738894,0.010441241,0.882508,0.0010007047],"about_ca_topic_score_codex":0.0007146539,"about_ca_topic_score_gemma":0.0001347343,"teacher_disagreement_score":0.13909091,"about_ca_system_score_codex":0.000014076965,"about_ca_system_score_gemma":0.0001230743,"threshold_uncertainty_score":0.99895614},"labels":[],"label_agreement":null},{"id":"W4401333304","doi":"10.1038/s41597-024-03499-3","title":"Nine months of daily LiDAR, orthophotos and MetOcean data from the eroding soft cliff coast at Happisburgh, UK","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Coastal and Marine Dynamics","field":"Earth and Planetary Sciences","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":"Tellabs (Canada)","funders":"Engineering and Physical Sciences Research Council; Natural Environment Research Council; Research Councils UK; Sight Research UK","keywords":"Lidar; Shore; Transect; Cliff; Geology; Orthophoto; Subaerial; Submarine pipeline; Oceanography; Environmental science; Remote sensing","score_opus":0.041130662941605535,"score_gpt":0.24798656887872955,"score_spread":0.20685590593712402,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401333304","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":[0.7923156,0.0050975927,0.0004770747,0.0008084897,0.0036847044,0.00040287976,0.1941679,0.00009192286,0.0029538532],"genre_scores_gemma":[0.9069324,0.00015320383,0.0006617001,0.00007530183,0.00014890019,5.3798647e-7,0.08482396,0.0000072727526,0.0071967035],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978721,0.000056052853,0.00030085474,0.0010410518,0.0004436079,0.00028630812],"domain_scores_gemma":[0.99667776,0.0004531242,0.000076056815,0.0026335625,0.00003278808,0.00012671476],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001597166,0.00015785421,0.00018938836,0.000073381816,0.00038503014,0.00063756487,0.0022433877,0.00004088439,0.0025455242],"category_scores_gemma":[0.00023863594,0.00010124881,0.000029135255,0.00048744588,0.00049221725,0.00065537647,0.0027578373,0.00016253856,0.00013648279],"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":[0.000075674434,0.000026803142,0.24207906,0.000084754436,0.00010957031,0.00005620965,0.00071482273,0.00006884047,0.00089984346,0.000053047843,0.43987998,0.31595138],"study_design_scores_gemma":[0.0002253019,0.000036183163,0.1034146,0.000110896755,0.00012575238,0.000020815956,0.0004447492,0.40426627,0.00005091705,0.00070629764,0.49033526,0.00026296123],"about_ca_topic_score_codex":0.010981364,"about_ca_topic_score_gemma":0.12532574,"teacher_disagreement_score":0.40419742,"about_ca_system_score_codex":0.0000031042212,"about_ca_system_score_gemma":0.00010834326,"threshold_uncertainty_score":0.9983663},"labels":[],"label_agreement":null},{"id":"W4401419620","doi":"10.1038/s41597-024-03691-5","title":"Where should we go - Estimating travel times for modelling accessibility to 24-hour emergency departments in Canada","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Urban Transport and Accessibility","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Carleton University","funders":"Government of Ontario","keywords":"Census; Travel time; Population; Geography; Service (business); Transport engineering; Subdivision; Health care; Business; Computer science; Medicine; Environmental health; Marketing; Engineering; Economic growth","score_opus":0.15627696841106278,"score_gpt":0.38433990418241,"score_spread":0.2280629357713472,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401419620","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":[0.8232449,0.004727041,0.11235506,0.0058717798,0.027665054,0.0032616598,0.01731092,0.00028435513,0.005279228],"genre_scores_gemma":[0.98231465,0.000021377062,0.010343936,0.000028060162,0.00021970856,0.00004800001,0.00086207374,0.000019075544,0.006143127],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968081,0.00006710821,0.00053169054,0.0012792457,0.00069735193,0.000616504],"domain_scores_gemma":[0.99850476,0.000102256796,0.000060150785,0.001014062,0.000082977655,0.00023578486],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027817015,0.00016242982,0.00021191116,0.00010814127,0.000670016,0.0005550106,0.0018392815,0.00006009063,0.0007062476],"category_scores_gemma":[0.00016818201,0.00015039208,0.000051649404,0.0010850723,0.000120474106,0.0013146878,0.00021138908,0.00015759023,0.000028244032],"study_design_candidate":"not_applicable","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":[0.00006277297,0.0003160847,0.19689314,0.0015679364,0.000078046076,0.00004860724,0.014203442,0.00801559,0.00024305112,0.0013092235,0.72290117,0.05436095],"study_design_scores_gemma":[0.00029516866,0.000014481687,0.007599474,0.0003626922,0.000072783965,1.8006484e-7,0.0034978073,0.79493177,0.00017227561,0.013174318,0.17920858,0.0006704884],"about_ca_topic_score_codex":0.5897595,"about_ca_topic_score_gemma":0.9899219,"teacher_disagreement_score":0.78691614,"about_ca_system_score_codex":0.00049850176,"about_ca_system_score_gemma":0.0031678295,"threshold_uncertainty_score":0.7732915},"labels":[],"label_agreement":null},{"id":"W4401455833","doi":"10.1038/s41597-024-03695-1","title":"MSPB: a longitudinal multi-sensor dataset with phenotypic trait measurements from honey bees","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Insect and Arachnid Ecology and Behavior","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université Laval; Institut National de la Recherche Scientifique; Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Varroa destructor; Biology; Apiary; Honey bee; Beehive; Population; Zoology; Ecology; Demography","score_opus":0.10953250777004635,"score_gpt":0.3222916178320017,"score_spread":0.21275911006195536,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401455833","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":[0.912676,0.0010562416,0.0016345683,0.00013878268,0.0017639827,0.00023561541,0.08237851,0.000043660322,0.00007263805],"genre_scores_gemma":[0.8176284,0.0000060495627,0.002866802,0.00007863981,0.00022553015,0.000013733264,0.17723931,0.000018225035,0.0019233178],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99832875,0.00004029084,0.00015272104,0.0009950651,0.00019787079,0.00028529225],"domain_scores_gemma":[0.99859196,0.000008226544,0.000032664128,0.0012456902,0.000040695093,0.00008077534],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004211127,0.00015753748,0.00011514133,0.000054300537,0.0002651086,0.00025569368,0.0007599489,0.00009830075,0.00032677822],"category_scores_gemma":[0.00003406075,0.00012152707,0.000030574993,0.00014794777,0.00027151796,0.00002869313,0.00037630828,0.00011558286,0.00021812184],"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":[0.00008607437,0.00021621078,0.007786467,0.000022259115,0.00012560558,0.00004793607,0.000049869686,0.0000034383677,0.7868192,0.0000073417923,0.20185067,0.0029849184],"study_design_scores_gemma":[0.0020300571,0.00041124175,0.06601038,0.0001579264,0.0006156089,0.000077860364,0.00020217738,0.0009346211,0.36710036,0.000047934867,0.56131834,0.0010934825],"about_ca_topic_score_codex":0.000075553406,"about_ca_topic_score_gemma":0.0014879628,"teacher_disagreement_score":0.41971886,"about_ca_system_score_codex":0.000008262432,"about_ca_system_score_gemma":0.0001270408,"threshold_uncertainty_score":0.495573},"labels":[],"label_agreement":null},{"id":"W4401591794","doi":"10.1038/s41597-024-03683-5","title":"The NACOB multi-surface walking dataset","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Gait Recognition and Analysis","field":"Engineering","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":"Institut national de psychiatrie légale Philippe-Pinel; Université de Montréal; Centre Hospitalier Universitaire Sainte-Justine; McGill University","funders":"Fonds de Recherche du Québec - Santé; Canada First Research Excellence Fund; Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Computer science; Information retrieval; Environmental science","score_opus":0.06017147036614638,"score_gpt":0.29959759865658775,"score_spread":0.23942612829044135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401591794","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.061531484,0.055414353,0.1177973,0.0040493812,0.06867416,0.0011686858,0.66611713,0.0068645026,0.018383032],"genre_scores_gemma":[0.7592549,0.0005544433,0.007332694,0.000116857256,0.00034616925,0.000010238726,0.20877543,0.0000884745,0.023520814],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991756,0.000017967788,0.0001226714,0.0003236425,0.00017528347,0.00018483785],"domain_scores_gemma":[0.9987061,0.000061888335,0.0000068173845,0.0011611471,0.000014434312,0.000049637194],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008636766,0.00007227664,0.0000539496,0.000046092413,0.00026918892,0.0013477767,0.00083233166,0.000018904486,0.00025808942],"category_scores_gemma":[0.000048257272,0.00004968208,0.000023417373,0.00054338016,0.00008385552,0.0003377054,0.00026053,0.0001098189,0.0022171787],"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":[1.9152274e-7,0.000004856408,0.0000051436427,0.000025925629,0.000041237075,0.000007037656,0.000044178785,0.00038199822,0.0029135814,0.000051954878,0.9454807,0.05104321],"study_design_scores_gemma":[0.000020469404,3.6964659e-7,0.000017074211,0.000015651789,0.000016724734,0.0000016263956,0.000061452774,0.36163905,0.00030060057,0.000030568313,0.6378461,0.000050276973],"about_ca_topic_score_codex":0.00000725389,"about_ca_topic_score_gemma":0.00013499518,"teacher_disagreement_score":0.6977234,"about_ca_system_score_codex":0.000013322119,"about_ca_system_score_gemma":0.000015360194,"threshold_uncertainty_score":0.9996889},"labels":[],"label_agreement":null},{"id":"W4401659238","doi":"10.1038/s41597-024-03679-1","title":"EDARA: An ERA5-based Dataset for Atmospheric River Analysis","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Climate variability and models","field":"Environmental Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Environment and Climate Change Canada","funders":"","keywords":"Precipitation; Environmental science; Troposphere; Flooding (psychology); Climatology; Range (aeronautics); Resource (disambiguation); Meteorology; Geography; Computer science; Geology","score_opus":0.0662248988126431,"score_gpt":0.32506288077919315,"score_spread":0.25883798196655006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401659238","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22831091,0.00016265191,0.2252282,0.0012236043,0.0028942823,0.0010238221,0.53991747,0.0002844138,0.0009546481],"genre_scores_gemma":[0.51093537,0.000005010097,0.06503755,0.00044683734,0.000100750854,0.0000548039,0.42084137,0.000031709686,0.0025466306],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99777776,0.000045606703,0.0001956123,0.0013279644,0.00034764543,0.00030543943],"domain_scores_gemma":[0.9968792,0.00009978017,0.000028744755,0.002847795,0.000007798769,0.00013663503],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0018447916,0.000118257834,0.00013801598,0.000029122546,0.00029838382,0.00057488837,0.0013992764,0.000043382177,0.0051866104],"category_scores_gemma":[0.00007000708,0.000101572405,0.00006613373,0.0014374169,0.0005014326,0.0011232774,0.0007150331,0.00006690875,0.000850075],"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":[0.000025345493,0.00031442646,0.0021983448,0.000066712026,0.00012833536,0.000009474221,0.00028156882,0.03071293,0.0026713908,0.00029159588,0.9492132,0.014086661],"study_design_scores_gemma":[0.00006294551,0.000012552738,0.0006816012,0.0000031818838,0.00019802299,2.9036744e-7,0.000012723129,0.5881727,0.000040395626,0.00058378774,0.41013303,0.000098826924],"about_ca_topic_score_codex":0.0004191293,"about_ca_topic_score_gemma":0.001147438,"teacher_disagreement_score":0.5574597,"about_ca_system_score_codex":0.0000736687,"about_ca_system_score_gemma":0.00004575973,"threshold_uncertainty_score":0.9999279},"labels":[],"label_agreement":null},{"id":"W4401666731","doi":"10.1038/s41597-024-03722-1","title":"ANPHY-Sleep: an Open Sleep Database from Healthy Adults Using High-Density Scalp Electroencephalogram","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Sleep and Wakefulness Research","field":"Neuroscience","cited_by":14,"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 Health Centre; McGill University; Montreal Neurological Institute and Hospital","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Montreal Neurological Institute and Hospital","keywords":"Sleep (system call); Scalp; Electroencephalography; Database; Audiology; Medicine; Psychology; Computer science; Neuroscience; Dermatology","score_opus":0.17170178281590792,"score_gpt":0.4042917301922292,"score_spread":0.23258994737632127,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401666731","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":[0.9674229,0.00036410202,0.0045705116,0.00087680045,0.005286399,0.0009557632,0.020019991,0.00033360068,0.00016991992],"genre_scores_gemma":[0.98727655,0.000028990924,0.0025803319,0.00041168163,0.0003999289,0.000024338779,0.008933995,0.000053375774,0.00029078638],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9926895,0.00059251906,0.000436799,0.0036998834,0.0014154589,0.0011658283],"domain_scores_gemma":[0.99349266,0.0003422099,0.00008453277,0.005368997,0.00011666368,0.0005949569],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0023846128,0.00029975164,0.00032444787,0.0003939374,0.0013411599,0.005671601,0.0078065563,0.00009864436,0.0006230308],"category_scores_gemma":[0.00097027817,0.00026816412,0.000043091404,0.0025916644,0.00081697886,0.005126304,0.00612766,0.00061876106,0.0006319631],"study_design_candidate":"simulation_or_modeling","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":[0.0012752117,0.0016053654,0.00073908374,0.00021464759,0.000060460232,0.0013217285,0.0007350605,0.00007182046,0.64152634,0.0041323192,0.06902561,0.27929237],"study_design_scores_gemma":[0.0014227425,0.00050176686,0.0013105806,0.00031337238,0.00008787067,0.00008265514,0.00025612427,0.7996694,0.1358882,0.0031347107,0.05639425,0.00093831413],"about_ca_topic_score_codex":0.009108881,"about_ca_topic_score_gemma":0.002821007,"teacher_disagreement_score":0.79959756,"about_ca_system_score_codex":0.00013699148,"about_ca_system_score_gemma":0.00045524916,"threshold_uncertainty_score":0.99997705},"labels":[],"label_agreement":null},{"id":"W4401915925","doi":"10.1038/s41597-024-03611-7","title":"A dataset of acoustic measurements from soundscapes collected worldwide during the COVID-19 pandemic","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Noise Effects and Management","field":"Health Professions","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":"The Scarborough Hospital; University of Toronto; Parks Canada; Université du Québec à Trois-Rivières; Environment and Climate Change Canada; Carleton University; University of Alberta","funders":"Leverhulme Trust","keywords":"Soundscape; Metadata; Pandemic; Data science; Data collection; Usability; Computer science; Coronavirus disease 2019 (COVID-19); Geography; Sound (geography); World Wide Web; Human–computer interaction; Oceanography; Sociology; Geology; Social science","score_opus":0.26853938945134587,"score_gpt":0.4603518546268951,"score_spread":0.19181246517554923,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401915925","genre_codex":"dataset","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":[0.4608805,0.004816083,0.00769049,0.004509007,0.02451884,0.006417089,0.4881869,0.00076195464,0.0022191536],"genre_scores_gemma":[0.8971501,0.00005946727,0.00039851276,0.0014059853,0.00041941585,0.00019465091,0.07788722,0.00004831619,0.022436304],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99713224,0.0005114741,0.0004896483,0.0007986508,0.0006468572,0.00042110903],"domain_scores_gemma":[0.99615115,0.0009854767,0.00014525937,0.002502493,0.000059757305,0.00015584438],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004357494,0.00014111385,0.00019365693,0.00019805515,0.0014169951,0.00018582963,0.001604086,0.000052616273,0.0017871419],"category_scores_gemma":[0.0013045256,0.0000907383,0.000029192848,0.0009470291,0.00020139398,0.0002831726,0.0019411442,0.00031910918,0.00055736495],"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":[0.00003324445,0.000033105884,0.0038492277,0.0007024565,0.000117076546,0.000010774052,0.00092750107,0.000042562402,0.017420257,0.000031129104,0.97649556,0.00033707827],"study_design_scores_gemma":[0.0005806011,0.000009314839,0.004970059,0.00032791644,0.00019879742,0.0000010774924,0.000914747,0.0022985577,0.000049094248,0.00049631885,0.99000746,0.00014606515],"about_ca_topic_score_codex":0.0012079173,"about_ca_topic_score_gemma":0.009307067,"teacher_disagreement_score":0.43626964,"about_ca_system_score_codex":0.0002022592,"about_ca_system_score_gemma":0.00068486255,"threshold_uncertainty_score":0.999883},"labels":[],"label_agreement":null},{"id":"W4402078561","doi":"10.1038/s41597-024-03771-6","title":"A synthetic vulnerable population dataset for fine scale geographical equity analysis and urban planning","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Health disparities and outcomes","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université de Sherbrooke; Transport Canada","funders":"","keywords":"Comparability; Equity (law); Vulnerability (computing); Scale (ratio); Population; Social equality; Environmental resource management; Context (archaeology); Risk analysis (engineering); Public economics; Environmental planning; Data science; Business; Computer science; Geography; Economics; Political science; Sociology","score_opus":0.0990967556283731,"score_gpt":0.4382109512222689,"score_spread":0.3391141955938958,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402078561","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":[0.45457616,0.01142343,0.025105255,0.04169988,0.011804107,0.0024908113,0.44975317,0.00062203,0.002525177],"genre_scores_gemma":[0.9387656,0.000022434326,0.0012537057,0.00018902853,0.00021852514,0.000017475946,0.057841375,0.000007645434,0.0016841947],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983063,0.00010885675,0.0001972159,0.00063769903,0.00035219133,0.00039773507],"domain_scores_gemma":[0.9987149,0.00037123414,0.000030989257,0.0006788168,0.000026404405,0.00017764488],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0052046785,0.00006996305,0.00015474988,0.0002595972,0.0015415133,0.001262784,0.00052829256,0.00005461427,0.0001665673],"category_scores_gemma":[0.0005612673,0.00006180484,0.000041967967,0.0011884008,0.00028126032,0.00056412927,0.00038328138,0.00010093438,0.000009450885],"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":[0.000014774415,0.000050374525,0.2015014,0.00044899844,0.00013642985,0.000005181414,0.0023539695,0.0000331612,0.000009807189,0.013910529,0.7614507,0.020084687],"study_design_scores_gemma":[0.0000769854,0.0000068893632,0.040938105,0.00007616117,0.0002896397,4.6915954e-7,0.00057820184,0.02113588,0.000003375841,0.0019839425,0.93477,0.00014035423],"about_ca_topic_score_codex":0.0052008536,"about_ca_topic_score_gemma":0.014797137,"teacher_disagreement_score":0.48418945,"about_ca_system_score_codex":0.000029083249,"about_ca_system_score_gemma":0.00010578713,"threshold_uncertainty_score":0.999774},"labels":[],"label_agreement":null},{"id":"W4402118623","doi":"10.1038/s41597-024-03785-0","title":"A comprehensive dataset for digital restoration of Dunhuang murals","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"3D Surveying and Cultural Heritage","field":"Earth and Planetary Sciences","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":"University of British Columbia","funders":"National Natural Science Foundation of China","keywords":"Mural; Computer science; Cultural heritage; Inpainting; Segmentation; Safeguarding; Digital preservation; Digital image; Resource (disambiguation); Artificial intelligence; Visual arts; Image processing; World Wide Web; Archaeology; Image (mathematics); History; Art","score_opus":0.15001813008581763,"score_gpt":0.32049508902344986,"score_spread":0.17047695893763223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402118623","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16201444,0.0026708855,0.00050254824,0.00021594783,0.0031263528,0.00030946065,0.83022577,0.00006723453,0.00086734333],"genre_scores_gemma":[0.6172197,0.000004474833,0.00051097915,0.000014870516,0.00005382812,5.082681e-7,0.38090262,0.0000016801034,0.0012913824],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.999104,0.000022757615,0.00015269825,0.00038791675,0.00019132445,0.00014126093],"domain_scores_gemma":[0.9991215,0.00015195222,0.00002892291,0.0006048681,0.000045001663,0.000047748857],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044542333,0.00006350234,0.00008435052,0.000048572532,0.00014141398,0.0006693392,0.0005069773,0.00002203849,0.00029212044],"category_scores_gemma":[0.00008817792,0.00004584117,0.00002149603,0.00026976914,0.00013940137,0.0011983011,0.00004971722,0.000039988077,0.00028256842],"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":[0.000015940204,0.000008186085,0.0020285859,0.00014720618,0.000015650752,0.00000535588,0.00013925551,0.000056374138,0.00056292786,0.00005077451,0.9283343,0.06863544],"study_design_scores_gemma":[0.0000676423,0.000035187466,0.0062443884,0.000050357095,0.000010415283,0.0000051385205,0.00024092314,0.0258157,0.000093627525,0.0003705159,0.9669692,0.000096928416],"about_ca_topic_score_codex":0.00014093074,"about_ca_topic_score_gemma":0.0005067047,"teacher_disagreement_score":0.4552052,"about_ca_system_score_codex":0.0000014195812,"about_ca_system_score_gemma":0.000045044697,"threshold_uncertainty_score":0.64544535},"labels":[],"label_agreement":null},{"id":"W4402207096","doi":"10.1038/s41597-024-03805-z","title":"Effects of changing farming practices in African agriculture","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Agricultural Innovations and Practices","field":"Agricultural and Biological Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Environment and Climate Change Canada; Ouranos","funders":"Foreign Agricultural Service; International Fund for Agricultural Development; European Commission; Consortium of International Agricultural Research Centers; U.S. Department of Agriculture","keywords":"Agriculture; Sustainability; Productivity; Psychological resilience; Business; Resilience (materials science); Natural resource economics; Psychological intervention; Livestock; Environmental resource management; Agricultural productivity; Environmental planning; Geography; Economic growth; Economics; Ecology","score_opus":0.07111008588108822,"score_gpt":0.3088407884436994,"score_spread":0.23773070256261117,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402207096","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":[0.9907128,0.002610197,0.0000074567884,0.0028471882,0.0010795292,0.00027668898,0.00047083962,0.00008138034,0.0019139053],"genre_scores_gemma":[0.9962105,0.0000415551,0.00020208924,0.000024874775,0.00019002895,0.000009405236,0.0011857958,5.988878e-7,0.002135121],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986844,0.00006921975,0.00021689277,0.00053363485,0.00025523282,0.00024058664],"domain_scores_gemma":[0.9989255,0.00063683116,0.00019693887,0.00014615706,0.000065119035,0.000029427481],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011089629,0.000099996076,0.000117018826,0.00006253945,0.00018925358,0.0005224639,0.00074956496,0.00005219909,0.00014433645],"category_scores_gemma":[0.00044723813,0.000031521726,0.000028399383,0.0034486654,0.00007091362,0.001420877,0.0003976687,0.00015609311,0.000039958908],"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":[0.000006187712,0.00010492013,0.00031535843,0.00013661946,0.00001918791,0.00002839176,0.0005835812,0.0000022052686,0.85037714,0.0021837482,0.022404091,0.12383855],"study_design_scores_gemma":[0.00006718428,0.000059323032,0.022119954,0.00035178775,0.000046493493,0.000019106557,0.0048661567,0.0009071547,0.021730592,0.000495923,0.94905686,0.00027948487],"about_ca_topic_score_codex":0.00027927262,"about_ca_topic_score_gemma":0.00082087284,"teacher_disagreement_score":0.9266527,"about_ca_system_score_codex":0.000014672978,"about_ca_system_score_gemma":0.000012824641,"threshold_uncertainty_score":0.50381315},"labels":[],"label_agreement":null},{"id":"W4402644711","doi":"10.1038/s41597-024-03869-x","title":"High-throughput drug screening identifies novel therapeutics for Low Grade Serous Ovarian Carcinoma","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Ovarian cancer diagnosis and treatment","field":"Medicine","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; BC Cancer Agency","funders":"Therapeutic Innovation Australia; BC Cancer Foundation; Medical Research Future Fund; Australian Cancer Research Foundation; Australian Government; Ovarian Cancer Canada; Marshfield Clinic Research Foundation; Cancer Research Society; Peter MacCallum Cancer Centre; Victorian Cancer Agency","keywords":"Serous fluid; Ovarian cancer; Serous carcinoma; Ovarian carcinoma; Oncology; Clear cell; Ovary; Clear cell carcinoma; Internal medicine; Medicine; Cancer research; Drug; Cancer; Carcinoma; Pharmacology","score_opus":0.11066439839271523,"score_gpt":0.34568069755072056,"score_spread":0.23501629915800532,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402644711","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":[0.4944007,0.03640459,0.18752372,0.101576164,0.07252186,0.009694164,0.09450474,0.0020651866,0.0013088733],"genre_scores_gemma":[0.95577633,0.00005407144,0.022542847,0.00047220144,0.0007743886,0.000103701714,0.0103906635,0.00007208019,0.009813705],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973317,0.000021149373,0.00035163836,0.0013275413,0.000503687,0.0004642828],"domain_scores_gemma":[0.9973109,0.00015800745,0.00006363209,0.0022049272,0.0001135429,0.0001489996],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00085944525,0.00024284859,0.00031498182,0.00020041464,0.0003780436,0.0010445362,0.00061146764,0.00006845913,0.00013444095],"category_scores_gemma":[0.00004061652,0.00019607475,0.00012227678,0.00057687366,0.00022621786,0.00050178805,0.00037472585,0.00016010564,0.000112874965],"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":[0.00021397247,0.0017349978,0.0033407928,0.0018777245,0.0020100346,0.00039747803,0.0030510486,0.000056859768,0.015901089,0.015211971,0.8574594,0.09874461],"study_design_scores_gemma":[0.00502121,0.0002057322,0.019354254,0.0012968442,0.0021404072,0.00014815769,0.0007533636,0.023667088,0.027448874,0.0020161942,0.91726077,0.0006871185],"about_ca_topic_score_codex":0.0003706159,"about_ca_topic_score_gemma":0.00022089352,"teacher_disagreement_score":0.46137565,"about_ca_system_score_codex":0.00011046932,"about_ca_system_score_gemma":0.00033287783,"threshold_uncertainty_score":0.9999925},"labels":[],"label_agreement":null},{"id":"W4402645290","doi":"10.1038/s41597-024-03871-3","title":"A global dataset of gross nitrogen transformation rates across terrestrial ecosystems","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Soil Carbon and Nitrogen Dynamics","field":"Agricultural and Biological 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":"University of Waterloo","funders":"National Research Foundation of Korea; Yonsei University; National Science Foundation","keywords":"Ecosystem; Environmental science; Transformation (genetics); Terrestrial ecosystem; Nitrogen; Nitrogen cycle; Ecology; Biology; Chemistry","score_opus":0.05211844908467723,"score_gpt":0.31494454221743395,"score_spread":0.26282609313275673,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402645290","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":[0.76402795,0.00029455335,0.000015495263,0.00013879724,0.0014893637,0.00014346672,0.23375082,0.00005409288,0.00008545967],"genre_scores_gemma":[0.8702817,0.000008256924,0.00002873239,0.000013680073,0.00017087652,0.000004265127,0.1294648,6.2890257e-7,0.000027038705],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985384,0.00005653657,0.00032373003,0.00048205737,0.0003360457,0.00026326824],"domain_scores_gemma":[0.9994654,0.00006239609,0.000055996235,0.00030999666,0.000027865943,0.00007836718],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011700175,0.000106859654,0.00013520704,0.000010634259,0.0001837342,0.00066197943,0.0010220765,0.00006287328,0.0001017531],"category_scores_gemma":[0.0000458606,0.000042929918,0.000056768276,0.0007890918,0.00015112301,0.0006098831,0.00026812078,0.000054375807,0.00008817292],"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":[0.00031826386,0.00043883437,0.022322051,0.0003731594,0.0002671368,0.000062547195,0.0011083867,0.000029727602,0.11862593,0.0024566595,0.49140176,0.36259556],"study_design_scores_gemma":[0.0005167698,0.00016895906,0.005588242,0.00016063591,0.0000890588,0.00007968165,0.001670582,0.18900362,0.0061290916,0.003197475,0.7928475,0.0005483953],"about_ca_topic_score_codex":0.0009175381,"about_ca_topic_score_gemma":0.011875123,"teacher_disagreement_score":0.36204717,"about_ca_system_score_codex":0.00002465988,"about_ca_system_score_gemma":0.000029019275,"threshold_uncertainty_score":0.6626597},"labels":[],"label_agreement":null},{"id":"W4403036292","doi":"10.1038/s41597-024-03865-1","title":"The International Climate Psychology Collaboration: Climate change-related data collected from 63 countries","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Climate Change Communication and Perception","field":"Social Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kellogg's (Canada); Simon Fraser University; University of British Columbia","funders":"Fondo de Financiamiento de Centros de Investigación en Áreas Prioritarias; Japan Society for the Promotion of Science; Biotechnology and Biological Sciences Research Council; Fundação para a Ciência e a Tecnologia; Uniwersytet Śląski w Katowicach; Shell Brasil; NOMIS Stiftung; Université de Lausanne; Centro de Estudios de Conflicto y Cohesión Social; Agencia Nacional de Investigación y Desarrollo; Erasmus Universiteit Rotterdam; Université de Genève; Austrian Science Fund; Stanford Center on Philanthropy and Civil Society; Thammasat University; Universität Hamburg; Norges Forskningsråd; Agentúra na Podporu Výskumu a Vývoja; Morsani College of Medicine; Simon Fraser University; Medical Research Council; National Research Foundation of Korea; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Riksbankens Jubileumsfond; Fonds Wetenschappelijk Onderzoek; Universitat Ramon Llull; National Research University Higher School of Economics; National Geographic Society; American University of Sharjah; Universität Wien; James S. McDonnell Foundation; Aarhus Universitets Forskningsfond; Agence Nationale de la Recherche; Fonds De La Recherche Scientifique - FNRS; Canada Research Chairs; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Research Foundation; Fundação de Amparo à Pesquisa do Estado de São Paulo; Jacobs Foundation; Pomona College; Wellcome Trust; Social Sciences and Humanities Research Council of Canada; University of Colorado Boulder; University of St Andrews; Aarhus Universitet; National Science Foundation; UK Research and Innovation; Clemson University; Universitetet i Stavanger; Vetenskapsrådet; John Templeton Foundation","keywords":"Climate change; Psychological intervention; Biology and political orientation; Psychology; Social psychology; Applied psychology; Environmental resource management; Geography; Political science; Politics; Ecology; Environmental science","score_opus":0.5800491103888415,"score_gpt":0.5281463008214803,"score_spread":0.05190280956736126,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403036292","genre_codex":"commentary","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022734586,0.01846031,0.000113083646,0.43196502,0.08709149,0.0022580056,0.26392087,0.001680204,0.17177641],"genre_scores_gemma":[0.20592202,0.27557418,0.0012620887,0.0037386538,0.003998802,0.00023385111,0.4936119,0.000103985134,0.015554505],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973971,0.00035194829,0.00037410494,0.0008473592,0.0006385316,0.00039092932],"domain_scores_gemma":[0.99557626,0.00047827524,0.000117769414,0.0034728548,0.00026690698,0.00008795648],"candidate_categories":["sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0047075017,0.00011724062,0.0001139413,0.00013351812,0.0030398094,0.0042727985,0.0055334913,0.00011728933,0.0037409107],"category_scores_gemma":[0.0005099698,0.00009598708,0.000022141014,0.0013777236,0.0010961448,0.0017538528,0.00238246,0.00019017865,0.0019485798],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042391526,0.000050487113,0.0005229077,0.000011740651,0.00005519156,0.000005420855,0.017566357,2.920435e-7,0.00020543669,0.026540458,0.9190625,0.035936818],"study_design_scores_gemma":[0.00014296503,0.0000052929686,0.0013748652,0.00005928901,0.000026490825,0.0000011219362,0.0050240946,0.0076357652,0.0000023786574,0.0011077761,0.9845027,0.0001172853],"about_ca_topic_score_codex":0.0005123885,"about_ca_topic_score_gemma":0.060304504,"teacher_disagreement_score":0.42822638,"about_ca_system_score_codex":0.0001063202,"about_ca_system_score_gemma":0.0002696763,"threshold_uncertainty_score":0.99984705},"labels":[],"label_agreement":null},{"id":"W4403133634","doi":"10.1038/s41597-024-03931-8","title":"Course-Skill Atlas: A national longitudinal dataset of skills taught in U.S. higher education curricula","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Labor market dynamics and wage inequality","field":"Economics, Econometrics and Finance","cited_by":7,"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":"Russell Sage Foundation","keywords":"Curriculum; Atlas (anatomy); Longitudinal data; Psychology; Mathematics education; Pedagogy; Biology; Sociology; Demography; Anatomy","score_opus":0.07755958872621702,"score_gpt":0.3232781377933296,"score_spread":0.24571854906711257,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403133634","genre_codex":"dataset","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":[0.26832736,0.010379807,0.0004936894,0.0034210365,0.01803186,0.00053143257,0.6829043,0.00006339982,0.01584714],"genre_scores_gemma":[0.92412686,0.000057268175,0.0006004828,0.0000729921,0.00015510025,0.0000122318215,0.069787,0.000013269033,0.0051748212],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981646,0.000020938756,0.00062826433,0.00084654806,0.00013708237,0.00020259412],"domain_scores_gemma":[0.99854404,0.00006947519,0.00017237035,0.001081837,0.00007657653,0.000055680895],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002808381,0.00010990569,0.00020795292,0.00032469706,0.000059200847,0.00033090264,0.00085927255,0.00005783172,0.0014198002],"category_scores_gemma":[0.00016871592,0.00011272148,0.000037079273,0.0009877556,0.00014985619,0.0007878382,0.00036611088,0.00012434334,0.00036077065],"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":[0.0000034607083,0.00060432724,0.029986406,0.00011261785,0.000032086795,0.0000055474493,0.000065693355,0.000029724863,0.00001193703,0.6197879,0.34782496,0.0015353952],"study_design_scores_gemma":[0.00015958404,0.000007944679,0.09182623,0.00011094096,0.000009271846,0.0000029414448,0.000015687585,0.007643374,0.000006790991,0.11308172,0.78691816,0.0002173134],"about_ca_topic_score_codex":0.00021014572,"about_ca_topic_score_gemma":0.00016581318,"teacher_disagreement_score":0.65579945,"about_ca_system_score_codex":0.000097670134,"about_ca_system_score_gemma":0.00023307679,"threshold_uncertainty_score":0.99949306},"labels":[],"label_agreement":null},{"id":"W4403228728","doi":"10.1038/s41597-024-03752-9","title":"The Global Dam Watch database of river barrier and reservoir information for large-scale applications","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Flood Risk Assessment and Management","field":"Environmental Science","cited_by":85,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Wildlife Federation; McGill University","funders":"Agence Nationale de la Recherche; European Commission; Oak Ridge National Laboratory; National Socio-Environmental Synthesis Center; McGill University; World Wildlife Fund; European Regional Development Fund; World Bank Group; National Science Foundation","keywords":"Hydropower; Scale (ratio); Environmental science; Database; Computer science; Environmental resource management; Hydrology (agriculture); Geography; Cartography; Ecology; Geology","score_opus":0.016121120110965486,"score_gpt":0.29012361459557046,"score_spread":0.27400249448460495,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403228728","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":[0.06837667,0.0017167581,0.7662166,0.010387155,0.004479854,0.006794622,0.11262167,0.00029008303,0.029116618],"genre_scores_gemma":[0.7500682,0.001112898,0.14393969,0.0005399807,0.0003337303,0.0012500988,0.06574007,0.000049032125,0.036966294],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99911106,0.000013071713,0.00015189574,0.00028966757,0.0002704735,0.00016384557],"domain_scores_gemma":[0.99884087,0.00003855786,0.00003367937,0.0010286017,0.000010636029,0.000047638016],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012294833,0.000055956283,0.00004422526,0.000014406023,0.00039789831,0.00033892243,0.0007311443,0.000015249531,0.0001018552],"category_scores_gemma":[0.00002630737,0.00003757622,0.000014894102,0.00031985444,0.00027858085,0.0013367811,0.0016418493,0.000032933964,0.00014372687],"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":[0.000009584446,0.000039901297,0.0025644791,0.00010085735,0.000018893183,2.2336845e-7,0.00033475057,0.00005629585,0.00019614959,0.017477753,0.9452552,0.033945873],"study_design_scores_gemma":[0.00009460269,0.0000064701294,0.0015111963,0.000008561815,0.000022698567,2.9024355e-7,0.0002872734,0.039181933,0.00007954048,0.0027085238,0.95604986,0.00004903127],"about_ca_topic_score_codex":0.00008422868,"about_ca_topic_score_gemma":0.00074242114,"teacher_disagreement_score":0.6816915,"about_ca_system_score_codex":0.00003377975,"about_ca_system_score_gemma":0.00001744147,"threshold_uncertainty_score":0.32682368},"labels":[],"label_agreement":null},{"id":"W4403282618","doi":"10.1038/s41597-024-03956-z","title":"Author Correction: Mechanical Unloading of Engineered Human Meniscus Models Under Simulated Microgravity: A Transcriptomic Study","year":2024,"lang":"en","type":"erratum","venue":"Scientific Data","topic":"Spaceflight effects on biology","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Meniscus; Transcriptome; Biology; Physics; Biochemistry; Gene expression; Optics","score_opus":0.1023104630241571,"score_gpt":0.37278572169367397,"score_spread":0.2704752586695169,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403282618","genre_codex":"editorial","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07094118,0.011560399,0.006531659,0.003948143,0.859625,0.01442101,0.02341889,0.002580645,0.0069730794],"genre_scores_gemma":[0.5156518,0.000011052343,0.0002482021,0.00004907193,0.0008284558,0.0000302363,0.03429491,0.00017436175,0.4487119],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9945509,0.00028106087,0.0009405871,0.002603745,0.0009467582,0.00067693525],"domain_scores_gemma":[0.9944744,0.000117028285,0.0002472654,0.0045555397,0.0003084466,0.0002972848],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0027735147,0.0006269348,0.0014199851,0.0011425178,0.00024587815,0.00026340203,0.0015243725,0.00089658826,0.00029684603],"category_scores_gemma":[0.0002084029,0.0005189979,0.00026750364,0.0015486991,0.0003898744,0.00019721448,0.0008348613,0.0019176598,0.00013889128],"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":[0.00010471542,0.000678365,0.0000029647722,0.0004613206,0.0007143515,0.00012796516,0.0004653782,0.00007074621,0.076426804,0.00011258437,0.92053103,0.00030379696],"study_design_scores_gemma":[0.0059908144,0.0031764416,0.00006812732,0.0029787414,0.010015785,0.00047220913,0.0022710161,0.26084054,0.009466752,0.0022468502,0.7005236,0.0019490971],"about_ca_topic_score_codex":0.0001644108,"about_ca_topic_score_gemma":0.00046379628,"teacher_disagreement_score":0.85879654,"about_ca_system_score_codex":0.00024860818,"about_ca_system_score_gemma":0.00070424896,"threshold_uncertainty_score":0.9997262},"labels":[],"label_agreement":null},{"id":"W4403303688","doi":"10.1038/s41597-024-03965-y","title":"A temporal (phospho-)proteomic dataset of neurotrophic receptor tyrosine kinase signalling in neuroblastoma","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Neuroblastoma Research and Treatments","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":"Children's Health Foundation; Irish Research Council; Science Foundation Ireland","keywords":"Neurotrophin; Neuroblastoma; Signalling; Receptor tyrosine kinase; Signalling pathways; Tyrosine kinase; Receptor; Biology; Tropomyosin receptor kinase B; Neuroscience; Computational biology; Signal transduction; Neurotrophic factors; Bioinformatics; Cell biology; Biochemistry; Genetics","score_opus":0.058551411565938495,"score_gpt":0.3358667250819108,"score_spread":0.2773153135159723,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403303688","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":[0.9635358,0.00054211135,0.0000715065,0.00074939773,0.00086228934,0.00084048306,0.033265255,0.00008482661,0.000048358663],"genre_scores_gemma":[0.96419156,0.000039949005,0.0013545426,0.000058113903,0.000072484174,0.000025643014,0.03321842,0.000044227287,0.0009950632],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99706525,0.00009499197,0.00047332834,0.0011992231,0.0006917414,0.00047545135],"domain_scores_gemma":[0.99759686,0.000077723234,0.000066543005,0.0019437488,0.00006160776,0.00025349346],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00077760045,0.00020277413,0.00030166403,0.00056665286,0.00008665423,0.00022855894,0.000764902,0.000048454232,0.00042399808],"category_scores_gemma":[0.00029297723,0.00016757238,0.000055616965,0.0014378879,0.0003453197,0.0004889166,0.0007662198,0.00036858412,0.0005963722],"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":[0.00067498116,0.0007772478,0.0013975297,0.00069710426,0.00006161954,0.0028877219,0.000057704387,0.000017035158,0.78854513,0.000049797087,0.1981193,0.0067148516],"study_design_scores_gemma":[0.008250331,0.0035367112,0.013712604,0.0044425223,0.00032783957,0.0005850532,0.000084463456,0.06695033,0.5681806,0.0003718093,0.3325694,0.0009883122],"about_ca_topic_score_codex":0.00017036323,"about_ca_topic_score_gemma":0.00006953781,"teacher_disagreement_score":0.22036447,"about_ca_system_score_codex":0.00005453151,"about_ca_system_score_gemma":0.00043545992,"threshold_uncertainty_score":0.7665357},"labels":[],"label_agreement":null},{"id":"W4403377357","doi":"10.1038/s41597-024-03962-1","title":"A practitioner-oriented regional hydrology data product for use in site-specific hydraulic applications","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Hydrology and Watershed Management Studies","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":true,"ca_institutions":"Global Institute for Water Security; Environment and Climate Change Canada; University of Saskatchewan","funders":"Canada First Research Excellence Fund","keywords":"Hydrology (agriculture); Environmental science; Product (mathematics); Geology; Mathematics; Geotechnical engineering","score_opus":0.08879299991659176,"score_gpt":0.30345120374451673,"score_spread":0.21465820382792497,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403377357","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":[0.24169514,0.009891691,0.41061375,0.1786104,0.02446671,0.027074935,0.0763022,0.002860006,0.028485168],"genre_scores_gemma":[0.7674711,0.00049849006,0.030476743,0.0019185795,0.00072242843,0.0015348716,0.15571634,0.00009266702,0.041568823],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971723,0.00006299758,0.00025639773,0.0018844269,0.0002496375,0.0003742647],"domain_scores_gemma":[0.9966563,0.00015560577,0.00005197167,0.0030711908,0.000010038113,0.00005491787],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0015921129,0.00013736641,0.00013012179,0.00015521803,0.0004116178,0.0002138694,0.0014497507,0.000045194272,0.0003799183],"category_scores_gemma":[0.00011208119,0.00012404489,0.000021139203,0.00078412,0.00074625545,0.0015981033,0.0028123243,0.00014879073,0.0017214704],"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":[0.000025184092,0.00015733908,0.0022029865,0.000025181129,0.00002303325,0.000011729389,0.00016936721,0.00032534474,0.00088848645,0.0012141416,0.99070305,0.0042541367],"study_design_scores_gemma":[0.00015376073,0.000012402204,0.0017248255,0.000009753996,0.000025381334,0.0000066185935,0.000026357522,0.02622263,0.000024906301,0.0012127028,0.97044885,0.00013178308],"about_ca_topic_score_codex":0.000120328645,"about_ca_topic_score_gemma":0.0013274052,"teacher_disagreement_score":0.5257759,"about_ca_system_score_codex":0.00006158857,"about_ca_system_score_gemma":0.000019975265,"threshold_uncertainty_score":0.9990558},"labels":[],"label_agreement":null},{"id":"W4403442553","doi":"10.1038/s41597-024-03973-y","title":"Age-specific ASPECTS atlas of Chinese subjects across different age groups for assessing acute ischemic stroke","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Acute Ischemic Stroke Management","field":"Medicine","cited_by":2,"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":"Higher Education Discipline Innovation Project; National Natural Science Foundation of China","keywords":"Ischemic stroke; Atlas (anatomy); Stroke (engine); Medicine; Gerontology; Internal medicine; Ischemia; Anatomy; Engineering","score_opus":0.04633025133040226,"score_gpt":0.34406892098895075,"score_spread":0.2977386696585485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403442553","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":[0.96957576,0.0016627979,0.006842996,0.00046081867,0.004605873,0.0011548144,0.007415305,0.00025436337,0.008027242],"genre_scores_gemma":[0.9600539,0.000060319748,0.003772678,0.00005135478,0.0005253512,0.000046785593,0.013584517,0.00007713703,0.021827964],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9960524,0.000029082803,0.0006075555,0.0016385954,0.00092042994,0.0007519603],"domain_scores_gemma":[0.99614555,0.00020150232,0.00016216622,0.0031657587,0.000110432375,0.00021458577],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010902545,0.00039224504,0.00062465033,0.00029040553,0.0002447392,0.00093150063,0.001373241,0.000117560296,0.00013459931],"category_scores_gemma":[0.00021225252,0.00029787302,0.00022597524,0.0008156098,0.00052773376,0.0006436202,0.001882944,0.00034286553,0.00008347764],"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":[0.00008097277,0.00018740508,0.00069164723,0.0007914263,0.00042470085,0.0005225358,0.00067887426,0.0000010542531,0.49074018,0.00014656024,0.49737445,0.008360194],"study_design_scores_gemma":[0.003361308,0.00019119534,0.014795964,0.0012650902,0.00088115904,0.00015183387,0.0010386853,0.0056673153,0.10225871,0.00031249094,0.86927146,0.0008048091],"about_ca_topic_score_codex":0.000008721153,"about_ca_topic_score_gemma":0.000028599008,"teacher_disagreement_score":0.38848147,"about_ca_system_score_codex":0.00016485715,"about_ca_system_score_gemma":0.00011855043,"threshold_uncertainty_score":0.99994737},"labels":[],"label_agreement":null},{"id":"W4403545417","doi":"10.1038/s41597-024-03940-7","title":"Lake Superior evaporation: A long-term eddy covariance dataset at Stannard Rock Lighthouse (2008–2022)","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Plant Water Relations and Carbon Dynamics","field":"Environmental Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Environment and Climate Change Canada","funders":"Environment and Climate Change Canada; Michigan Technological University; National Oceanic and Atmospheric Administration; NOAA Great Lakes Environmental Research Laboratory; U.S. Department of Commerce; National Science Foundation","keywords":"Eddy covariance; Lake ecosystem; Hydrology (agriculture); Environmental science; Term (time); Snow; Range (aeronautics); Evaporation; Ecosystem; Physical geography; Geology; Geography; Meteorology; Ecology","score_opus":0.025844394886345833,"score_gpt":0.26233651235338723,"score_spread":0.2364921174670414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403545417","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30493042,0.00168351,0.019565498,0.0022008345,0.00944542,0.0012137209,0.6583461,0.0006225542,0.0019919295],"genre_scores_gemma":[0.2660234,0.00018430618,0.0028849572,0.00027290054,0.00026267752,0.000049027,0.6408239,0.00007970244,0.08941912],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.997438,0.000051773044,0.0002884523,0.0011961348,0.00064657774,0.0003790675],"domain_scores_gemma":[0.9974859,0.000029850837,0.00004853489,0.0022656105,0.00001002053,0.00016011251],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000871298,0.00018084918,0.00013457917,0.00007966966,0.00046266455,0.00094955595,0.0013698095,0.0000722738,0.006757701],"category_scores_gemma":[0.000032814976,0.00015719609,0.000031916476,0.0007654776,0.0002123229,0.0014730839,0.0019977489,0.00016048495,0.008103161],"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":[0.000019268666,0.000085941865,0.006084217,0.00004126332,0.000028730372,0.0003258954,0.00022885374,0.0034953572,0.0059977407,0.00011882302,0.9810096,0.0025642884],"study_design_scores_gemma":[0.00012409686,0.00001608776,0.0021166627,0.000039793922,0.00003953098,0.00010135949,0.0000064793057,0.117872685,0.00017733294,0.0000795898,0.87916964,0.00025671316],"about_ca_topic_score_codex":0.000027534266,"about_ca_topic_score_gemma":0.0044211727,"teacher_disagreement_score":0.11437733,"about_ca_system_score_codex":0.00014041807,"about_ca_system_score_gemma":0.000062979634,"threshold_uncertainty_score":0.9941503},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W4403547097","doi":"10.1038/s41597-024-03972-z","title":"A dataset of Solicited Cough Sound for Tuberculosis Triage Testing","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Respiratory and Cough-Related Research","field":"Medicine","cited_by":11,"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 de l’Université de Montréal","funders":"National Institute of Allergy and Infectious Diseases; National Institutes of Health; Fonds de Recherche du Québec - Santé; Bill and Melinda Gates Foundation; U.S. Department of Health and Human Services","keywords":"Medicine; Tuberculosis; Triage; Intensive care medicine; Disease; Pandemic; Limiting; Infectious disease (medical specialty); Pathology; Medical emergency; Coronavirus disease 2019 (COVID-19)","score_opus":0.31017244749585604,"score_gpt":0.44934048993525966,"score_spread":0.13916804243940362,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403547097","genre_codex":"dataset","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":[0.4277858,0.00828459,0.0081372475,0.0025475442,0.0049379584,0.0041526062,0.5387246,0.00038206676,0.0050475663],"genre_scores_gemma":[0.7143413,0.00004134011,0.0069270185,0.00039441852,0.00077734765,0.00011508247,0.26612875,0.000099392186,0.011175391],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99803483,0.000046735244,0.00037385707,0.000718649,0.0005111496,0.00031478173],"domain_scores_gemma":[0.9971992,0.0004899335,0.000046948073,0.0019550023,0.0001817735,0.00012718448],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029756513,0.000105707935,0.00021482696,0.00026584294,0.00019880784,0.0002807917,0.0006568975,0.00007310916,0.00021374386],"category_scores_gemma":[0.0018686802,0.000081102815,0.000048610917,0.0013521827,0.00030808887,0.0003681688,0.0004078926,0.00021290887,0.0001411414],"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":[0.0001300387,0.00013948156,0.00019506803,0.00089058146,0.00016215652,0.000061270024,0.00012825007,0.0000064783007,0.052968904,0.00023464074,0.92252487,0.02255826],"study_design_scores_gemma":[0.0011595625,0.0002872769,0.00023207942,0.0006115498,0.00033088238,0.00004944095,0.00018854995,0.05728791,0.007030705,0.00093404105,0.9317157,0.00017225336],"about_ca_topic_score_codex":0.000031847998,"about_ca_topic_score_gemma":0.00001190585,"teacher_disagreement_score":0.28655547,"about_ca_system_score_codex":0.000024621371,"about_ca_system_score_gemma":0.00037649562,"threshold_uncertainty_score":0.3307277},"labels":[],"label_agreement":null},{"id":"W4403872579","doi":"10.1038/s41597-024-04026-0","title":"A global dataset of salmonid biomass in streams","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Fish Ecology and Management Studies","field":"Environmental Science","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":"Concordia University","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Biomass (ecology); STREAMS; Range (aeronautics); Sampling (signal processing); Scope (computer science); Environmental science; Taxon; Ecology; Fishery; Biology; Computer science","score_opus":0.027897313757870572,"score_gpt":0.29157818573838074,"score_spread":0.26368087198051016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403872579","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":[0.7107653,0.0005729045,0.0006216518,0.003201211,0.005295823,0.0007851847,0.22037005,0.00015966661,0.058228195],"genre_scores_gemma":[0.98406,0.000015052963,0.00063663145,0.000074103926,0.0000118086955,0.0000066847024,0.0134917665,0.0000039300785,0.0017000084],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989091,0.000021766591,0.00015456595,0.00055470364,0.00017841856,0.00018144073],"domain_scores_gemma":[0.99901986,0.000021358874,0.000022422793,0.0009101333,0.0000015090388,0.00002473621],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0007723958,0.000062884406,0.00007752096,0.00004418222,0.00007078525,0.00006322118,0.0009027714,0.000022194581,0.0013711819],"category_scores_gemma":[0.00004546165,0.000053563726,0.000009732803,0.00077539915,0.00051437586,0.00044570488,0.002604476,0.000032371438,0.0008741534],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000022373556,0.000049030226,0.08758787,0.000020687596,0.000010283246,0.000023828728,0.00002894875,0.000009388442,0.00009073022,0.00017786457,0.90834475,0.003654388],"study_design_scores_gemma":[0.000093435,0.000015064548,0.30277643,0.000020261397,0.00001822085,0.0000019482834,0.00008171487,0.0029491999,0.000047345904,0.0014333752,0.6924701,0.00009292625],"about_ca_topic_score_codex":0.00056215766,"about_ca_topic_score_gemma":0.023634693,"teacher_disagreement_score":0.27329472,"about_ca_system_score_codex":0.00004823152,"about_ca_system_score_gemma":0.00001039823,"threshold_uncertainty_score":0.9999038},"labels":[],"label_agreement":null},{"id":"W4403891519","doi":"10.1038/s41597-024-03897-7","title":"FARFUM-RoP, A dataset for computer-aided detection of Retinopathy of Prematurity","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Retinopathy of Prematurity Studies","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Retinopathy of prematurity; Computer science; Medicine; Gestational age; Biology; Pregnancy","score_opus":0.07432057729253969,"score_gpt":0.3530332026409905,"score_spread":0.27871262534845076,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403891519","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":[0.6073307,0.009113905,0.032823805,0.0020171187,0.014158572,0.0047723646,0.32894093,0.00038288248,0.00045973097],"genre_scores_gemma":[0.9424524,0.000039879655,0.023739934,0.000030043575,0.0002687971,0.000021835749,0.03295639,0.000028669028,0.00046210396],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99788994,0.00005206518,0.0005069185,0.0008277092,0.00049320195,0.0002301909],"domain_scores_gemma":[0.9971487,0.00019645994,0.0001513894,0.0022108846,0.00021841956,0.00007417276],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021251976,0.00014690791,0.00041784102,0.00024252335,0.00011191149,0.000089090005,0.0006222287,0.00007367594,0.000020162055],"category_scores_gemma":[0.0007032981,0.00012247072,0.00008676239,0.00047541133,0.0004606109,0.0002908568,0.00077353447,0.00015433907,0.000020701516],"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":[0.000421143,0.00044585238,0.00030049423,0.010999224,0.0003000518,0.000033547458,0.001365492,0.0000023854336,0.35807186,0.00024209305,0.5852176,0.042600233],"study_design_scores_gemma":[0.002287311,0.0012734665,0.010856341,0.0039068745,0.0012650872,0.00023993089,0.0005990242,0.05669495,0.43865702,0.0016148217,0.48203975,0.0005654121],"about_ca_topic_score_codex":0.000030210456,"about_ca_topic_score_gemma":0.000041043426,"teacher_disagreement_score":0.33512163,"about_ca_system_score_codex":0.000027370725,"about_ca_system_score_gemma":0.00011847423,"threshold_uncertainty_score":0.4994211},"labels":[],"label_agreement":null},{"id":"W4404199554","doi":"10.1038/s41597-024-04010-8","title":"Neural Dynamics of Creative Movements During the Rehearsal and Performance of “LiveWire\"","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Neural dynamics and brain function","field":"Neuroscience","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":"McGill University; Rice University; National Science Foundation","keywords":"Electrooculography; Forehead; Electroencephalography; Computer science; Dynamics (music); Brain activity and meditation; Inertial measurement unit; Motion (physics); Artificial intelligence; Brain–computer interface; Computer vision; Psychology; Eye movement; Neuroscience; Medicine","score_opus":0.03630925699347074,"score_gpt":0.27132811150185093,"score_spread":0.2350188545083802,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404199554","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":[0.99647677,0.00004997833,0.000021871305,0.00017336979,0.001077011,0.0001278028,0.0016882875,0.000017987255,0.00036694555],"genre_scores_gemma":[0.9958743,0.000030229374,0.00002017416,0.000019006506,0.000015506568,0.0000015692377,0.00009226265,0.0000062655677,0.0039407057],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989367,0.00003979271,0.00016961462,0.0004433899,0.00027932294,0.00013118892],"domain_scores_gemma":[0.99916404,0.000087962144,0.000060074708,0.00063777436,0.000025749765,0.000024407973],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037118135,0.00006805274,0.000079724094,0.00008080522,0.00018136234,0.00013693243,0.00051699305,0.00001564172,0.000026829708],"category_scores_gemma":[0.00012554132,0.000044864762,0.000017664339,0.00044402215,0.00048188138,0.00045834438,0.00059874885,0.00009379389,0.000004677404],"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":[0.00009154414,0.000077419616,0.003891367,0.0005208131,0.000016455955,0.000010753319,0.0005598595,0.00014845385,0.95819235,0.0039539677,0.0013064515,0.031230547],"study_design_scores_gemma":[0.00010308809,0.000077724995,0.021777246,0.00007946779,0.000010591948,0.000013027568,0.000090799986,0.93348825,0.04338017,0.00022675774,0.0006797572,0.00007312921],"about_ca_topic_score_codex":0.0000220762,"about_ca_topic_score_gemma":0.000019255824,"teacher_disagreement_score":0.9333398,"about_ca_system_score_codex":0.00001463149,"about_ca_system_score_gemma":0.000023502807,"threshold_uncertainty_score":0.1829532},"labels":[],"label_agreement":null},{"id":"W4404347553","doi":"10.1038/s41597-024-04011-7","title":"A Biomechanical Dataset of 1,798 Healthy and Injured Subjects During Treadmill Walking and Running","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Lower Extremity Biomechanics and Pathologies","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Running Injury Clinic; University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Treadmill; Physical medicine and rehabilitation; Medicine; Physical therapy; Computer science","score_opus":0.037846277827889616,"score_gpt":0.2801639564275309,"score_spread":0.24231767859964126,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404347553","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":[0.8531284,0.009389313,0.0009290459,0.00011966883,0.0025449244,0.0002319664,0.13315384,0.0004140097,0.00008884474],"genre_scores_gemma":[0.9843797,0.00028801674,0.0021242404,0.000010129416,0.000044659704,0.0000037648579,0.013083345,0.000022159635,0.000043972937],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99878395,0.000015021329,0.00022684534,0.0005663428,0.00015951203,0.00024833356],"domain_scores_gemma":[0.99900573,0.00006296972,0.000022024002,0.0008063524,0.000012034819,0.000090883346],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007500795,0.00012355275,0.00016127384,0.00025891743,0.00011560128,0.0003171602,0.0003683949,0.000062583924,0.00004265332],"category_scores_gemma":[0.00006138845,0.00011056157,0.000012906483,0.00045146167,0.000107828375,0.00035461676,0.00074018247,0.00011867244,0.000009097001],"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":[0.00004643213,0.000051930416,0.00018748791,0.0034260266,0.00012355269,0.00020693487,0.0016488275,0.0000068325653,0.70174253,0.0011599871,0.15648311,0.13491637],"study_design_scores_gemma":[0.0016607017,0.0002951428,0.00276261,0.0021120054,0.00024632743,0.0005509554,0.0014215522,0.4290217,0.07963521,0.004810009,0.47565007,0.0018337166],"about_ca_topic_score_codex":0.000016184713,"about_ca_topic_score_gemma":0.00004634047,"teacher_disagreement_score":0.62210727,"about_ca_system_score_codex":0.000015105733,"about_ca_system_score_gemma":0.00002548859,"threshold_uncertainty_score":0.45085698},"labels":[],"label_agreement":null},{"id":"W4404484879","doi":"10.1038/s41597-024-03994-7","title":"Historical datasets (1950–2022) of monthly water balance components for the Laurentian Great Lakes","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Hydrology and Watershed Management Studies","field":"Environmental Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Environment and Climate Change Canada","funders":"National Oceanic and Atmospheric Administration; Environment and Climate Change Canada","keywords":"Water balance; Balance (ability); Bayesian probability; Environmental science; Psychological resilience; Reliability (semiconductor); Water resources; Ecosystem; Environmental resource management; Computer science; Ecology; Geology","score_opus":0.0376020613180141,"score_gpt":0.25516026664432484,"score_spread":0.21755820532631073,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404484879","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":[0.533364,0.02440524,0.023142135,0.12889656,0.0991343,0.009523141,0.16244355,0.0012840979,0.017806996],"genre_scores_gemma":[0.95856464,0.00005164912,0.00046549513,0.00017312134,0.00010727207,0.00006015672,0.018229526,0.000020057087,0.022328094],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985299,0.00003290441,0.00019208508,0.00065296155,0.00029548383,0.00029665403],"domain_scores_gemma":[0.99858236,0.00007395388,0.000027560734,0.001273251,0.000004576123,0.000038271533],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0010664779,0.000108512795,0.00012869958,0.000043326017,0.00046624462,0.00009934113,0.0014146523,0.000029749664,0.00095748785],"category_scores_gemma":[0.000030338728,0.000059562775,0.000040569717,0.0001736185,0.0005604977,0.00038699634,0.0018611334,0.000076207376,0.00044378903],"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":[0.000013318399,0.00003960048,0.0019589115,0.000039424984,0.000050461822,0.0000062558443,0.0002562631,0.00009388207,0.002596351,0.00005491061,0.99339306,0.0014975339],"study_design_scores_gemma":[0.000109494555,0.000014873284,0.0015798488,0.000012400776,0.00007214483,7.952849e-7,0.000020673395,0.011194648,0.00048168667,0.00047107373,0.9859579,0.00008446265],"about_ca_topic_score_codex":0.00018212461,"about_ca_topic_score_gemma":0.00052036054,"teacher_disagreement_score":0.42520064,"about_ca_system_score_codex":0.000059116388,"about_ca_system_score_gemma":0.000003506263,"threshold_uncertainty_score":0.9999558},"labels":[],"label_agreement":null},{"id":"W4404719260","doi":"10.1038/s41597-024-04101-6","title":"A high-resolution satellite-based solar-induced chlorophyll fluorescence dataset for China from 2000 to 2022","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Remote Sensing in Agriculture","field":"Environmental Science","cited_by":25,"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":"Remote sensing; Environmental science; Satellite; Primary production; Image resolution; Atmospheric sciences; Meteorology; Ecosystem; Computer science; Geography; Geology; Physics; Ecology","score_opus":0.024622025579839064,"score_gpt":0.2577707167241957,"score_spread":0.23314869114435666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404719260","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3813615,0.0006057573,0.022429092,0.007854333,0.017762324,0.0032091471,0.5658031,0.0005530691,0.00042163144],"genre_scores_gemma":[0.51704437,0.000013086369,0.086043425,0.0005354169,0.00066770194,0.000020508704,0.39096197,0.00007358227,0.0046399375],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99641496,0.000070021895,0.000294422,0.0019084137,0.0007745303,0.0005376636],"domain_scores_gemma":[0.9968344,0.00009699254,0.000057960362,0.002755852,0.000014557356,0.00024025614],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0010219841,0.00024350664,0.00018059494,0.000091128575,0.00044143692,0.0009955429,0.0020083492,0.000099748686,0.0010749612],"category_scores_gemma":[0.00021927137,0.00019253076,0.000051032606,0.0011685156,0.00022534982,0.00073711,0.001157494,0.00021352392,0.0040988415],"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":[0.000024779205,0.000046618647,0.000019955656,0.000014736609,0.000008255644,0.000014619477,0.00013262563,0.0005961726,0.3063091,0.000008906734,0.64944136,0.043382876],"study_design_scores_gemma":[0.00020206474,0.000055318425,0.0072030206,0.00008935112,0.000040394138,0.0000034731272,0.000023313301,0.097437546,0.03191296,0.0003225681,0.8623313,0.00037874194],"about_ca_topic_score_codex":0.0023794533,"about_ca_topic_score_gemma":0.0012472543,"teacher_disagreement_score":0.27439615,"about_ca_system_score_codex":0.0003049084,"about_ca_system_score_gemma":0.000088529676,"threshold_uncertainty_score":0.9998382},"labels":[],"label_agreement":null},{"id":"W4405075600","doi":"10.1038/s41597-024-04157-4","title":"Generative models of MRI-derived neuroimaging features and associated dataset of 18,000 samples","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Machine Learning in Healthcare","field":"Computer Science","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":"National Institute of Biomedical Imaging and Bioengineering; National Institute on Aging; Canadian Institutes of Health Research; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; Northern California Institute for Research and Education; Pfizer; Novartis Pharmaceuticals Corporation; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; University of Southern California; BioClinica; Biogen; Bristol-Myers Squibb; Eli Lilly and Company; National Institutes of Health; U.S. Department of Health and Human Services","keywords":"Neuroimaging; Computer science; Machine learning; Context (archaeology); Artificial intelligence; Generative model; Normative; Generative grammar; Data science; Psychology; Neuroscience; Geography","score_opus":0.10633155753044737,"score_gpt":0.352174247784702,"score_spread":0.24584269025425465,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405075600","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":[0.086052544,0.012203544,0.5949056,0.008509434,0.0071768193,0.0010992493,0.28845066,0.0006621289,0.000940033],"genre_scores_gemma":[0.8911711,0.000069099035,0.0820688,0.00014451853,0.000057802896,0.0000052654773,0.026033878,0.000024162573,0.00042537245],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99776655,0.000233386,0.0003240993,0.0009820831,0.00045808384,0.00023578783],"domain_scores_gemma":[0.9973027,0.0002635438,0.00014222947,0.0020964672,0.000117195,0.00007785353],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001588995,0.00012263,0.00020356195,0.00022128625,0.00017382548,0.0005744787,0.0021926633,0.000037216596,0.000028462584],"category_scores_gemma":[0.00037705258,0.00010748484,0.000020566302,0.0007582553,0.00028680146,0.0011896545,0.0023148237,0.00022011716,0.0000035185153],"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":[0.000009612188,0.00010438694,0.0013579061,0.00069474493,0.00011127137,0.00004855749,0.005733391,0.004086906,0.025719708,0.026079375,0.90198636,0.03406777],"study_design_scores_gemma":[0.0000990424,0.00002626315,0.0024358819,0.00013702344,0.000013628658,0.00001320166,0.000054247867,0.98070526,0.0015898505,0.0041045276,0.010686068,0.0001349915],"about_ca_topic_score_codex":0.00043628307,"about_ca_topic_score_gemma":0.00010310349,"teacher_disagreement_score":0.97661835,"about_ca_system_score_codex":0.000015275042,"about_ca_system_score_gemma":0.00017312939,"threshold_uncertainty_score":0.5539712},"labels":[],"label_agreement":null},{"id":"W4405516627","doi":"10.1038/s41597-024-04239-3","title":"Chromosome-level genome assembly of Phortica okadai, a vector of Thelazia callipaeda","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Parasitic Diseases Research and Treatment","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Petroleum Technology Research Centre; Guizhou Science and Technology Department","keywords":"Biology; Genome; Chromosome; Genetics; Zoology; Computational biology; Gene","score_opus":0.11901215003872492,"score_gpt":0.3880388147661537,"score_spread":0.26902666472742875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405516627","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":[0.9264779,0.012772879,0.0004891937,0.0007954578,0.0010938998,0.0009838929,0.047085483,0.00009415986,0.010207151],"genre_scores_gemma":[0.98942596,0.00006751629,0.0006270039,0.000011457536,0.000059062422,0.000012819612,0.0038537555,0.000015215387,0.0059272083],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99794525,0.00003551652,0.00030555384,0.0005844273,0.00080207636,0.00032715232],"domain_scores_gemma":[0.9976591,0.00009813314,0.000041673185,0.0017795198,0.00013082456,0.00029078612],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00053493975,0.00011652241,0.00026989335,0.0002065823,0.000053306434,0.00008163107,0.00055231183,0.000034697678,0.00090914144],"category_scores_gemma":[0.00029233686,0.00008511761,0.00009179965,0.000619312,0.000417039,0.0001734348,0.00036722457,0.00009293601,0.00034196058],"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":[0.00044617848,0.0032917913,0.0018018485,0.0028161404,0.002141715,0.0014304683,0.0006177636,0.00000415543,0.85095924,0.0033029974,0.0899945,0.043193176],"study_design_scores_gemma":[0.0064799488,0.002491333,0.28068075,0.003421292,0.003462396,0.0003224268,0.0006944275,0.021435797,0.250083,0.0012910189,0.4285646,0.0010729864],"about_ca_topic_score_codex":0.000079810685,"about_ca_topic_score_gemma":0.000022354116,"teacher_disagreement_score":0.6008763,"about_ca_system_score_codex":0.000054171418,"about_ca_system_score_gemma":0.0009402655,"threshold_uncertainty_score":0.99544615},"labels":[],"label_agreement":null},{"id":"W4405523294","doi":"10.1038/s41597-024-04261-5","title":"Primate Phenotypes: A Multi-Institution Collection of 3D Morphological Data Housed in MorphoSource","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Primate Behavior and Ecology","field":"Psychology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University; University of Toronto","funders":"Ministerio de Ciencia e Innovación; American Museum of Natural History; Agencia Estatal de Investigación; National Science Foundation","keywords":"Digitization; Phenomics; Metadata; Natural history; National Museum of Natural History; Computer science; Data science; World Wide Web; Biology; Ecology; Genomics","score_opus":0.16115306330709683,"score_gpt":0.3947069348684969,"score_spread":0.23355387156140006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405523294","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":[0.94749194,0.0016508852,0.012098217,0.00032541988,0.016312143,0.0010143167,0.015165161,0.0005063353,0.0054355925],"genre_scores_gemma":[0.9825939,0.00001930499,0.0037737642,0.00003924164,0.000059533373,0.000028930754,0.010350246,0.000023333248,0.0031117469],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99753183,0.0001464613,0.00042302904,0.0013071755,0.00020996816,0.00038154493],"domain_scores_gemma":[0.9966473,0.000075161646,0.00007737608,0.003105593,0.00003465801,0.000059920345],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0020636965,0.00013963306,0.00023616926,0.00037046886,0.00013529525,0.00013055542,0.0019016747,0.00016181765,0.0015760213],"category_scores_gemma":[0.00018622424,0.00012544038,0.00002327744,0.0010588577,0.00046240096,0.00049073476,0.0013798636,0.00023612034,0.0009991265],"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":[0.0005519472,0.004361395,0.033927646,0.00039931564,0.00019697536,0.001566234,0.006098123,0.00015090517,0.12190672,0.004551665,0.770612,0.055677056],"study_design_scores_gemma":[0.006232528,0.00039708798,0.3288432,0.000389087,0.0005175021,0.00076192815,0.001839112,0.16034493,0.003067069,0.00045851723,0.4956785,0.0014705212],"about_ca_topic_score_codex":0.00059189886,"about_ca_topic_score_gemma":0.00075332756,"teacher_disagreement_score":0.2949156,"about_ca_system_score_codex":0.000085261294,"about_ca_system_score_gemma":0.00016599585,"threshold_uncertainty_score":0.9997787},"labels":[],"label_agreement":null},{"id":"W4405858697","doi":"10.1038/s41597-024-04324-7","title":"Transcriptome and translatome profiling of Col-0 and grp7grp8 under ABA treatment in Arabidopsis","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"RNA Research and Splicing","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Key Research and Development Program of China; Institute of Genetics; Universität Bielefeld; Chinese Academy of Sciences","keywords":"Biology; Ribosome profiling; Translational regulation; Arabidopsis; Transcriptome; Translation (biology); Ribosome; Abscisic acid; Computational biology; RNA; RNA-binding protein; Messenger RNA; Arabidopsis thaliana; Immunoprecipitation; Eukaryotic translation; RNA-Seq; Cell biology; Gene expression; Gene; Genetics","score_opus":0.04613357419638759,"score_gpt":0.32769013025125393,"score_spread":0.28155655605486635,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405858697","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":[0.9917616,0.0065663117,0.00027867864,0.00019200482,0.00010898183,0.00018413294,0.0007867842,0.0000055143914,0.00011595714],"genre_scores_gemma":[0.9969765,0.0003641857,0.00041379375,0.000008295236,0.000018821194,0.000007290776,0.00067821937,0.000007744401,0.0015251618],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990605,0.000026178805,0.00012800237,0.00049949397,0.00011260271,0.00017322964],"domain_scores_gemma":[0.9994782,0.000011804676,0.000009798958,0.0004212782,0.000014705416,0.00006417107],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043202814,0.00007544251,0.00009600904,0.000100966776,0.000046022946,0.00011041931,0.0001704855,0.000042808395,0.0000073604915],"category_scores_gemma":[0.000013713875,0.000061030805,0.000018221443,0.00017817052,0.00019616603,0.000014386385,0.000077187346,0.00004227679,0.0000015698516],"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":[0.000021553118,0.000030328232,0.0008403064,0.00007371117,0.000026787808,0.000006164163,0.00010691411,0.0000034065715,0.98804015,0.0001531312,0.00030592136,0.010391647],"study_design_scores_gemma":[0.0020192564,0.0005916266,0.008341636,0.00025251717,0.000077755074,0.000057655594,0.0010817257,0.013674196,0.90739876,0.0006203553,0.06542351,0.0004609794],"about_ca_topic_score_codex":0.000065631466,"about_ca_topic_score_gemma":0.00027185056,"teacher_disagreement_score":0.08064134,"about_ca_system_score_codex":0.0000076137235,"about_ca_system_score_gemma":0.00009626103,"threshold_uncertainty_score":0.2488764},"labels":[],"label_agreement":null},{"id":"W4406087184","doi":"10.1038/s41597-025-04372-7","title":"A Collaborative and Scalable Geospatial Data Set for Arctic Retrogressive Thaw Slumps with Data Standards","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Climate change and permafrost","field":"Earth and Planetary Sciences","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Permafrost; Geospatial analysis; Arctic; Computer science; Database; Environmental science; Physical geography; Data mining; Data science; Remote sensing; Geography; Geology; Oceanography","score_opus":0.06993715916196934,"score_gpt":0.32993986702557104,"score_spread":0.2600027078636017,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406087184","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016468665,0.0020452265,0.00063889223,0.0010294863,0.0011513886,0.000636795,0.9769438,0.000028888076,0.0010568488],"genre_scores_gemma":[0.07131045,0.00020986637,0.003102243,0.00023311639,0.00016953191,0.0000041285152,0.9233574,0.000007468146,0.0016057852],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99721646,0.00007078298,0.00021826697,0.0015353605,0.00052831316,0.00043083337],"domain_scores_gemma":[0.9944527,0.00028700035,0.00010914029,0.0047267955,0.000287624,0.00013671126],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002362238,0.00017901436,0.00024154497,0.000119740194,0.0007463599,0.0011871209,0.0032046533,0.000058747577,0.0016954148],"category_scores_gemma":[0.0005123206,0.00013221671,0.0000080822865,0.0008505133,0.00062658766,0.0017849287,0.001412975,0.00012083222,0.000027697415],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030616598,0.000024860803,0.15477656,0.00018292239,0.00007703355,0.000015863568,0.0003520884,0.000008921727,0.000023639144,0.00003585257,0.83117044,0.013025622],"study_design_scores_gemma":[0.0012228764,0.00016309944,0.031178728,0.00028607773,0.00019891298,0.0000136218005,0.0026608976,0.10664516,0.000039267747,0.00041536617,0.8568169,0.00035909165],"about_ca_topic_score_codex":0.0028492645,"about_ca_topic_score_gemma":0.1962064,"teacher_disagreement_score":0.19335714,"about_ca_system_score_codex":0.000006946918,"about_ca_system_score_gemma":0.0006982836,"threshold_uncertainty_score":0.99984974},"labels":[],"label_agreement":null},{"id":"W4406087194","doi":"10.1038/s41597-025-04378-1","title":"Reconstruction of long-term hourly sea level data for Prince Edward Island, Canada","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Geophysics and Gravity Measurements","field":"Earth and Planetary Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Prince Edward Island","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Natural Resources Canada; Canada Foundation for Innovation; Atlantic Canada Opportunities Agency; Government of Canada","keywords":"Shore; Context (archaeology); Climate change; Storm surge; Term (time); Sea level; Storm; Geography; Oceanography; Historical record; Hazard; Physical geography; Environmental science; Climatology; Meteorology; Geology; Archaeology; Ecology; History","score_opus":0.08145897699803296,"score_gpt":0.2695946761605909,"score_spread":0.18813569916255796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406087194","genre_codex":"dataset","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":[0.4750947,0.0003734239,0.005692904,0.00053429964,0.011974874,0.0007411867,0.50357836,0.00001987835,0.0019903276],"genre_scores_gemma":[0.9186154,0.0000055379337,0.0014366137,0.000050719584,0.0000648634,7.2374297e-7,0.07655952,0.0000021359986,0.0032644607],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99856424,0.000027627531,0.00021096159,0.00061049015,0.00036184327,0.00022483953],"domain_scores_gemma":[0.9976043,0.00005357964,0.00009923775,0.002070319,0.00011136313,0.00006119521],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009426978,0.00008609832,0.00013245412,0.00006255111,0.0002460617,0.0001488952,0.0018898598,0.000025685698,0.00014377064],"category_scores_gemma":[0.00013308605,0.000076051416,0.00001582606,0.00031203762,0.00012334496,0.000447346,0.00020113516,0.000059973205,0.000013133723],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023831852,0.00002064598,0.55022615,0.00012314587,0.00004536314,0.0000018720334,0.000010678574,0.00003105904,0.0000931386,0.000022065236,0.19740818,0.25199383],"study_design_scores_gemma":[0.00048419312,0.000020145622,0.9407298,0.00010805487,0.000058573165,0.0000040141163,0.00004320509,0.008534972,0.0004876134,0.00069262914,0.048652466,0.00018433365],"about_ca_topic_score_codex":0.28741938,"about_ca_topic_score_gemma":0.9652925,"teacher_disagreement_score":0.67787313,"about_ca_system_score_codex":0.000008487531,"about_ca_system_score_gemma":0.0011317013,"threshold_uncertainty_score":0.71732575},"labels":[],"label_agreement":null},{"id":"W4406274339","doi":"10.1038/s41597-024-04175-2","title":"The North American Repository for Archaeological Isotopes","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Archaeology and ancient environmental studies","field":"Earth and Planetary Sciences","cited_by":4,"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":"Max-Planck-Institut für Menschheitsgeschichte; Max-Planck-Gesellschaft","keywords":"Archaeology; Isotope; Geography; Geology; Physics","score_opus":0.023966023876634945,"score_gpt":0.24392142845207074,"score_spread":0.2199554045754358,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406274339","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":[0.9750957,0.0026807855,0.002061511,0.0047448836,0.0035144624,0.0005659175,0.002568528,0.000067447116,0.008700761],"genre_scores_gemma":[0.9807355,0.000099534576,0.0012412225,0.00028518809,0.000054125267,0.0000055206506,0.001308436,9.964991e-7,0.016269468],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99896514,0.000048409784,0.00013008488,0.00045359245,0.00012575714,0.00027698718],"domain_scores_gemma":[0.99887985,0.0003453486,0.000047021695,0.00067788234,0.000011005982,0.000038866],"candidate_categories":["sts"],"consensus_categories":["sts"],"category_scores_codex":[0.0005432846,0.000070243026,0.000086572596,0.000026080988,0.0021403008,0.000057383262,0.0011284818,0.000012121821,0.000030819603],"category_scores_gemma":[0.0001249553,0.000040020892,0.000026368938,0.00024136995,0.004047431,0.00010056665,0.0003902119,0.000069255104,0.00005759697],"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":[0.00002388424,0.0000076075057,0.88008064,0.000002949219,0.0000149745865,0.0000016230745,0.000054052165,0.000026693706,0.0000034743698,0.0002447337,0.038124945,0.08141442],"study_design_scores_gemma":[0.000040971474,0.0000235965,0.62531745,0.0000016183208,0.000006312191,9.736058e-7,0.0001499918,0.0011773873,0.000016544684,0.00083103497,0.3723953,0.00003881286],"about_ca_topic_score_codex":0.00014970404,"about_ca_topic_score_gemma":0.009548049,"teacher_disagreement_score":0.33427036,"about_ca_system_score_codex":0.0000024827043,"about_ca_system_score_gemma":0.0000266252,"threshold_uncertainty_score":0.9991588},"labels":[],"label_agreement":null},{"id":"W4406384985","doi":"10.1038/s41597-025-04420-2","title":"Author Correction: Typical and extreme weather datasets for studying the resilience of buildings to climate change and heatwaves","year":2025,"lang":"en","type":"erratum","venue":"Scientific Data","topic":"Wind and Air Flow Studies","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University; National Research Council Canada","funders":"","keywords":"Resilience (materials science); Climate change; Extreme weather; Environmental science; Climate extremes; Climatology; Geography; Environmental resource management; Ecology; Geology; Biology","score_opus":0.09279450622727894,"score_gpt":0.3117577800378403,"score_spread":0.21896327381056138,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406384985","genre_codex":"dataset","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.041011237,0.030556686,0.0048844866,0.060791925,0.39628896,0.020757718,0.42037618,0.00047046304,0.024862355],"genre_scores_gemma":[0.022748088,0.0021603187,0.01204878,0.00214389,0.0033534751,0.0006821874,0.019928215,0.00013306884,0.93680197],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979349,0.00004298799,0.00023422041,0.0011080024,0.0003497971,0.00033009736],"domain_scores_gemma":[0.99841857,0.00013729285,0.00009688068,0.0012515278,0.0000145650465,0.000081140824],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013633511,0.0001929331,0.0002592229,0.00006980468,0.000856663,0.00022389054,0.0010495165,0.00008042833,0.000078999656],"category_scores_gemma":[0.00029829796,0.00013062527,0.000023922716,0.00038327125,0.0008114404,0.00028693123,0.0047598425,0.00017891884,0.000014048305],"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":[0.000025044752,0.000025216968,0.0007764563,0.00006908554,0.000010040899,6.994425e-7,0.00045657746,6.014014e-7,0.000102538055,0.00002345354,0.97068125,0.027829017],"study_design_scores_gemma":[0.00009249706,0.0000448037,0.013429167,0.00029144646,0.00006116827,0.0000028148859,0.0005218458,0.00080135296,0.000023241812,0.00006609416,0.984506,0.00015955225],"about_ca_topic_score_codex":0.00007775305,"about_ca_topic_score_gemma":0.00044194018,"teacher_disagreement_score":0.9119396,"about_ca_system_score_codex":0.000024684092,"about_ca_system_score_gemma":0.000019198966,"threshold_uncertainty_score":0.6588846},"labels":[],"label_agreement":null},{"id":"W4406438417","doi":"10.1038/s41597-024-04289-7","title":"Time series data on typhoid fever incidence during outbreaks from 2000 to 2022","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Salmonella and Campylobacter epidemiology","field":"Agricultural and Biological 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":"Public Health Ontario; University of Toronto","funders":"Bill and Melinda Gates Foundation","keywords":"Typhoid fever; Outbreak; Incidence (geometry); Paratyphoid fever; Virology; Series (stratigraphy); Medicine; Geography; Biology; Mathematics","score_opus":0.041881609053480345,"score_gpt":0.27675945089769405,"score_spread":0.2348778418442137,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406438417","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":[0.9740823,0.0002210421,0.0000042022157,0.004545106,0.001481412,0.00018529131,0.017909288,0.000085406005,0.0014859898],"genre_scores_gemma":[0.7830678,0.00006622671,0.0006485789,0.0036058137,0.0008619141,0.000023030381,0.061454233,0.0000041068743,0.1502683],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99751544,0.00013770543,0.00027330715,0.0014433562,0.0002470339,0.00038315894],"domain_scores_gemma":[0.997928,0.00027026344,0.00006595389,0.0015667892,0.000045135923,0.00012384144],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0010576582,0.00015638459,0.00021994452,0.00003376321,0.00045258645,0.0002529383,0.004075388,0.00008334015,0.0029039874],"category_scores_gemma":[0.00060488906,0.00006797225,0.000026519501,0.00077908486,0.00019366237,0.0005402461,0.0039951955,0.0001369438,0.0023158193],"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":[0.00009016793,0.00007702305,0.008241151,0.0000048487545,0.000025809215,0.000012962139,0.00006985334,0.0000052654773,0.31540695,0.00005017828,0.644964,0.0310518],"study_design_scores_gemma":[0.00008834525,0.000031776875,0.22951251,0.000052713604,0.000016729538,0.000003202764,0.00015039911,0.00019107526,0.0038051438,0.0005991184,0.76532084,0.00022813787],"about_ca_topic_score_codex":0.00067032356,"about_ca_topic_score_gemma":0.0015595772,"teacher_disagreement_score":0.3116018,"about_ca_system_score_codex":0.00003626576,"about_ca_system_score_gemma":0.000042964388,"threshold_uncertainty_score":0.998461},"labels":[],"label_agreement":null},{"id":"W4406617993","doi":"10.1038/s41597-024-04100-7","title":"Perceptions of science, science communication, and climate change attitudes in 68 countries – the TISP dataset","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Climate Change Communication and Perception","field":"Social Sciences","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Trinity Western University; University of Victoria; University of Alberta; Western University","funders":"NOMIS Stiftung; Universität Hamburg; Aston University; Vetenskapsrådet; Aarhus Universitets Forskningsfond; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; Eidgenössisches Departement für Umwelt, Verkehr, Energie und Kommunikation; Agence Nationale de la Recherche; John Templeton Foundation; Deutsche Forschungsgemeinschaft; Government of Canada; Genome Canada; Harvard University; Victoria University of Wellington; Resnick Sustainability Institute for Science, Energy and Sustainability, California Institute of Technology; European Commission; Trinity Western University; Fédération Wallonie-Bruxelles; Bill and Melinda Gates Foundation","keywords":"Climate change; Perception; Science communication; Climate science; Psychology; Open science; Data science; Science education; Ecology; Computer science; Biology; Statistics; Mathematics; Mathematics education","score_opus":0.4252245965880386,"score_gpt":0.5126555831040039,"score_spread":0.08743098651596537,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406617993","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":[0.81225437,0.00530309,0.000058222013,0.06217831,0.0030304126,0.0028113453,0.045578934,0.00016989317,0.068615414],"genre_scores_gemma":[0.9868387,0.009550086,0.00033603638,0.00031360987,0.000019573667,0.000028118495,0.0026434748,0.0000028451798,0.00026755812],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982111,0.00018662818,0.0002462393,0.00044602738,0.0005857915,0.00032419912],"domain_scores_gemma":[0.99641633,0.0001908967,0.0000986755,0.0029307567,0.0002991946,0.0000641539],"candidate_categories":["sts"],"consensus_categories":["sts"],"category_scores_codex":[0.01237181,0.00006959942,0.00010401202,0.0005109446,0.004994288,0.0008685206,0.004743275,0.00003119389,0.00030760176],"category_scores_gemma":[0.00067121896,0.000056769783,0.000009554659,0.003395657,0.027712505,0.0019307034,0.0031359072,0.000117234034,0.000044144817],"study_design_candidate":"observational","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":[0.000025760408,0.00045026478,0.30884138,0.00017344476,0.000009312858,4.5899208e-7,0.12502407,0.0000025941138,0.0050305105,0.42000172,0.08410148,0.056338996],"study_design_scores_gemma":[0.00017321415,0.0000060862603,0.43671858,0.00018860247,0.000014770085,5.9598204e-7,0.028972268,0.00050993275,0.000030462063,0.0007990639,0.5324642,0.00012218505],"about_ca_topic_score_codex":0.002458397,"about_ca_topic_score_gemma":0.03872852,"teacher_disagreement_score":0.44836274,"about_ca_system_score_codex":0.00009952933,"about_ca_system_score_gemma":0.0005045723,"threshold_uncertainty_score":0.99630105},"labels":[{"model":"gemma","categories":["sts"],"domain":null,"study_design":"observational","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"observational","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W4406639191","doi":"10.1038/s41597-025-04458-2","title":"‘DeltaCAN - A new data set of Canadian Arctic and subarctic coastal deltas’","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Methane Hydrates and Related Phenomena","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":true,"ca_institutions":"Nutrasource; Université du Québec à Rimouski; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Subarctic climate; Arctic; Oceanography; Geography; Data set; The arctic; Physical geography; Ecology; Environmental science; Geology; Biology; Statistics; Mathematics","score_opus":0.05409016079844076,"score_gpt":0.2735868980091791,"score_spread":0.21949673721073837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406639191","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":[0.79528785,0.0029842083,0.0013523266,0.016443158,0.0074765976,0.0021611988,0.06764569,0.00013257875,0.1065164],"genre_scores_gemma":[0.9661192,0.00008051925,0.00259983,0.00020866157,0.00003101459,0.0000015573097,0.010029218,0.000012338898,0.020917606],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982134,0.00005101169,0.00023974721,0.0008736519,0.00026889646,0.00035329926],"domain_scores_gemma":[0.9966745,0.00004723321,0.0000646077,0.002861408,0.0000114114555,0.00034084026],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0011102343,0.000116196585,0.00014667322,0.00024643936,0.0002451293,0.00015460215,0.0021144068,0.00005366119,0.0017847476],"category_scores_gemma":[0.00020824553,0.000100695914,0.0000118188,0.0014853133,0.0005624863,0.00049386855,0.003027725,0.00013974827,0.00014600014],"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":[0.000019646866,0.000051861232,0.02886807,0.00009888644,0.000085090265,0.000019447578,0.0006604426,0.00018018084,0.0036872874,0.0009138469,0.9187302,0.046685018],"study_design_scores_gemma":[0.0004991452,0.000026567961,0.016307008,0.00008685619,0.00012010099,0.000013515453,0.00032695627,0.0169887,0.00025002388,0.0036839019,0.96143407,0.00026318076],"about_ca_topic_score_codex":0.39540645,"about_ca_topic_score_gemma":0.54293716,"teacher_disagreement_score":0.17083141,"about_ca_system_score_codex":0.000049766626,"about_ca_system_score_gemma":0.00031776325,"threshold_uncertainty_score":0.99912775},"labels":[],"label_agreement":null},{"id":"W4406686892","doi":"10.1038/s41597-025-04452-8","title":"Data on insect biodiversity in a Chinese potato agroecosystem from DNA metabarcoding","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Environmental DNA in Biodiversity Studies","field":"Environmental Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"Agricultural Research Service; U.S. Department of Agriculture","keywords":"Biodiversity; Agroecosystem; Barcode; Biology; Taxon; PEST analysis; DNA barcoding; Insect pest; Insect; Ecology; Agroforestry; Crop; Solanum tuberosum; Geography; Agriculture; Agronomy; Botany","score_opus":0.05616166878685588,"score_gpt":0.2621959826184704,"score_spread":0.2060343138316145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406686892","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":[0.9618477,0.00012323492,0.00003174531,0.0004975885,0.0011870336,0.00030296922,0.032602917,0.000050063158,0.0033567436],"genre_scores_gemma":[0.98799825,0.000034737368,0.0015703492,0.00033672532,0.000017734208,0.0000031002726,0.0090865465,0.000005283311,0.0009472677],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9968839,0.000121117504,0.00025059615,0.0017943643,0.00057778216,0.00037219786],"domain_scores_gemma":[0.995662,0.00013913387,0.00008469692,0.004026343,0.0000031935806,0.00008468584],"candidate_categories":["open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0011375021,0.00022052371,0.00025066448,0.00016433338,0.000595055,0.00019662561,0.004769354,0.000057183675,0.0007541623],"category_scores_gemma":[0.00024252415,0.00019840285,0.00003378748,0.0009443235,0.0005621011,0.0010518976,0.016977761,0.00018338009,0.0033721167],"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":[0.000019640565,0.00014712909,0.8099095,0.00000834111,0.00003239502,0.000024105319,0.00019138523,0.00001617877,0.002945007,0.0000035788275,0.18548536,0.0012173229],"study_design_scores_gemma":[0.00053736323,0.000012221074,0.92803675,0.000049028902,0.000043486238,5.8594156e-7,0.0004962319,0.0012831982,0.000489039,0.00009577444,0.06870625,0.00025009512],"about_ca_topic_score_codex":0.002326819,"about_ca_topic_score_gemma":0.0049472465,"teacher_disagreement_score":0.11812718,"about_ca_system_score_codex":0.00030086172,"about_ca_system_score_gemma":0.000009859356,"threshold_uncertainty_score":0.99740386},"labels":[],"label_agreement":null},{"id":"W4406693740","doi":"10.1038/s41597-025-04409-x","title":"Hydrologic outputs generated over the Great Lakes with a calibrated version of the GEM-Hydro model","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Hydrology and Watershed Management Studies","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Waterloo; Environment and Climate Change Canada","funders":"","keywords":"Surface runoff; Streamflow; Environmental science; Water balance; Precipitation; Hydrology (agriculture); Snow; Drainage basin; Hydrological modelling; Surface water; Potential evaporation; Data assimilation; Climatology; Meteorology; Geography; Geology; Ecology","score_opus":0.02115464285611983,"score_gpt":0.22934834480210126,"score_spread":0.2081937019459814,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406693740","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":[0.9767345,0.00007076075,0.0008269756,0.004439806,0.00044088604,0.00042747447,0.00037980961,0.0000472661,0.016632479],"genre_scores_gemma":[0.9674088,0.0000060548805,0.000086931366,0.00072230474,0.0000050629865,0.000007919761,0.00016524279,0.000004302389,0.031593375],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998696,0.00009672905,0.00014552212,0.0005411591,0.00028242773,0.00023812764],"domain_scores_gemma":[0.99831194,0.0000295125,0.00007271931,0.0015552802,0.000009101707,0.000021467942],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006423629,0.00011922902,0.00011546153,0.000037843667,0.0007257745,0.000062285246,0.0016519376,0.000043844448,0.00050132186],"category_scores_gemma":[0.000034761862,0.000054415155,0.000025457286,0.00075431337,0.0014512182,0.000271656,0.002761066,0.000103833234,0.00014431766],"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":[0.000082334256,0.00010892761,0.051934,0.00001666523,0.000117075855,0.000004537447,0.0003520012,0.09283379,0.005712529,0.00031175307,0.84798986,0.00053653243],"study_design_scores_gemma":[0.00068014825,0.000035886133,0.02148328,0.000030811123,0.00017889038,0.0000012529249,0.0000694741,0.8454193,0.0033657127,0.0015293794,0.12701473,0.00019115474],"about_ca_topic_score_codex":0.000121194484,"about_ca_topic_score_gemma":0.00042285674,"teacher_disagreement_score":0.75258553,"about_ca_system_score_codex":0.000024637091,"about_ca_system_score_gemma":0.000019791847,"threshold_uncertainty_score":0.5582144},"labels":[],"label_agreement":null},{"id":"W4406823140","doi":"10.1038/s41597-025-04447-5","title":"DeepExtremeCubes: Earth system spatio-temporal data for assessing compound heatwave and drought impacts","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Remote Sensing in Agriculture","field":"Environmental Science","cited_by":7,"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":"Sächsisches Staatsministerium für Wissenschaft und Kunst; Bundesministerium für Wirtschaft und Energie; European Commission","keywords":"Biosphere; Ecosystem; Land cover; Computer science; Structuring; Earth observation; Event (particle physics); Earth system science; Climate change; Remote sensing; Environmental science; Satellite; Data mining; Earth science; Land use; Geography; Ecology; Geology","score_opus":0.04743203166249778,"score_gpt":0.29621963667475115,"score_spread":0.2487876050122534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406823140","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":[0.8034765,0.001560624,0.098456055,0.003995174,0.015492073,0.0048392727,0.022098849,0.000816074,0.049265362],"genre_scores_gemma":[0.9129989,0.0000048591414,0.060054865,0.0001227388,0.00012389338,0.0000017353178,0.021969728,0.000019393714,0.00470386],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972943,0.00009318762,0.00031883334,0.0014332131,0.0004463577,0.00041409524],"domain_scores_gemma":[0.9960535,0.0001418197,0.0001268966,0.003513633,0.000028184118,0.00013595786],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0018904442,0.00019646432,0.00022403296,0.00006514461,0.000777105,0.0015785831,0.0018418595,0.00008172825,0.00004663131],"category_scores_gemma":[0.00028398097,0.00015352211,0.000023211396,0.00062456843,0.00051503506,0.0017191338,0.0032523703,0.00012512309,0.00007536311],"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":[0.000023638118,0.000115289586,0.012060949,0.00030637954,0.00005640704,0.000023427703,0.00023964612,0.00011965411,0.010523197,0.00031007788,0.94416773,0.032053616],"study_design_scores_gemma":[0.00069842563,0.000019368454,0.025680719,0.00048018352,0.00011610132,0.00006479036,0.0010460225,0.30309188,0.00089319877,0.00025941335,0.66719663,0.00045328715],"about_ca_topic_score_codex":0.0004715729,"about_ca_topic_score_gemma":0.0028432654,"teacher_disagreement_score":0.30297223,"about_ca_system_score_codex":0.00011453565,"about_ca_system_score_gemma":0.00007014673,"threshold_uncertainty_score":0.9994579},"labels":[],"label_agreement":null},{"id":"W4406838870","doi":"10.1038/s41597-025-04498-8","title":"Chromosome-level genome assembly and annotation of the gynogenetic large-scale loach (Paramisgurnus dabryanus)","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ministry of Agriculture","funders":"Chinese Academy of Sciences; National Natural Science Foundation of China","keywords":"Biology; Genome; Cypriniformes; Cobitidae; Genetics; Sequence assembly; Gene; Reference genome; Chromosome; Evolutionary biology; Genome project; Computational biology; Fish <Actinopterygii>; Fishery","score_opus":0.029107682088781988,"score_gpt":0.26910009418465536,"score_spread":0.23999241209587338,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406838870","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":[0.98865867,0.0041285674,0.0010462645,0.00019914025,0.0007126165,0.000228538,0.0040880307,0.0000022530069,0.0009359149],"genre_scores_gemma":[0.9950066,0.00013783119,0.0010269309,0.00008839971,0.000046595993,0.000010230666,0.0008020427,0.000007832495,0.002873545],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9988063,0.00004812476,0.0002118332,0.0005855154,0.00013888498,0.00020932674],"domain_scores_gemma":[0.9982864,0.000012776353,0.000086844935,0.0014743042,0.000104415776,0.00003523226],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00049773656,0.000113738744,0.00012579176,0.00004533581,0.00026682141,0.00007113601,0.0008251238,0.00006380715,0.0000063478983],"category_scores_gemma":[0.000089924826,0.00008912385,0.000036524452,0.00024722383,0.00028210678,0.0000022647964,0.0014786387,0.000047323723,0.0000031847217],"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":[0.000010504605,0.00006160413,0.0038827697,0.00003949677,0.000063601175,2.321575e-7,0.00011466585,0.00004284267,0.98589563,0.00007565183,0.007795233,0.002017792],"study_design_scores_gemma":[0.00094808347,0.000080194164,0.39280054,0.0000359189,0.00013174336,0.000007910823,0.0005154867,0.0012544884,0.29937932,0.00047128266,0.30405346,0.00032157768],"about_ca_topic_score_codex":0.000011323705,"about_ca_topic_score_gemma":0.00016732006,"teacher_disagreement_score":0.6865163,"about_ca_system_score_codex":0.000006492237,"about_ca_system_score_gemma":0.000120900164,"threshold_uncertainty_score":0.36343652},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"bench_or_experimental","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W4406872169","doi":"10.1038/s41597-025-04465-3","title":"The UnconTrust Database for Studies of Unconscious Semantic Processing and Attentional Allocation","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Neural and Behavioral Psychology Studies","field":"Neuroscience","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":"Canadian Institute for Advanced Research","funders":"Templeton World Charity Foundation; Canadian Institute for Advanced Research","keywords":"Unconscious mind; Computer science; Scope (computer science); Field (mathematics); Information processing; Database; Diversity (politics); Data science; Cognitive psychology; Psychology; Sociology","score_opus":0.31316931525912817,"score_gpt":0.45988314866995456,"score_spread":0.1467138334108264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406872169","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":[0.97321546,0.0050258115,0.0007072406,0.012791163,0.0043270397,0.00092693226,0.002766799,0.000053665062,0.0001858904],"genre_scores_gemma":[0.9945668,0.00011500546,0.00019587531,0.00019308508,0.000021031528,0.000027935668,0.00012224642,0.0000032434857,0.004754778],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988812,0.000041588402,0.0002012975,0.0005669401,0.00015351779,0.00015545198],"domain_scores_gemma":[0.99881077,0.00036022207,0.00009129014,0.0005905854,0.00013070424,0.000016432588],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00078269735,0.00007426344,0.00010969409,0.000058759313,0.0011509443,0.00012443648,0.00055370055,0.000014071056,0.0000012179335],"category_scores_gemma":[0.0009901288,0.000045093915,0.000015930218,0.00033282023,0.0015812649,0.0002756579,0.00060344825,0.00004824928,0.000002463514],"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":[0.00007774026,0.00015221951,0.0030845792,0.00028672875,0.00002929189,0.0000025614875,0.00017260418,0.0000013446413,0.7604239,0.0030393165,0.16053055,0.07219914],"study_design_scores_gemma":[0.0052350266,0.0003047335,0.020264292,0.0013772228,0.0010377022,0.000056657675,0.00943398,0.008320908,0.5985019,0.06062708,0.29378048,0.0010599683],"about_ca_topic_score_codex":0.0000038516373,"about_ca_topic_score_gemma":0.00016694852,"teacher_disagreement_score":0.16192196,"about_ca_system_score_codex":0.0000072036155,"about_ca_system_score_gemma":0.000050552535,"threshold_uncertainty_score":0.8852249},"labels":[],"label_agreement":null},{"id":"W4407063052","doi":"10.1038/s41597-025-04382-5","title":"Investigating the Quality of DermaMNIST and Fitzpatrick17k Dermatological Image Datasets","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Cutaneous Melanoma Detection and Management","field":"Medicine","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Alliance de recherche numérique du Canada; Natural Sciences and Engineering Research Council of Canada; Government of Canada; Simon Fraser University; Nvidia","keywords":"Quality (philosophy); Computer science; Information retrieval; Dermatology; Medicine; Physics","score_opus":0.0761432071486184,"score_gpt":0.3701774839851385,"score_spread":0.2940342768365201,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407063052","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":[0.9559217,0.0009566946,0.003993323,0.01592031,0.0017426129,0.001261771,0.0060189655,0.00015116995,0.014033441],"genre_scores_gemma":[0.99133927,0.000014074878,0.002611226,0.000894598,0.000019638414,0.000004884916,0.0031219495,0.0000036652425,0.001990682],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99893963,0.000078686986,0.00027237763,0.0003700758,0.00021840422,0.00012082891],"domain_scores_gemma":[0.998282,0.00012565505,0.00008230684,0.00141305,0.00004196624,0.00005502294],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011568873,0.00006538351,0.00014572407,0.00007924613,0.0002517846,0.00011763448,0.00038072464,0.000025175537,0.000057294856],"category_scores_gemma":[0.0009916539,0.00004199691,0.000018590024,0.00038295196,0.0006280834,0.000087369604,0.0009920235,0.00009703984,0.0000145664835],"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":[0.000032536078,0.00014939846,0.011218739,0.0006189488,0.000079328056,0.000037210375,0.00015237975,5.6704084e-7,0.030734913,0.004210722,0.92940253,0.023362724],"study_design_scores_gemma":[0.0012764387,0.000033695535,0.0791617,0.00016000311,0.00025501434,0.00024033822,0.0015004117,0.004431455,0.010586571,0.0016944973,0.9004651,0.00019481499],"about_ca_topic_score_codex":0.000053312117,"about_ca_topic_score_gemma":0.00005333485,"teacher_disagreement_score":0.06794296,"about_ca_system_score_codex":0.000009980584,"about_ca_system_score_gemma":0.00006128934,"threshold_uncertainty_score":0.23141995},"labels":[],"label_agreement":null},{"id":"W4407065613","doi":"10.1038/s41597-025-04396-z","title":"Bias-corrected high-resolution temperature and precipitation projections for Canada","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Climate variability and models","field":"Environmental Science","cited_by":8,"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 Manitoba; University of Saskatchewan; University of Calgary","funders":"Global Water Futures","keywords":"Precipitation; Environmental science; Climatology; Geography; Geology; Meteorology","score_opus":0.036079763683100945,"score_gpt":0.26615225314414787,"score_spread":0.23007248946104691,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407065613","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":[0.9844262,0.000030361265,0.002464143,0.0017257164,0.0032142776,0.00091814843,0.006099196,0.00005168087,0.0010702879],"genre_scores_gemma":[0.9751013,0.0000051183165,0.004229041,0.00017007919,0.000027406473,0.000069287606,0.008158014,0.0000059245867,0.012233849],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99901605,0.00003049909,0.0001233211,0.0005286506,0.0001476857,0.00015377978],"domain_scores_gemma":[0.99919325,0.000090252004,0.000030809428,0.00062870915,0.000020817406,0.000036166006],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005829207,0.00006260402,0.00006152628,0.00003698373,0.0005041499,0.00015595593,0.00028525342,0.0000376566,0.000082960556],"category_scores_gemma":[0.00038666377,0.00005686538,0.000007910979,0.00044306068,0.00014479294,0.00032999323,0.0003576128,0.000053568896,0.0000045187676],"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":[0.00002241477,0.000071072674,0.0019774728,0.0000423674,0.000009779861,2.4219298e-7,0.00019472206,0.00163514,0.017931933,0.0008804133,0.97316647,0.0040679644],"study_design_scores_gemma":[0.0010239194,0.000042201416,0.05052023,0.000077366916,0.000098339806,0.000003439687,0.0005560568,0.34825438,0.002659063,0.0065044076,0.5898705,0.000390045],"about_ca_topic_score_codex":0.18335016,"about_ca_topic_score_gemma":0.75231326,"teacher_disagreement_score":0.5689631,"about_ca_system_score_codex":0.00018765165,"about_ca_system_score_gemma":0.00020296467,"threshold_uncertainty_score":0.822088},"labels":[],"label_agreement":null},{"id":"W4407238378","doi":"10.1038/s41597-025-04547-2","title":"A single-nucleus RNA sequencing atlas of the postnatal retina of the shark Scyliorhinus canicula","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"European Regional Development Fund; Natural Sciences and Engineering Research Council of Canada; Xunta de Galicia; European Commission; Biotechnology and Biological Sciences Research Council; Spanish National Plan for Scientific and Technical Research and Innovation; Agencia Estatal de Investigación; Ministerio de Ciencia, Innovación y Universidades","keywords":"Scyliorhinus canicula; Biology; Retina; Vertebrate; Retinal; Anatomy; Evolutionary biology; Neuroscience; Genetics; Fishery","score_opus":0.029446579591905907,"score_gpt":0.24564587453646644,"score_spread":0.21619929494456053,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407238378","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":[0.99342453,0.00034654373,0.00010174772,0.0001926604,0.0017154851,0.00018763042,0.001835826,0.000005197504,0.0021903554],"genre_scores_gemma":[0.9967799,0.0000051753136,0.00020777219,0.00009007217,0.000038013604,0.0000013597597,0.00035905978,0.00000851112,0.002510112],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987893,0.000072033734,0.00026499643,0.00045771684,0.00023226922,0.00018367096],"domain_scores_gemma":[0.9975025,0.000014307302,0.00013629218,0.0021964582,0.00012265012,0.000027811393],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004978523,0.00010588711,0.000120808254,0.00003360553,0.00020562513,0.00006602072,0.0020247118,0.00007979231,0.000012685585],"category_scores_gemma":[0.0002922057,0.000066541186,0.00010140791,0.0004213034,0.00052446366,0.000009137901,0.0011121464,0.00010025111,0.0000014240586],"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":[0.000019910007,0.00004260295,0.0006579387,0.00003860088,0.000026845517,7.244334e-7,0.00007005578,0.0000134422025,0.9884376,0.00009880237,0.009914339,0.0006791205],"study_design_scores_gemma":[0.0002148151,0.00002362195,0.0012863299,0.000116558,0.000041158586,0.0000066178673,0.000109736924,0.0003127076,0.97401804,0.000041431795,0.023748687,0.000080283324],"about_ca_topic_score_codex":0.00024768108,"about_ca_topic_score_gemma":0.00047670997,"teacher_disagreement_score":0.014419566,"about_ca_system_score_codex":0.000023347931,"about_ca_system_score_gemma":0.00036079003,"threshold_uncertainty_score":0.37624517},"labels":[],"label_agreement":null},{"id":"W4407251531","doi":"10.1038/s41597-025-04548-1","title":"An Integrated Database for Exploring Alternative Promoters in Animals","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","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":"Ministry of Agriculture","funders":"Huazhong Agricultural University; Fundamental Research Funds for the Central Universities; Natural Science Foundation of Hubei Province; National Natural Science Foundation of China","keywords":"Biology; Promoter; Enhancer; Computational biology; Database; Transcription factor; Transcription (linguistics); Genetics; Gene expression; Gene; Computer science","score_opus":0.06597041708514718,"score_gpt":0.3276484842748255,"score_spread":0.26167806718967834,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407251531","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":[0.96731275,0.000110188565,0.024314385,0.0001353562,0.00082411076,0.0003584815,0.0068142856,0.000009170517,0.000121289915],"genre_scores_gemma":[0.9530649,0.000026608204,0.014268668,0.00008150227,0.0000466249,0.00005987802,0.03195794,0.000012432695,0.000481428],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99891603,0.000026826603,0.00015951337,0.0006536936,0.000062014275,0.00018195185],"domain_scores_gemma":[0.9985405,0.0000071712752,0.000039698065,0.0013145024,0.000060809358,0.000037321355],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006605183,0.000086544285,0.00008033191,0.00009077423,0.00008405497,0.00014099812,0.000958276,0.000032663444,0.0000049837117],"category_scores_gemma":[0.0001320095,0.00008399108,0.000016839558,0.00018127276,0.00007763119,0.000018247283,0.00045501333,0.00004386878,0.000002313064],"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":[0.000067154375,0.00013925439,0.0005640669,0.000051732022,0.00003212656,0.000002431779,0.00011341111,0.00019624157,0.972062,0.000850322,0.013960919,0.011960356],"study_design_scores_gemma":[0.0016775897,0.0002359559,0.001199665,0.00016304763,0.00003407257,0.0000028097313,0.0015467649,0.18807735,0.33741644,0.001325021,0.4678196,0.0005016682],"about_ca_topic_score_codex":0.000041798896,"about_ca_topic_score_gemma":0.0003881095,"teacher_disagreement_score":0.6346455,"about_ca_system_score_codex":0.000016690126,"about_ca_system_score_gemma":0.00012607659,"threshold_uncertainty_score":0.3425057},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W4407251902","doi":"10.1038/s41597-025-04491-1","title":"BenthicNet: A global compilation of seafloor images for deep learning applications","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Underwater Acoustics Research","field":"Earth and Planetary Sciences","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":"Tula Foundation; Fisheries and Oceans Canada; Dalhousie University; Memorial University of Newfoundland; Bedford Institute of Oceanography; Vector Institute","funders":"Alliance de recherche numérique du Canada; Hakai Institute; Ocean Frontier Institute; Australian Centre for Field Robotics; Atlantic Canada Opportunities Agency; University of Tasmania; Australian Government","keywords":"Seafloor spreading; Geology; Deep learning; Computer science; Artificial intelligence; Oceanography","score_opus":0.04507460497129716,"score_gpt":0.33209781881484973,"score_spread":0.28702321384355256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407251902","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":[0.0015437029,0.00040047275,0.96842957,0.0003252876,0.00037987818,0.0006833808,0.01869166,0.000041722422,0.0095043015],"genre_scores_gemma":[0.9451515,0.000010577163,0.025235668,0.00002192302,0.000038923423,0.000007037618,0.026717104,0.000001927515,0.0028153553],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988583,0.000043228807,0.00017456808,0.0004206581,0.0002853797,0.00021786765],"domain_scores_gemma":[0.9989096,0.00015527724,0.000050806255,0.0006723692,0.00015983323,0.000052135227],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010059297,0.000059295562,0.00008885956,0.00010686566,0.0003830246,0.00024251026,0.0009501945,0.000031672276,0.00029321614],"category_scores_gemma":[0.00013874558,0.000053256066,0.000020574938,0.000678071,0.00026313093,0.00024085383,0.00013800155,0.00007285482,0.00008073216],"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":[0.00007948548,0.00011445582,0.25153586,0.00048219805,0.000084792526,0.0000010194071,0.00014132197,0.06932978,0.0021147889,0.0007894556,0.05818655,0.6171403],"study_design_scores_gemma":[0.0002723723,0.000027546394,0.051794298,0.00001990216,0.00003178728,8.7715426e-7,0.00021808506,0.8187116,0.0005195136,0.0052739508,0.12303465,0.000095464806],"about_ca_topic_score_codex":0.00018301076,"about_ca_topic_score_gemma":0.0009984907,"teacher_disagreement_score":0.9436078,"about_ca_system_score_codex":0.000006997903,"about_ca_system_score_gemma":0.0001350117,"threshold_uncertainty_score":0.32105112},"labels":[],"label_agreement":null},{"id":"W4407391025","doi":"10.1038/s41597-025-04544-5","title":"A high resolution, gridded product for vapor pressure deficit using Daymet","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Climate variability and models","field":"Environmental Science","cited_by":6,"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 Science Foundation","keywords":"Vapour Pressure Deficit; Product (mathematics); Vapor pressure; Environmental science; Resolution (logic); Computer science; Thermodynamics; Mathematics; Botany; Physics; Biology; Transpiration; Artificial intelligence","score_opus":0.07467332530574496,"score_gpt":0.3049825374918117,"score_spread":0.23030921218606676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407391025","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":[0.8069911,0.0008272933,0.112947255,0.0048850197,0.013150846,0.0052535133,0.050226692,0.00040483824,0.005313456],"genre_scores_gemma":[0.8945514,0.000007901482,0.07637368,0.00025350525,0.00015358781,0.00007668254,0.008815712,0.00002709098,0.019740462],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979051,0.00005218671,0.00025749023,0.001159046,0.00027624168,0.0003499367],"domain_scores_gemma":[0.99739516,0.00006667444,0.00006981485,0.002382671,0.00002769758,0.000057986308],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021363434,0.00011452864,0.00014039673,0.000062197076,0.00059306325,0.00022883042,0.0012063014,0.000045801193,0.0005544865],"category_scores_gemma":[0.0005559102,0.00010496871,0.000033318847,0.0006254231,0.0003779174,0.0005569811,0.001547832,0.00007318211,0.000069114234],"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":[0.00009802412,0.0004850076,0.00304196,0.00023702635,0.000058681293,0.0000015224897,0.00028039527,0.04612953,0.07053265,0.0061284164,0.8685201,0.004486733],"study_design_scores_gemma":[0.00048112863,0.000015512176,0.0017994706,0.000047314345,0.00015071659,0.0000025396548,0.00005113497,0.27161017,0.0025835433,0.01182741,0.71117836,0.00025270824],"about_ca_topic_score_codex":0.00046492618,"about_ca_topic_score_gemma":0.00023722151,"teacher_disagreement_score":0.22548063,"about_ca_system_score_codex":0.000068036,"about_ca_system_score_gemma":0.00007091089,"threshold_uncertainty_score":0.60712385},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W4407574495","doi":"10.1038/s41597-025-04532-9","title":"A chromosome-level genome assembly of Mylabris sibirica Fischer von Waldheim, 1823 (Coleoptera, Meloidae)","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Beetle Biology and Toxicology Studies","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":"","keywords":"Biology; Chromosome; Zoology; Genetics; Gene","score_opus":0.047848173343356344,"score_gpt":0.30340353535684067,"score_spread":0.25555536201348433,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407574495","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":[0.97487485,0.004818422,0.00083192624,0.0013625541,0.0020637831,0.00039312092,0.004125503,0.00003094976,0.0114988675],"genre_scores_gemma":[0.9667681,0.00011372701,0.00096163637,0.00034336816,0.0001117139,0.000020405532,0.0031686572,0.000010746885,0.028501656],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99815315,0.00009533433,0.00032088827,0.00095439865,0.0001285622,0.0003476914],"domain_scores_gemma":[0.99781936,0.000033918586,0.00012395458,0.0018281603,0.00013776874,0.000056818168],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007228917,0.00018470272,0.00026012477,0.00011238765,0.00027234465,0.000042807642,0.0012713281,0.00025426855,0.00007970063],"category_scores_gemma":[0.00030973216,0.00016465044,0.00007094979,0.0003606983,0.0007419263,0.000013130502,0.0017304838,0.00012554097,0.00006675118],"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":[0.000064112945,0.00021665792,0.0034618045,0.00004306949,0.0003194327,0.0000038552935,0.000042246193,0.000002553573,0.8212231,0.00014005155,0.17239657,0.002086569],"study_design_scores_gemma":[0.0007100053,0.00017462287,0.06681543,0.000030485655,0.000106235464,0.000004690675,0.00009608867,0.000047604975,0.25321117,0.00012347629,0.67838246,0.0002977222],"about_ca_topic_score_codex":0.000020617497,"about_ca_topic_score_gemma":0.00024026673,"teacher_disagreement_score":0.56801194,"about_ca_system_score_codex":0.0000135253285,"about_ca_system_score_gemma":0.0001980393,"threshold_uncertainty_score":0.671425},"labels":[],"label_agreement":null},{"id":"W4407635770","doi":"10.1038/s41597-025-04580-1","title":"A semantic approach to mapping the Provenance Ontology to Basic Formal Ontology","year":2025,"lang":"en","type":"article","venue":"Scientific Data","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":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Ontology; Upper ontology; Ontology-based data integration; Information retrieval; Variety (cybernetics); Open Biomedical Ontologies; Interoperability; OWL-S; Process ontology; SPARQL; Ontology alignment; Semantic Web; Formal ontology; Consistency (knowledge bases); Suggested Upper Merged Ontology; Ontology components; World Wide Web; Semantic Web Stack; RDF; Artificial intelligence","score_opus":0.3061377680787358,"score_gpt":0.40577316655683815,"score_spread":0.09963539847810238,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407635770","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":[0.03457638,0.00021124212,0.8205706,0.028384939,0.01809822,0.002169419,0.0010322263,0.00018687393,0.09477012],"genre_scores_gemma":[0.8257139,0.000001094744,0.030058792,0.006733765,0.00018989193,0.00012510752,0.0006838004,0.000016683047,0.13647701],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9932337,0.000330531,0.00089390407,0.0030821182,0.0014958803,0.0009638695],"domain_scores_gemma":[0.9880857,0.0007194099,0.00018411705,0.010496263,0.00031240177,0.0002020973],"candidate_categories":["sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.023147332,0.00021620159,0.00037394473,0.0010911695,0.0013979779,0.0027324427,0.013089437,0.000058645557,0.00008515029],"category_scores_gemma":[0.0076124086,0.00013670097,0.00007402443,0.0066182995,0.00042796016,0.00075270125,0.011844088,0.00019986717,0.0019737096],"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":[0.00001470541,0.00009146073,0.0003805746,0.000012295103,0.000016063274,0.000003053911,0.00087592745,0.0002894986,0.00013056873,0.019999897,0.8168173,0.1613687],"study_design_scores_gemma":[0.00018739952,0.000019849675,0.008847006,0.00003915389,0.00001590789,0.000008758831,0.0020425576,0.040572014,0.000034565,0.007829003,0.9402239,0.0001799154],"about_ca_topic_score_codex":0.00016139323,"about_ca_topic_score_gemma":0.00093384535,"teacher_disagreement_score":0.79113746,"about_ca_system_score_codex":0.000062305444,"about_ca_system_score_gemma":0.00027188164,"threshold_uncertainty_score":0.99990207},"labels":[],"label_agreement":null},{"id":"W4407856910","doi":"10.1038/s41597-025-04630-8","title":"A standardized lexicon of body odor words crafted from 17 countries","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Olfactory and Sensory Function Studies","field":"Neuroscience","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary; Western University","funders":"","keywords":"Operationalization; Digitization; Nonverbal communication; Odor; Perception; Cognitive psychology; Lexicon; Computer science; Psychology; Communication; Natural language processing; Computer vision","score_opus":0.15883060814098482,"score_gpt":0.328983230531369,"score_spread":0.1701526223903842,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407856910","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":[0.9040474,0.00055604725,0.0041200127,0.0020449874,0.0130841695,0.0005923208,0.056451086,0.00029460556,0.018809343],"genre_scores_gemma":[0.95185864,0.000026653883,0.00020269696,0.00043690277,0.000050826915,0.000005942835,0.0004965709,0.000008249078,0.046913546],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99799484,0.00012836834,0.00031351484,0.0008572878,0.00048295318,0.00022305394],"domain_scores_gemma":[0.9976323,0.00040659224,0.00011457321,0.001690458,0.00011122947,0.000044842862],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006144842,0.00012672947,0.00025504042,0.00017179796,0.0005362327,0.0002695672,0.0009253747,0.000042484557,0.00080847956],"category_scores_gemma":[0.0016470586,0.00010694523,0.000042963413,0.00071497005,0.0008901706,0.000462057,0.00071346556,0.00010265723,0.00010747606],"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":[0.00039965138,0.00011599081,0.0013931266,0.000040526807,0.00004519194,0.0000092347245,0.0006483718,0.0000061646842,0.4098457,0.0030738201,0.58339214,0.0010300729],"study_design_scores_gemma":[0.00058485894,0.000016929327,0.0013465293,0.000047940317,0.000038272014,4.0858967e-7,0.0003727782,0.0002827967,0.23077182,0.0015198741,0.76490355,0.00011423056],"about_ca_topic_score_codex":0.000024675475,"about_ca_topic_score_gemma":0.00006884499,"teacher_disagreement_score":0.18151142,"about_ca_system_score_codex":0.000024864737,"about_ca_system_score_gemma":0.00021142782,"threshold_uncertainty_score":0.88522846},"labels":[],"label_agreement":null},{"id":"W4407877295","doi":"10.1038/s41597-025-04451-9","title":"Applying the FAIR Principles to computational workflows","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Scientific Computing and Data Management","field":"Decision Sciences","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":"Ontario Institute for Cancer Research","funders":"Biotechnology and Biological Sciences Research Council; Agence Nationale de la Recherche","keywords":"Workflow; Computer science; Data science; Database","score_opus":0.356785298571699,"score_gpt":0.4538253241408091,"score_spread":0.09704002556911012,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407877295","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":[0.014293517,0.00029724382,0.86255145,0.023841914,0.027771607,0.0033360615,0.0031958444,0.00034633226,0.06436605],"genre_scores_gemma":[0.573618,0.0000018364693,0.078519545,0.0060242303,0.0003839024,0.0003958403,0.0037482246,0.00002449469,0.33728394],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9943949,0.00019037067,0.0006803389,0.0020324395,0.0023121869,0.00038979345],"domain_scores_gemma":[0.9901741,0.0014982703,0.00014108856,0.007737023,0.00032783224,0.000121681966],"candidate_categories":["sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.021551134,0.00013577419,0.00016970746,0.00062338496,0.0016049718,0.005858323,0.010797701,0.000025601576,0.00030559514],"category_scores_gemma":[0.0062630577,0.000083133906,0.000055002864,0.0052814623,0.00034971238,0.00051330903,0.010236524,0.00012606257,0.0027112428],"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":[0.0000039099045,0.000027041688,0.00045669213,0.0000020584273,0.00000865666,0.0000012798831,0.00009823188,0.01110908,0.000013544399,0.012424784,0.7265278,0.24932694],"study_design_scores_gemma":[0.00007959484,0.000002828871,0.004067181,0.000021390377,0.000008561015,7.593988e-7,0.00058752036,0.13038339,0.0000102261,0.018672796,0.84607977,0.00008595817],"about_ca_topic_score_codex":0.000023350194,"about_ca_topic_score_gemma":0.00015745425,"teacher_disagreement_score":0.78403187,"about_ca_system_score_codex":0.00003647049,"about_ca_system_score_gemma":0.00021921564,"threshold_uncertainty_score":0.9996948},"labels":[],"label_agreement":null},{"id":"W4408067639","doi":"10.1038/s41597-025-04621-9","title":"A dataset on formulation parameters and characteristics of drug-loaded PLGA microparticles","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Advanced Drug Delivery Systems","field":"Pharmacology, Toxicology and Pharmaceutics","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Structural Genomics Consortium; University of Toronto","funders":"","keywords":"PLGA; Drug; Chemistry; Nanotechnology; Materials science; Pharmacology; Medicine; Nanoparticle","score_opus":0.16381189512461256,"score_gpt":0.4457319390361242,"score_spread":0.2819200439115116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408067639","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":[0.94714606,0.00020255211,0.00040102264,0.00034381676,0.0021076952,0.00038681927,0.04922865,0.000026769405,0.00015662462],"genre_scores_gemma":[0.9826973,0.000018984569,0.00050194375,0.00035773293,0.000022244472,0.000008073907,0.015601829,0.000006524293,0.0007853755],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99856216,0.0001856487,0.00036662447,0.0005187004,0.00013436996,0.00023249931],"domain_scores_gemma":[0.99834275,0.00034870117,0.0001642982,0.0010054067,0.00005773055,0.000081135],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011454452,0.000120871046,0.00019512049,0.00015747511,0.0002284132,0.000058308975,0.0005802836,0.00007404834,0.00005838729],"category_scores_gemma":[0.00024695936,0.000114311966,0.000016920769,0.0002994037,0.00035851268,0.0002844022,0.00045573025,0.00019100893,0.00006814104],"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":[0.0006498488,0.0005060497,0.011912774,0.00033983262,0.00020572751,0.000016175136,0.0008262233,0.00020757613,0.40278983,0.0022569078,0.482464,0.09782508],"study_design_scores_gemma":[0.0014169432,0.00003808775,0.0055529443,0.000101002195,0.00018855243,0.00000514507,0.00029906278,0.022071537,0.21030678,0.0005437385,0.7592272,0.0002489673],"about_ca_topic_score_codex":0.000015126132,"about_ca_topic_score_gemma":0.000015046845,"teacher_disagreement_score":0.27676326,"about_ca_system_score_codex":0.000024128809,"about_ca_system_score_gemma":0.000055235196,"threshold_uncertainty_score":0.46615067},"labels":[],"label_agreement":null},{"id":"W4408170081","doi":"10.1038/s41597-025-04724-3","title":"Multifaceted and extensive behavioral trajectories of genomically diverse Drosophila lines","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Neurobiology and Insect Physiology Research","field":"Neuroscience","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 Genetics; ACT-X; Japan Science and Technology Agency; Japan Society for the Promotion of Science; Japan Science Society","keywords":"Drosophila (subgenus); Computational biology; Evolutionary biology; Computer science; Biology; Genetics; Gene","score_opus":0.11419918126394273,"score_gpt":0.3710138542053832,"score_spread":0.25681467294144045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408170081","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":[0.9964853,0.00005563802,0.000007788606,0.00019027092,0.0010530669,0.00019051446,0.0018348244,0.000028026128,0.00015457145],"genre_scores_gemma":[0.9978185,0.000024274901,0.0001167697,0.00011628394,0.000018468956,0.0000038308317,0.0001937484,0.000004249182,0.0017038661],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99849236,0.00015373023,0.00018458946,0.00081787363,0.00011723291,0.00023420753],"domain_scores_gemma":[0.99854124,0.00021451077,0.00005499577,0.0010451936,0.00009588327,0.00004816687],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003046726,0.0000970996,0.00017166985,0.00015638913,0.00034306414,0.00006139471,0.0009996557,0.000065201166,0.00004563707],"category_scores_gemma":[0.0008409538,0.00008196772,0.000023079236,0.00042909235,0.0024360048,0.0002474829,0.0014139481,0.00016685664,0.000023831453],"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":[0.00006331943,0.00009277215,0.0013505326,0.000014348443,0.000003500442,0.0000059660506,0.00010453965,0.000001144414,0.9925592,0.00051036227,0.004310491,0.0009838337],"study_design_scores_gemma":[0.00058866123,0.000116644784,0.036550585,0.000024264651,0.000028753757,0.000008849256,0.00015516252,0.0005475057,0.9558953,0.0013905236,0.004546362,0.00014739936],"about_ca_topic_score_codex":0.000022174496,"about_ca_topic_score_gemma":0.0000144425585,"teacher_disagreement_score":0.0366639,"about_ca_system_score_codex":0.00000590324,"about_ca_system_score_gemma":0.00010211098,"threshold_uncertainty_score":0.8975561},"labels":[],"label_agreement":null},{"id":"W4408195974","doi":"10.1038/s41597-025-04715-4","title":"A Comprehensive Dataset of Surface Water Quality Spanning 1940-2023 for Empirical and ML Adopted Research","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Water Quality and Pollution Assessment","field":"Environmental Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Water quality; Quality (philosophy); Environmental science; Surface water; Data science; Computer science; Biology; Ecology; Environmental engineering; Physics","score_opus":0.4412245770869852,"score_gpt":0.520185085393014,"score_spread":0.0789605083060288,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408195974","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":[0.93944967,0.000070216556,0.0018512757,0.004191236,0.00073661853,0.00065797335,0.052347414,0.000022967353,0.0006726017],"genre_scores_gemma":[0.93532294,0.000009236838,0.009065219,0.00046675192,0.000031175226,0.000017111377,0.046967372,0.000010568412,0.008109631],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99755865,0.00039406182,0.00036816165,0.0007744992,0.00053034356,0.00037428434],"domain_scores_gemma":[0.99801534,0.0002932935,0.00005172222,0.0015045224,0.000046164583,0.000088968234],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0056786863,0.00009186316,0.00017357143,0.000069296875,0.000517057,0.00017425824,0.0009252465,0.000050530998,0.00038721066],"category_scores_gemma":[0.00015320281,0.00006934122,0.000019891546,0.00045984815,0.001295996,0.00034111695,0.0030315446,0.00013673537,0.00015265669],"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":[0.00006211922,0.00013396711,0.009434135,0.00013463985,0.000021285392,0.0000011160984,0.00068404246,0.00011607091,0.03352586,0.00018830958,0.9547334,0.0009650591],"study_design_scores_gemma":[0.0003916841,0.000025300658,0.032311857,0.000028415314,0.000012489317,6.060114e-7,0.00052302756,0.0021487307,0.010073048,0.0011269767,0.95324785,0.00011001608],"about_ca_topic_score_codex":0.0008667393,"about_ca_topic_score_gemma":0.00023038004,"teacher_disagreement_score":0.023452815,"about_ca_system_score_codex":0.000053181528,"about_ca_system_score_gemma":0.000041456864,"threshold_uncertainty_score":0.47751513},"labels":[],"label_agreement":null},{"id":"W4408279735","doi":"10.1038/s41597-024-04193-0","title":"Harnessing Smartphone Sensors for Enhanced Road Safety: A Comprehensive Dataset and Review","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Data science","score_opus":0.027734023176698493,"score_gpt":0.29099685300039113,"score_spread":0.26326282982369265,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408279735","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10737917,0.25490168,0.26133323,0.012443438,0.014670134,0.007423353,0.33017957,0.004485193,0.007184207],"genre_scores_gemma":[0.5608331,0.028048584,0.04340159,0.0038821169,0.00022292965,0.00029685925,0.35341343,0.00018210895,0.009719269],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988852,0.000020355184,0.0002595773,0.0005161467,0.00007452755,0.00024415719],"domain_scores_gemma":[0.99828213,0.00007395177,0.000034773726,0.0015291572,0.000041718027,0.000038255148],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005097731,0.00012958694,0.00024805532,0.00009852823,0.00030600105,0.000073088035,0.0006017243,0.00007153917,0.000031504525],"category_scores_gemma":[0.00011029857,0.00012749006,0.000018544288,0.00037194838,0.00026878194,0.0002516494,0.00045091545,0.0001311782,0.000037840535],"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":[0.000017008884,0.000019106397,0.000010401725,0.0018360226,0.000081656115,0.0000033659833,0.00004169092,0.00009742556,0.0115938615,0.0004442999,0.663863,0.32199216],"study_design_scores_gemma":[0.00036123005,0.000005446994,0.0004766426,0.0007517498,0.000072961506,0.000004789233,0.000048474005,0.02094821,0.0044890507,0.00032071647,0.9723357,0.0001850418],"about_ca_topic_score_codex":0.0000044855256,"about_ca_topic_score_gemma":0.000022991055,"teacher_disagreement_score":0.45345393,"about_ca_system_score_codex":0.000026737713,"about_ca_system_score_gemma":0.000047647478,"threshold_uncertainty_score":0.51988935},"labels":[],"label_agreement":null},{"id":"W4408429731","doi":"10.1038/s41597-025-04763-w","title":"Electromyographic typing gesture classification dataset for neurotechnological human-machine interfaces","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Muscle activation and electromyography studies","field":"Engineering","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":"Toronto Rehabilitation Institute; University of Toronto; University Health Network","funders":"","keywords":"Session (web analytics); Computer science; Task (project management); Electromyography; Typing; Interface (matter); Gesture; Artificial intelligence; Key (lock); Machine learning; Speech recognition; Human–computer interaction; Pattern recognition (psychology); Physical medicine and rehabilitation; Medicine; Engineering; World Wide Web","score_opus":0.05592928662354131,"score_gpt":0.31274121495168883,"score_spread":0.25681192832814753,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408429731","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":[0.432114,0.016537555,0.39475146,0.022340322,0.012665126,0.006504206,0.096708834,0.00812184,0.010256662],"genre_scores_gemma":[0.9746858,0.00007343866,0.00089830486,0.00008026137,0.000026199876,0.00006454329,0.023975266,0.000012045136,0.00018416165],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988968,0.000017581515,0.00020102301,0.000515526,0.000097323755,0.000271774],"domain_scores_gemma":[0.99862695,0.000058056085,0.000033061937,0.0012134727,0.000042707452,0.00002575081],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038438285,0.00013430727,0.00013348713,0.00038686013,0.00043424414,0.00021588181,0.0009971672,0.000072663315,0.000016465769],"category_scores_gemma":[0.00011747381,0.000121579425,0.000029241884,0.0010810352,0.0001548231,0.00029642033,0.00022526966,0.00020592305,0.0000027285034],"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":[0.000008806606,0.00006834325,0.00041891998,0.0001165015,0.00011387575,3.2059103e-7,0.000020950452,0.00003323132,0.12733877,0.0069464277,0.80859965,0.056334227],"study_design_scores_gemma":[0.00032439802,0.00004150997,0.014240799,0.000046980807,0.000051836625,0.000001157715,0.00009721376,0.019301794,0.008242293,0.0031684765,0.954227,0.00025654366],"about_ca_topic_score_codex":0.0000038964426,"about_ca_topic_score_gemma":0.000061013754,"teacher_disagreement_score":0.5425718,"about_ca_system_score_codex":0.000017406255,"about_ca_system_score_gemma":0.0000119289,"threshold_uncertainty_score":0.4957865},"labels":[],"label_agreement":null},{"id":"W4408663620","doi":"10.1038/s41597-025-04809-z","title":"A spatially constrained remote sensing-based inventory of glacial lakes worldwide","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Cryospheric studies and observations","field":"Earth and Planetary Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Glacial period; Paleolimnology; Environmental science; Remote sensing; Physical geography; Geography; Geology; Oceanography; Climate change; Geomorphology","score_opus":0.04030912102009116,"score_gpt":0.2574513166487394,"score_spread":0.21714219562864823,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408663620","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":[0.7957041,0.0037182837,0.07945068,0.009978167,0.02327332,0.0015414999,0.023087109,0.00036566224,0.06288114],"genre_scores_gemma":[0.95816976,0.000012619037,0.027537432,0.0008127306,0.00013208023,1.1853412e-7,0.007429634,0.000004324969,0.0059013083],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988346,0.000043859425,0.00025884117,0.0004048928,0.00025405042,0.0002037386],"domain_scores_gemma":[0.9987634,0.0001436055,0.000091748865,0.0008534597,0.000097173775,0.000050617415],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006921518,0.00008933506,0.0001540732,0.00007733476,0.00032435652,0.00010656708,0.0005773894,0.00002855203,0.00078510836],"category_scores_gemma":[0.00038506172,0.00007850511,0.000037088128,0.0008331589,0.00055642694,0.00012495852,0.00008563552,0.00006421605,0.00003827986],"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":[0.000087268585,0.000041797368,0.09982575,0.000118870135,0.0000903877,0.000016566835,0.00027889208,0.0018593739,0.000419881,0.00027012813,0.18998535,0.70700574],"study_design_scores_gemma":[0.0005289128,0.000028065468,0.1294739,0.00011962721,0.00005803189,8.052941e-7,0.00031120816,0.542629,0.00017039929,0.0012707842,0.3252224,0.00018688329],"about_ca_topic_score_codex":0.0022620275,"about_ca_topic_score_gemma":0.06479744,"teacher_disagreement_score":0.7068189,"about_ca_system_score_codex":0.0000036513804,"about_ca_system_score_gemma":0.0003699792,"threshold_uncertainty_score":0.9522676},"labels":[],"label_agreement":null},{"id":"W4408712625","doi":"10.1038/s41597-025-04456-4","title":"Banana Leaves Imagery Dataset","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Smart Agriculture and AI","field":"Agricultural and Biological Sciences","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":"International Development Research Centre; Styrelsen för Internationellt Utvecklingssamarbete","keywords":"Tanzania; Fusarium wilt; Agriculture; Data collection; Geography; Race (biology); Computer science; Remote sensing; Cartography; Horticulture; Biology; Botany; Environmental planning; Statistics; Mathematics","score_opus":0.041991631899976914,"score_gpt":0.26667905758240595,"score_spread":0.22468742568242905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408712625","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":[0.6532779,0.0029867273,0.00005465366,0.0368077,0.012137043,0.0009829156,0.25069353,0.0005549609,0.04250458],"genre_scores_gemma":[0.48549223,0.00005435267,0.0005198012,0.0032992626,0.0009969672,0.00001712397,0.44841585,0.0000013329088,0.061203096],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986724,0.000035422276,0.00015446986,0.0006801151,0.00020071382,0.00025684971],"domain_scores_gemma":[0.99926436,0.0000907928,0.00003669045,0.00050608034,0.000039255137,0.000062821746],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005550143,0.00009973826,0.00010772382,0.000017843415,0.0004642998,0.0005088312,0.0016714797,0.00004317009,0.0007242972],"category_scores_gemma":[0.00010694488,0.00003126922,0.000029524314,0.00087599567,0.00015917719,0.00045623523,0.0009812728,0.000080059486,0.0004436742],"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":[0.0000021773183,0.000035252477,0.0007537417,0.0000027508097,0.0000062700537,0.000002713121,0.000004522265,1.039021e-7,0.046614967,0.00020771347,0.9161739,0.03619593],"study_design_scores_gemma":[0.000037324633,0.000007043217,0.032393936,0.00001426688,0.000012836326,0.0000013094168,0.00012400562,0.000026199154,0.0020957051,0.000383502,0.96480745,0.00009641528],"about_ca_topic_score_codex":0.00014408426,"about_ca_topic_score_gemma":0.0012431346,"teacher_disagreement_score":0.19772232,"about_ca_system_score_codex":0.0000075765206,"about_ca_system_score_gemma":0.000016520285,"threshold_uncertainty_score":0.79305464},"labels":[],"label_agreement":null},{"id":"W4408820614","doi":"10.1038/s41597-025-04771-w","title":"The Eye Movement Database of Passage Reading in Vertically Written Traditional Mongolian","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Natural Language Processing Techniques","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":false,"ca_institutions":"McMaster University","funders":"Social Sciences and Humanities Research Council of Canada; Canada Research Chairs; Government of Canada","keywords":"Reading (process); Movement (music); Computer science; Database; Information retrieval; Linguistics; Art","score_opus":0.03549533225539785,"score_gpt":0.3043132777584626,"score_spread":0.26881794550306476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408820614","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":[0.007159498,0.004477453,0.9496998,0.023102121,0.0036726128,0.0010569895,0.0031338476,0.0006001896,0.0070974627],"genre_scores_gemma":[0.4336181,0.000042817264,0.55859965,0.00089526083,0.000064038766,0.00004943714,0.0016569998,0.000013241362,0.005060474],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99839145,0.000063256244,0.00029162967,0.0005826553,0.00042864567,0.00024239095],"domain_scores_gemma":[0.9971994,0.00015826218,0.000064611115,0.0024639263,0.00007427372,0.000039500268],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020966302,0.00008257839,0.00009696585,0.00018085148,0.00023438508,0.00050358236,0.00478404,0.000029251232,0.0000066532534],"category_scores_gemma":[0.00042329115,0.000059672002,0.000019199057,0.0010489422,0.00024724976,0.00090568216,0.0020164845,0.00015587611,0.0000055247606],"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":[0.000009990493,0.00015836366,0.00050199195,0.00006981741,0.000016000608,0.000022973582,0.00018671743,0.0000024515996,0.02614852,0.8032133,0.10664352,0.06302637],"study_design_scores_gemma":[0.0007000197,0.00004480525,0.0049723666,0.0010967414,0.000025364974,0.0000032219696,0.00018046159,0.1704212,0.09843466,0.67056876,0.053064045,0.0004883486],"about_ca_topic_score_codex":0.00004899354,"about_ca_topic_score_gemma":0.00008171393,"teacher_disagreement_score":0.4264586,"about_ca_system_score_codex":0.00004733859,"about_ca_system_score_gemma":0.00017986006,"threshold_uncertainty_score":0.88900167},"labels":[],"label_agreement":null},{"id":"W4408963841","doi":"10.1038/s41597-025-04863-7","title":"Multimodal precision MRI of the individual human brain at ultra-high fields","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Advanced MRI Techniques and Applications","field":"Medicine","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; McGill University; Montreal Neurological Institute and Hospital","funders":"Wellcome Trust","keywords":"Human brain; Computer science; Artificial intelligence; Computational biology; Neuroscience; Psychology; Biology","score_opus":0.05193038708683744,"score_gpt":0.3736884220903615,"score_spread":0.32175803500352407,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408963841","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":[0.713781,0.00036436025,0.20030402,0.03779093,0.0024153301,0.0043630046,0.014363318,0.0003872172,0.026230805],"genre_scores_gemma":[0.94859993,0.000005310885,0.014522905,0.00038020275,0.000033565608,0.000021630529,0.002547817,0.0000066865027,0.033881936],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990363,0.000017549606,0.00019338375,0.0003855329,0.00024705534,0.000120162906],"domain_scores_gemma":[0.9975612,0.00007279963,0.00006795536,0.0022081858,0.00005654864,0.000033323216],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004587975,0.000063788924,0.00010750844,0.0000646232,0.000302086,0.000026406233,0.0008691665,0.000055585955,0.00012972971],"category_scores_gemma":[0.00017280223,0.000042665586,0.000034755405,0.0004178054,0.00025884228,0.000074817086,0.0007745312,0.00011790185,0.000009365401],"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":[0.00001511352,0.0001763973,0.0012461733,0.000034660094,0.000012286389,6.5506293e-7,0.0001283651,0.000024462832,0.11930692,0.0067773815,0.8546457,0.01763185],"study_design_scores_gemma":[0.0008999407,0.000053881755,0.039909314,0.00029344374,0.00010815493,0.0000061167934,0.000104917555,0.00064919674,0.25852108,0.011099682,0.6882172,0.00013704569],"about_ca_topic_score_codex":0.00003318341,"about_ca_topic_score_gemma":0.000084688334,"teacher_disagreement_score":0.23481894,"about_ca_system_score_codex":0.000021061536,"about_ca_system_score_gemma":0.000060185892,"threshold_uncertainty_score":0.23234318},"labels":[],"label_agreement":null},{"id":"W4409000241","doi":"10.1038/s41597-025-04869-1","title":"UrBAN: Urban Beehive Acoustics and PheNotyping Dataset","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Insect and Pesticide Research","field":"Agricultural and Biological Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université Laval; Institut National de la Recherche Scientifique; Université du Québec à Montréal","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Beehive; Apiary; Varroa; Population; Proxy (statistics); Geography; Drone; Swarming (honey bee); Mite; Beekeeping; Biology; Ecology; Computer science; Environmental health; Machine learning; Medicine","score_opus":0.061818336176629074,"score_gpt":0.3063153138626512,"score_spread":0.24449697768602213,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409000241","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":[0.7395066,0.0042602643,0.00031088997,0.005693248,0.003848526,0.00102821,0.2310054,0.00021526798,0.014131603],"genre_scores_gemma":[0.90907913,0.00005045378,0.00029325188,0.00035825412,0.00037010486,0.000005844314,0.082845874,9.666934e-7,0.0069960877],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987213,0.000051209467,0.00013420287,0.0005625042,0.00022775991,0.0003030107],"domain_scores_gemma":[0.999224,0.0002394109,0.000028674101,0.00036605055,0.000057128444,0.00008472535],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00086321105,0.00008650648,0.000099309545,0.000027672795,0.0006125917,0.0005402211,0.0010551721,0.00004724789,0.0005234612],"category_scores_gemma":[0.00028350763,0.00003517185,0.000012119322,0.00056445354,0.00028647287,0.00024418288,0.0012497394,0.00012521703,0.00009943695],"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":[0.000008967781,0.000026391132,0.0017620705,0.00001397989,0.000007667768,0.000003713709,0.000031754535,3.0958654e-7,0.051911216,0.00078413566,0.9124054,0.033044443],"study_design_scores_gemma":[0.000091953334,0.000024333014,0.028577881,0.000040416347,0.000023094475,0.0000021822389,0.00019190162,0.002999682,0.0005110057,0.001071159,0.96632063,0.00014573363],"about_ca_topic_score_codex":0.00014723539,"about_ca_topic_score_gemma":0.00026645488,"teacher_disagreement_score":0.16957258,"about_ca_system_score_codex":0.000010455321,"about_ca_system_score_gemma":0.00003246352,"threshold_uncertainty_score":0.5731533},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W4409031891","doi":"10.1038/s41597-024-04207-x","title":"Global Roadkill Data: a dataset on terrestrial vertebrate mortality caused by collision with vehicles","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Wildlife-Road Interactions and Conservation","field":"Environmental Science","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Laurentian University; Université Laval; Centre de Géomatique du Québec; Parks Canada; Lake Simcoe Region Conservation Authority; Concordia University; Memorial University of Newfoundland; Canadian Wildlife Federation; Environment and Climate Change Canada; Mount Allison University","funders":"H2020 European Research Council; Agencia Estatal de Investigación; Instituto Chico Mendes de Conservação da Biodiversidade; Tanzania Wildlife Research Institute; HORIZON EUROPE Framework Programme; U.S. Fish and Wildlife Service; Fondation Segré; Consejo Mexiquense de Ciencia y Tecnología; Unitatea Executiva pentru Finantarea Invatamantului Superior, a Cercetarii, Dezvoltarii si Inovarii; University of Venda; Miljødirektoratet; Environment and Climate Change Canada; Academia Româna; Fundação de Apoio ao Desenvolvimento do Ensino, Ciência e Tecnologia do Estado de Mato Grosso do Sul; Consejo Nacional de Ciencia y Tecnología; Boise State University; Ministerio de Ciencia e Innovación; Fundação de Amparo à Pesquisa do Estado de Goiás; Ministarstvo Prosvete, Nauke i Tehnološkog Razvoja; Ministère des Transports; Lietuvos Mokslo Taryba; Fundação de Amparo à Pesquisa do Estado de São Paulo; European Commission; Sächsisches Staatsministerium für Wissenschaft und Kunst; Narodowym Centrum Nauki; National Geographic Society; King Mongkut's University of Technology Thonburi; Akademie Věd České Republiky; Ministry of Environment; National Research Foundation; U.S. Department of Agriculture; Ministério da Ciência, Tecnologia e Inovação; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior; Environmental Restoration and Conservation Agency; Royal Zoological Society of Scotland; National Natural Science Foundation of China; Idaho Transportation Department; Fundação de Amparo à Pesquisa e Inovação do Estado de Santa Catarina; Massachusetts Department of Fish and Game; Generalitat de Catalunya; Bundesministerium für Verkehr und Digitale Infrastruktur; Comunidad de Madrid; Ministry of Natural Resources; Biologické Centrum, Akademie Věd České Republiky; Conselho Nacional de Desenvolvimento Científico e Tecnológico; British Herpetological Society; Deutsche Bundesstiftung Umwelt; Junta de Andalucía; Fundação para a Ciência e a Tecnologia; Idaho Department of Fish and Game; McLean Foundation; Fundación Charles Darwin; Natural Sciences and Engineering Research Council of Canada; Bundesministerium für Bildung und Forschung; Panthera; Idea Wild; Mekelle University","keywords":"Collision; Vertebrate; Environmental science; Ecology; Biology; Geography; Computer science; Computer security","score_opus":0.04990942759797331,"score_gpt":0.32237358595060733,"score_spread":0.27246415835263404,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409031891","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":[0.8189403,0.00001934365,0.0006577882,0.0011765484,0.0015279222,0.00039876805,0.17512843,0.000054922788,0.0020959955],"genre_scores_gemma":[0.63642454,0.000008652598,0.0004124039,0.0011377117,0.000063566644,0.000016943535,0.35923174,0.000010590071,0.0026938624],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976736,0.00008501932,0.00024983095,0.0012160756,0.0005277002,0.00024777677],"domain_scores_gemma":[0.995613,0.000039109415,0.00009893682,0.0041551488,0.000009104559,0.00008469577],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007935517,0.00014764268,0.00012757737,0.00003556777,0.00044259164,0.00056827633,0.0021645455,0.000046639925,0.00039920284],"category_scores_gemma":[0.0001419525,0.00011667888,0.000012103658,0.0008428953,0.00036065726,0.0016501569,0.0018394537,0.00009547001,0.0004601325],"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":[0.000056031855,0.0001571326,0.03201503,0.0000023280768,0.000020147143,0.0000042119223,0.0000066840867,0.00010458879,0.00041975893,0.000026178783,0.9643552,0.002832715],"study_design_scores_gemma":[0.00066028995,0.000042891093,0.053208806,0.00003853759,0.000054650896,0.0000014359274,0.000052029485,0.026224297,0.00029773614,0.000099730256,0.9191468,0.0001728416],"about_ca_topic_score_codex":0.0031786084,"about_ca_topic_score_gemma":0.0061834278,"teacher_disagreement_score":0.1841033,"about_ca_system_score_codex":0.00013865482,"about_ca_system_score_gemma":0.0001002261,"threshold_uncertainty_score":0.59142256},"labels":[],"label_agreement":null},{"id":"W4409045544","doi":"10.1038/s41597-025-04678-6","title":"An chromosome-level haplotype-resolved genome assembly and annotation of pitaya (Selenicereus polyrhizus)","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Botanical Research and Applications","field":"Agricultural and Biological 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":"Ministry of Agriculture","funders":"National Natural Science Foundation of China","keywords":"Contig; Haplotype; Biology; Genome; Sequence assembly; Gene; Genetics; Reference genome; Chromosome; Coding region; Gene prediction; Computational biology; Genotype; Transcriptome","score_opus":0.08317464501943966,"score_gpt":0.32675391724953634,"score_spread":0.24357927223009668,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409045544","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":[0.9910954,0.00035695432,0.00021303122,0.0020339445,0.00010330566,0.00026796683,0.005255437,0.000041182826,0.00063273427],"genre_scores_gemma":[0.99548894,0.00003261403,0.0005059803,0.000053386866,0.000042971,0.000009905843,0.002767505,6.4777305e-7,0.0010980354],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9986668,0.000056285462,0.00020414789,0.0005707277,0.0002648498,0.00023716131],"domain_scores_gemma":[0.99906385,0.00015803227,0.000058704703,0.0004533923,0.0001308452,0.00013517954],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00071815896,0.00007880711,0.00011597575,0.000023342247,0.0003319889,0.0002455595,0.0011389521,0.000052151903,0.00014790977],"category_scores_gemma":[0.00022646198,0.000035035126,0.000020808955,0.0007970046,0.0002634493,0.0003622049,0.00044252528,0.00008399453,0.000032009724],"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":[0.000011789604,0.00011842208,0.0003346388,0.000007910947,0.000008088948,3.1100893e-7,0.000013129825,3.7933e-7,0.9150405,0.0018450541,0.0032520266,0.07936776],"study_design_scores_gemma":[0.0003571898,0.0002804291,0.79467523,0.00004733023,0.0000379219,0.0000018521806,0.00040229553,0.0035127625,0.023434307,0.0056005036,0.17133725,0.00031289726],"about_ca_topic_score_codex":0.00021298412,"about_ca_topic_score_gemma":0.0013916026,"teacher_disagreement_score":0.8916062,"about_ca_system_score_codex":0.000011263751,"about_ca_system_score_gemma":0.00004133212,"threshold_uncertainty_score":0.2553424},"labels":[],"label_agreement":null},{"id":"W4409158760","doi":"10.1038/s41597-025-04852-w","title":"StoichLife: A Global Dataset of Plant and Animal Elemental Content","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Isotope Analysis in Ecology","field":"Environmental Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"Australian Research Council; Natural Sciences and Engineering Research Council of Canada; National Science Foundation; Royal Society; Department of Education and Training; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Vlaamse regering; Fonds Wetenschappelijk Onderzoek; Ministério da Ciência, Tecnologia e Inovação; Deutsches Zentrum für integrative Biodiversitätsforschung Halle-Jena-Leipzig; Deutsche Forschungsgemeinschaft; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Russian Science Foundation","keywords":"Content (measure theory); Information retrieval; Environmental science; Computer science; Mathematics","score_opus":0.04010059842137004,"score_gpt":0.2917755226563082,"score_spread":0.25167492423493815,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409158760","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":[0.7512915,0.00015508973,0.00041563401,0.0007518634,0.00089079805,0.00041855915,0.23888445,0.000023360219,0.0071687084],"genre_scores_gemma":[0.9531464,0.00000936604,0.0023718684,0.00049620273,0.000011621194,0.000006663431,0.042371176,0.0000036609435,0.001583068],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986033,0.000045644367,0.0002715971,0.0006154326,0.000250673,0.00021335122],"domain_scores_gemma":[0.9986035,0.000026672049,0.00008588938,0.0012249704,0.000008296854,0.000050624873],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009422587,0.0000806968,0.00014106352,0.000038272563,0.00015067485,0.00007214293,0.001119127,0.000027835187,0.0017119197],"category_scores_gemma":[0.00012756663,0.00007073645,0.0000141396795,0.00040879243,0.0007936111,0.0002987538,0.0034658117,0.000046040397,0.00019250791],"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":[0.000023138187,0.00009642399,0.13555665,0.0000071028635,0.00003061406,0.0000059346467,0.000018855839,0.0000027571052,0.0053911153,0.0005543365,0.8554837,0.002829361],"study_design_scores_gemma":[0.00061682693,0.00006304478,0.1929044,0.000014699121,0.00011067362,0.000012252334,0.00029530586,0.0060401135,0.0013755809,0.00022602963,0.7981727,0.0001683602],"about_ca_topic_score_codex":0.00038175157,"about_ca_topic_score_gemma":0.0023235658,"teacher_disagreement_score":0.20185484,"about_ca_system_score_codex":0.00006889671,"about_ca_system_score_gemma":0.00002601003,"threshold_uncertainty_score":0.99920064},"labels":[],"label_agreement":null},{"id":"W4409185689","doi":"10.1038/s41597-025-04868-2","title":"An open-access database of nature-based carbon offset project boundaries","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Land Use and Ecosystem Services","field":"Environmental Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carbon Engineering (Canada)","funders":"","keywords":"Geospatial analysis; Reforestation; Digitization; Database; Deforestation (computer science); Computer science; Offset (computer science); Carbon footprint; Afforestation; Remote sensing; Georeference; Metadata; Environmental science; Environmental resource management; Geography; Physical geography; Greenhouse gas; Forestry; World Wide Web; Geology; Telecommunications","score_opus":0.04432664285794074,"score_gpt":0.36030916925412615,"score_spread":0.3159825263961854,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409185689","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":[0.9757252,0.00013394529,0.00007892459,0.00034423426,0.0020128256,0.00062277715,0.009834909,0.00004424258,0.011202954],"genre_scores_gemma":[0.9912741,0.000002447338,0.00048570457,0.00018769424,0.000015668164,0.000013740466,0.0076647154,0.0000062817467,0.00034962725],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99828047,0.00007580035,0.00023359229,0.000827693,0.00035608432,0.00022633636],"domain_scores_gemma":[0.99675083,0.000025768679,0.00010685358,0.003043934,0.00001819706,0.00005439548],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0013416341,0.00010996875,0.00016286358,0.00009667568,0.0004192415,0.0024868734,0.006986746,0.000058866575,0.00047182248],"category_scores_gemma":[0.000050593033,0.00008370547,0.000012809943,0.000998631,0.00022672386,0.0025700505,0.005129059,0.00010432892,0.000027148171],"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":[0.0003328192,0.0015207919,0.27086124,0.0009620724,0.00007975025,0.000025512521,0.00043647134,0.00036954734,0.03637181,0.0009888972,0.68082565,0.007225435],"study_design_scores_gemma":[0.00087017927,0.000063795356,0.017419502,0.0002692591,0.000074194475,0.0000013123332,0.00017731471,0.09579593,0.03103719,0.0005851153,0.85333526,0.00037091738],"about_ca_topic_score_codex":0.008809343,"about_ca_topic_score_gemma":0.025065048,"teacher_disagreement_score":0.25344175,"about_ca_system_score_codex":0.000035353754,"about_ca_system_score_gemma":0.0002728452,"threshold_uncertainty_score":0.9985486},"labels":[],"label_agreement":null},{"id":"W4409246424","doi":"10.1038/s41597-025-04921-0","title":"Whole Genome Sequence of the gut commensal protist Tritrichomonas musculus isolated from laboratory mice","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","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; Hospital for Sick Children","funders":"NHLBI Division of Intramural Research; Canadian Institutes of Health Research; U.S. Department of Health and Human Services; National Institutes of Health; Government of Canada; National Institute of Allergy and Infectious Diseases; Division of Intramural Research, National Institute of Allergy and Infectious Diseases","keywords":"Biology; Genome; Gene; Axenic; Genetics; Giardia; Model organism; Protist; Entamoeba; Giardia lamblia; Whole genome sequencing; Computational biology; Entamoeba histolytica; Bacteria","score_opus":0.02464295819662421,"score_gpt":0.2698881851833915,"score_spread":0.24524522698676732,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409246424","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":[0.9586757,0.0042239553,0.0002250028,0.00063327386,0.0018881226,0.00044934356,0.033390224,0.000004812358,0.00050960993],"genre_scores_gemma":[0.9932769,0.00005068878,0.0004733181,0.00022327805,0.00006391266,0.0000126941,0.0033001304,0.000008667956,0.0025904386],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988261,0.000077889315,0.0002198224,0.0005688572,0.00012981214,0.00017755646],"domain_scores_gemma":[0.99787354,0.000017015276,0.00009771323,0.0018158305,0.00016401788,0.000031891337],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038558643,0.000111436726,0.00013078997,0.00003336342,0.00024631224,0.00006623722,0.00144356,0.00006603638,0.000008316894],"category_scores_gemma":[0.00013411764,0.000086735075,0.000040493418,0.00039822256,0.00037830204,0.0000021864462,0.001566703,0.00007250959,0.000008472253],"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":[0.000015010456,0.000041535346,0.001651825,0.000012042686,0.00006641195,4.4645088e-7,0.00004245888,0.0000073169444,0.9728431,0.00001913932,0.024875425,0.00042530318],"study_design_scores_gemma":[0.00050557015,0.000037236292,0.028337043,0.000026609483,0.000062745625,6.8523315e-7,0.0001347992,0.00025916795,0.07160614,0.0002098232,0.89864427,0.00017594302],"about_ca_topic_score_codex":0.000102516795,"about_ca_topic_score_gemma":0.00016389876,"teacher_disagreement_score":0.90123695,"about_ca_system_score_codex":0.0000110102155,"about_ca_system_score_gemma":0.00023482583,"threshold_uncertainty_score":0.3536954},"labels":[],"label_agreement":null},{"id":"W4409427820","doi":"10.1038/s41597-025-04970-5","title":"Establishing a comprehensive host-parasite stable isotope database to unravel trophic relationships","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Isotope Analysis in Ecology","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of Alberta","funders":"Agencia Estatal de Investigación; Marsden Fund; HORIZON EUROPE Framework Programme; Ministry of Business, Innovation and Employment; Royal Society Te Apārangi; European Commission","keywords":"Host (biology); Trophic level; Stable isotope ratio; Parasite hosting; Database; Biology; Ecology; Computer science; World Wide Web","score_opus":0.0569834263259266,"score_gpt":0.30193306094343164,"score_spread":0.24494963461750505,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409427820","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":[0.904864,0.00023402863,0.037600067,0.005518632,0.0045333076,0.0018894295,0.0061328555,0.00024136963,0.03898627],"genre_scores_gemma":[0.84297305,0.000021495533,0.05304526,0.003281496,0.00010418127,0.000099602374,0.009468706,0.00004755661,0.09095867],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9967196,0.00026739217,0.00041491678,0.0015041344,0.00051613717,0.0005777915],"domain_scores_gemma":[0.9951884,0.00034036257,0.000108438275,0.004126652,0.000055168122,0.00018095244],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001997009,0.00019198845,0.00025372082,0.00032442505,0.0010846866,0.0006249844,0.002958773,0.0000756846,0.002455801],"category_scores_gemma":[0.0015152722,0.00019206644,0.00004078992,0.002933027,0.0004630895,0.0016782173,0.0054175863,0.00033931382,0.004837241],"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":[0.000029378183,0.00020297467,0.08216795,0.000020287602,0.000051822535,0.000029127148,0.00045091577,0.0022471163,0.030974917,0.0016345779,0.8803683,0.001822622],"study_design_scores_gemma":[0.00037672825,0.000023413555,0.1434371,0.000047239126,0.00010592577,0.000005113649,0.0005342343,0.011965235,0.0013399557,0.00095402927,0.84084886,0.00036217042],"about_ca_topic_score_codex":0.00070927007,"about_ca_topic_score_gemma":0.0037621155,"teacher_disagreement_score":0.061891012,"about_ca_system_score_codex":0.0002222356,"about_ca_system_score_gemma":0.000096085365,"threshold_uncertainty_score":0.99845606},"labels":[],"label_agreement":null},{"id":"W4409566488","doi":"10.1038/s41597-025-04907-y","title":"ROBIN: Reference observatory of basins for international hydrological climate change detection","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Hydrology and Watershed Management Studies","field":"Environmental Science","cited_by":7,"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 Saskatchewan","funders":"U.S. Geological Survey; Natural Environment Research Council; Research Councils UK","keywords":"Streamflow; Climate change; Water cycle; Coupled model intercomparison project; Environmental science; Drainage basin; Climatology; Climate model; Global warming; Adaptation (eye); Global change; Scale (ratio); Identification (biology); Environmental resource management; Water resources; Hydrological modelling; Physical geography; Geography; Ecology; Geology; Cartography","score_opus":0.10340024084581281,"score_gpt":0.3016252393294802,"score_spread":0.1982249984836674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409566488","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":[0.9087985,0.00014959884,0.011761138,0.007392837,0.012727899,0.0016883013,0.0054008346,0.00019190124,0.051888984],"genre_scores_gemma":[0.9970368,0.000030039135,0.0006767793,0.0003221945,0.00002438553,0.000045777368,0.0004947311,0.0000023892246,0.0013668995],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99903774,0.00002554569,0.0001542105,0.00047082742,0.00013161058,0.00018008323],"domain_scores_gemma":[0.99930346,0.000034587047,0.000059675524,0.00056901027,0.000015136579,0.000018119159],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00087284204,0.00006572145,0.00008678655,0.000053289827,0.00024907204,0.000027363352,0.0008574079,0.000042032727,0.0002307626],"category_scores_gemma":[0.0001244824,0.000055305878,0.00001994135,0.00020989809,0.00040052462,0.00034730943,0.00177294,0.00004937472,0.00008429775],"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":[0.0006192931,0.0010322197,0.39381936,0.0002817841,0.00030177046,0.000008911285,0.0009862931,0.00050829776,0.05171214,0.0131300315,0.33161947,0.20598042],"study_design_scores_gemma":[0.00042733524,0.000056518264,0.16685723,0.00002317898,0.000047919202,3.7555404e-7,0.00006650933,0.014379047,0.0032333983,0.0032022083,0.81157047,0.00013580627],"about_ca_topic_score_codex":0.000027564756,"about_ca_topic_score_gemma":0.00029556273,"teacher_disagreement_score":0.479951,"about_ca_system_score_codex":0.000029721265,"about_ca_system_score_gemma":0.0000030537108,"threshold_uncertainty_score":0.25266886},"labels":[],"label_agreement":null},{"id":"W4409669866","doi":"10.1038/s41597-025-05005-9","title":"Author Correction: An open-access database of nature-based carbon offset project boundaries","year":2025,"lang":"en","type":"erratum","venue":"Scientific Data","topic":"Environmental Conservation and Management","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carbon Engineering (Canada)","funders":"","keywords":"Offset (computer science); Computer science; Database; World Wide Web; Open source; Information retrieval; Programming language; Software","score_opus":0.0788561484145464,"score_gpt":0.3757769037891152,"score_spread":0.2969207553745688,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409669866","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":[0.0016401594,0.0009093373,0.0012567895,0.008432641,0.38217488,0.008003728,0.089514285,0.000390342,0.50767785],"genre_scores_gemma":[0.0012143824,0.000024580273,0.0013057115,0.0014133545,0.00012741348,0.000094438496,0.15877515,0.00003665914,0.8370083],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99558526,0.00022034023,0.0005455109,0.0020875465,0.0011830509,0.0003782626],"domain_scores_gemma":[0.9937572,0.000039191105,0.00047017023,0.0055839205,0.000025791016,0.00012374215],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.0019990082,0.00036915235,0.0003993818,0.00028514263,0.0007576015,0.0034399112,0.010082926,0.0003027255,0.0026696094],"category_scores_gemma":[0.00028461684,0.00035793852,0.000044940087,0.0013619914,0.001730142,0.0024140996,0.018039074,0.00077423453,0.00005247369],"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":[0.00004167147,0.00030104505,0.00036417125,0.00014970126,0.000023194762,0.0000068708337,0.000037969545,0.000019909647,0.00015362997,0.00007190155,0.9967446,0.002085377],"study_design_scores_gemma":[0.00026252633,0.000052684412,0.0013456995,0.00022701168,0.000100283854,9.2108405e-7,0.0000932675,0.012476076,0.0003697242,0.00005267315,0.98465747,0.00036168398],"about_ca_topic_score_codex":0.009050629,"about_ca_topic_score_gemma":0.020057935,"teacher_disagreement_score":0.38204747,"about_ca_system_score_codex":0.00029368914,"about_ca_system_score_gemma":0.00082206074,"threshold_uncertainty_score":0.9998873},"labels":[],"label_agreement":null},{"id":"W4409766480","doi":"10.1038/s41597-025-05001-z","title":"HarvestStat Africa – Harmonized Subnational Crop Statistics for Sub-Saharan Africa","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Climate change impacts on agriculture","field":"Agricultural and Biological Sciences","cited_by":16,"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","funders":"U.S. Geological Survey; Bundesministerium für Bildung und Forschung; Goddard Space Flight Center; Wyoming-Montana Water Science Center; Volkswagen Foundation; Deutsches Zentrum für integrative Biodiversitätsforschung Halle-Jena-Leipzig; Consortium of International Agricultural Research Centers; U.S. Department of the Interior; Canada Research Chairs; United States Agency for International Development; Deutsche Forschungsgemeinschaft; National Aeronautics and Space Administration","keywords":"Agriculture; Sorghum; Famine; Agricultural productivity; Yield (engineering); Agricultural economics; Scarcity; Geography; Crop; Crop yield; Agroforestry; Environmental science; Economics; Ecology; Forestry; Biology","score_opus":0.1283449131331734,"score_gpt":0.30388792199483927,"score_spread":0.17554300886166588,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409766480","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17163439,0.007376661,0.0037020524,0.03653258,0.010119081,0.005100022,0.75336176,0.0009049348,0.011268515],"genre_scores_gemma":[0.47701567,0.000791985,0.017912988,0.0011786622,0.0015149519,0.00044398787,0.3152117,0.000015872438,0.18591416],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978028,0.00005845572,0.00031849582,0.0008585779,0.0004289717,0.0005326881],"domain_scores_gemma":[0.9985456,0.00041384087,0.00012582286,0.00038709666,0.00037267062,0.00015496544],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00092592253,0.00018705352,0.0002136835,0.000058198846,0.0008571269,0.0015632365,0.0015117108,0.00009214215,0.0005776891],"category_scores_gemma":[0.00088473427,0.00007687743,0.000058501006,0.0012020273,0.00025185855,0.00045996596,0.0005439294,0.000109957204,0.00012406871],"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":[0.000029188039,0.00011076156,0.000029415414,0.000019702753,0.000015745358,0.0000018921241,0.000049061076,7.7290036e-7,0.14403059,0.0006291973,0.82943565,0.025648022],"study_design_scores_gemma":[0.0003012399,0.000039837745,0.009630967,0.00003806161,0.000037019083,0.0000015921829,0.0001107383,0.0006353429,0.0019401627,0.002496499,0.9845583,0.0002102662],"about_ca_topic_score_codex":0.00005930987,"about_ca_topic_score_gemma":0.0021337634,"teacher_disagreement_score":0.43815005,"about_ca_system_score_codex":0.00007641371,"about_ca_system_score_gemma":0.00006801729,"threshold_uncertainty_score":0.9994732},"labels":[],"label_agreement":null},{"id":"W4409826571","doi":"10.1038/s41597-025-04898-w","title":"Airborne imaging spectroscopy surveys of Arctic and boreal Alaska and northwestern Canada 2017–2023","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Climate change and permafrost","field":"Earth and Planetary 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":true,"ca_institutions":"Canadian Polar Commission; Government of Northwest Territories; University of British Columbia","funders":"Jet Propulsion Laboratory; National Aeronautics and Space Administration","keywords":"Tundra; Permafrost; Taiga; Imaging spectrometer; Environmental science; Remote sensing; Arctic; Transect; Climate change; Physical geography; Boreal; Ecotone; Oceanography; Geography; Geology; Ecology; Forestry; Spectrometer; Habitat","score_opus":0.03355551431714082,"score_gpt":0.2582392655103902,"score_spread":0.2246837511932494,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409826571","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":[0.9211976,0.0024991827,0.00002748953,0.000692246,0.0015349595,0.00012387581,0.07174673,0.000009833947,0.0021680759],"genre_scores_gemma":[0.9729387,0.00016620666,0.000061877654,0.00009842723,0.00003116344,2.2772211e-7,0.025857562,0.0000017626701,0.0008440651],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99886703,0.000061833416,0.00016306317,0.00046953475,0.00019547033,0.00024307925],"domain_scores_gemma":[0.99906147,0.00012651418,0.000052173422,0.00062703615,0.000038873633,0.000093947565],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00096208794,0.00009416934,0.00013866242,0.000088031484,0.0001969457,0.00019871478,0.0003984044,0.000016545007,0.00040359498],"category_scores_gemma":[0.00003861754,0.00008150555,0.000008235702,0.00028529254,0.00028023162,0.00027177256,0.00015659147,0.00006679777,0.000008260639],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004604492,0.0000045277498,0.95317745,0.00006127233,0.0000071432833,0.0000127306575,0.00007046054,0.0000013419457,0.00011238926,0.0000029442078,0.037237786,0.009307339],"study_design_scores_gemma":[0.00013530183,0.000007254959,0.9848415,0.000042465046,0.000016201515,0.000008854694,0.00024122892,0.0020789371,0.00008856339,0.00008553877,0.012369292,0.00008480711],"about_ca_topic_score_codex":0.83940583,"about_ca_topic_score_gemma":0.9920346,"teacher_disagreement_score":0.15262881,"about_ca_system_score_codex":0.000004579767,"about_ca_system_score_gemma":0.0002259403,"threshold_uncertainty_score":0.4419082},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":true,"confidence":"high"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":true,"confidence":"high"}],"label_agreement":"agree"},{"id":"W4410037531","doi":"10.1038/s41597-025-05069-7","title":"Multimodal sensor dataset for monitoring older adults post lower limb fractures in community settings","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Hip and Femur Fractures","field":"Medicine","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":"University Health Network; University of Toronto; Toronto Rehabilitation Institute","funders":"","keywords":"Physical medicine and rehabilitation; Lower limb; Computer science; Medicine; Surgery","score_opus":0.025410983150132807,"score_gpt":0.35694932403285506,"score_spread":0.33153834088272227,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410037531","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":[0.92409426,0.00032382365,0.00025100194,0.0024822021,0.0030237765,0.0010658803,0.06843755,0.00006501188,0.00025648292],"genre_scores_gemma":[0.9045406,0.000004510674,0.002943824,0.000978937,0.00016139454,0.000019278712,0.090274766,0.000016146627,0.0010605417],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99832565,0.00008636212,0.0003152323,0.00061302545,0.0002740612,0.00038565346],"domain_scores_gemma":[0.99643546,0.00039584312,0.00007405778,0.0028303706,0.00015109986,0.00011315352],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014230348,0.00017644455,0.00026327843,0.00030074723,0.00045245897,0.00019032932,0.00094334624,0.00012138892,0.00009925526],"category_scores_gemma":[0.0017470833,0.00014691276,0.00004664526,0.00039213232,0.00019569317,0.00032123635,0.0007054529,0.00056382426,0.000041354662],"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":[0.0014736047,0.0013069053,0.017075403,0.00081943686,0.00008271805,0.000050923536,0.0023813364,0.00001161452,0.00902977,0.000008198732,0.93687624,0.030883864],"study_design_scores_gemma":[0.005187164,0.00019757324,0.33779708,0.0019087935,0.00017015514,0.000013376895,0.0054222476,0.0029065234,0.012740975,0.000067218694,0.633164,0.00042491584],"about_ca_topic_score_codex":0.0005929979,"about_ca_topic_score_gemma":0.00036418613,"teacher_disagreement_score":0.32072166,"about_ca_system_score_codex":0.000044566485,"about_ca_system_score_gemma":0.00014826198,"threshold_uncertainty_score":0.59909284},"labels":[],"label_agreement":null},{"id":"W4410056551","doi":"10.1038/s41597-025-05054-0","title":"A Dataset for Understanding Radiologist-Artificial Intelligence Collaboration","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","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":"Artificial Intelligence in Medicine (Canada)","funders":"Alfred P. Sloan Foundation","keywords":"Computer science; Data science; Artificial intelligence","score_opus":0.6273723659303506,"score_gpt":0.545717655039745,"score_spread":0.08165471089060561,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410056551","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":[0.005125703,0.00045729862,0.9287846,0.026823873,0.009419929,0.001989005,0.02666156,0.00008229029,0.00065574364],"genre_scores_gemma":[0.8346319,0.0000320363,0.008767652,0.00097548217,0.0004133298,0.00007917138,0.15334189,0.000012777346,0.0017457496],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99835753,0.000039810093,0.00044808435,0.00069136673,0.00018534034,0.00027785802],"domain_scores_gemma":[0.9978175,0.000291728,0.00008321618,0.0014941203,0.00022444666,0.000088980094],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017810516,0.00009765381,0.00016363568,0.00025003438,0.00057342276,0.0002933355,0.00048012615,0.00008509748,0.00008878729],"category_scores_gemma":[0.001999852,0.00009045503,0.000024593892,0.0010455789,0.00032785992,0.00034894948,0.00015724533,0.000104542305,0.000075182325],"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":[0.00023815935,0.00016181247,0.00031807213,0.0001919418,0.00003062781,0.0000022014506,0.0004491904,0.000036472757,0.0018374171,0.05809096,0.8526469,0.08599624],"study_design_scores_gemma":[0.00006843653,0.00022459037,0.00008395338,0.00027252562,0.00021022026,0.000010078314,0.02392266,0.08091519,0.023544986,0.33597815,0.534471,0.0002982141],"about_ca_topic_score_codex":0.000088405766,"about_ca_topic_score_gemma":0.00050562737,"teacher_disagreement_score":0.92001694,"about_ca_system_score_codex":0.00023981795,"about_ca_system_score_gemma":0.00096126244,"threshold_uncertainty_score":0.4410362},"labels":[],"label_agreement":null},{"id":"W4410265518","doi":"10.1038/s41597-025-05090-w","title":"A database for igneous rocks of the Newfoundland Appalachians","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Geological and Geochemical Analysis","field":"Earth and Planetary 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":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Igneous rock; Geology; Geochemistry; Database; Computer science","score_opus":0.02718396622174989,"score_gpt":0.241120765856028,"score_spread":0.2139367996342781,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410265518","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":[0.86561996,0.0022361467,0.0133683635,0.007905282,0.004190684,0.0010692357,0.067852795,0.00007859734,0.037678912],"genre_scores_gemma":[0.9861001,0.000003887397,0.00086587114,0.00019991442,0.000027149996,9.425463e-7,0.006107309,5.874764e-7,0.0066942675],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990672,0.00002833495,0.00016138723,0.00041134068,0.00014813623,0.0001836223],"domain_scores_gemma":[0.99853057,0.00015941204,0.0000504897,0.0011683828,0.00004661161,0.000044540295],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005058236,0.000065180066,0.00011458691,0.00004373256,0.00028218183,0.000081636135,0.0014791035,0.000025443998,0.0015069938],"category_scores_gemma":[0.0003572311,0.000034705765,0.000058071368,0.0005911961,0.00027884103,0.00009676933,0.000228103,0.000059295482,0.00003935111],"study_design_candidate":"observational","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":[0.00005951728,0.000093404735,0.801697,0.00011182374,0.00007615587,0.0000016131598,0.000049188395,0.0007304844,0.0011229354,0.0006825962,0.1531048,0.042270456],"study_design_scores_gemma":[0.00068547577,0.000052869935,0.2093008,0.00009264027,0.0003090823,0.000005073929,0.00019351578,0.13921382,0.0013303993,0.090482876,0.5580182,0.00031524172],"about_ca_topic_score_codex":0.0037470006,"about_ca_topic_score_gemma":0.051543426,"teacher_disagreement_score":0.5923962,"about_ca_system_score_codex":0.000001116009,"about_ca_system_score_gemma":0.000059565078,"threshold_uncertainty_score":0.99940574},"labels":[],"label_agreement":null},{"id":"W4410308840","doi":"10.1038/s41597-025-05087-5","title":"The SESAME Human-Earth Atlas","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Atmospheric and Environmental Gas Dynamics","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":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; National Aeronautics and Space Administration","keywords":"Atlas (anatomy); Earth (classical element); Astrobiology; Geography; Geology; Biology; Astronomy; Physics; Paleontology","score_opus":0.016197631690290763,"score_gpt":0.2560904796216868,"score_spread":0.23989284793139604,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410308840","genre_codex":"empirical","genre_gemma":"other","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":[0.6968314,0.00048152043,0.019036274,0.0033998322,0.005569883,0.0008810575,0.00035251863,0.0002498025,0.2731977],"genre_scores_gemma":[0.48586813,0.000044921162,0.007500168,0.00048164884,0.000045401703,0.000014303369,0.0005187329,0.000018111316,0.5055086],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99855053,0.000034103323,0.00016580214,0.00060576707,0.00033087697,0.00031289627],"domain_scores_gemma":[0.9977419,0.000041672753,0.000043995875,0.002109002,0.0000020889267,0.00006133895],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00070413825,0.00010368925,0.00007205053,0.0000048750617,0.0013306624,0.00029183354,0.0019875932,0.000033895623,0.00093735004],"category_scores_gemma":[0.000040166244,0.000071562776,0.000026699896,0.00036011057,0.0013304327,0.00029501936,0.0028969366,0.00011064749,0.0013513793],"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":[0.000014039752,0.00018422256,0.05146186,0.000008495481,0.000039937262,0.000009559606,0.00019398783,0.0060430234,0.009089522,0.004917444,0.8040839,0.12395404],"study_design_scores_gemma":[0.00010066528,0.0000070128003,0.031943947,0.0000051589845,0.000011571904,0.0000012049472,0.00016757664,0.010577778,0.000109095745,0.0017904572,0.9551864,0.000099117766],"about_ca_topic_score_codex":0.0001757749,"about_ca_topic_score_gemma":0.00043538204,"teacher_disagreement_score":0.23231086,"about_ca_system_score_codex":0.00006641305,"about_ca_system_score_gemma":0.000012987251,"threshold_uncertainty_score":0.9999759},"labels":[],"label_agreement":null},{"id":"W4410315829","doi":"10.1038/s41597-025-05133-2","title":"A beneficial arthropod dataset for agricultural landscapes in Western Canada, and adjacent mountain ecosystems","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Ecology and Vegetation Dynamics Studies","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":true,"ca_institutions":"Agriculture and Agri-Food Canada; Ducks Unlimited Canada; Calgary Laboratory Services; Simon Fraser University; University of Calgary","funders":"Alberta Innovates; Alberta Innovates Bio Solutions; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Alberta Canola Producers Commission; TD Friends of the Environment Foundation; Institute for Wetland and Waterfowl Research, Ducks Unlimited Canada; Alberta Biodiversity Monitoring Institute; Saskatchewan Canola Development Commission; Alberta Conservation Association","keywords":"Arthropod; Agriculture; Ecosystem; Geography; Ecology; Ecosystem services; Agroforestry; Environmental resource management; Biology; Environmental science","score_opus":0.012400308234453119,"score_gpt":0.25043991261102744,"score_spread":0.23803960437657432,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410315829","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":[0.964861,0.00015898302,0.00013845618,0.001335,0.00095224107,0.00038224683,0.031937856,0.000007561535,0.00022666372],"genre_scores_gemma":[0.97714734,0.000010805357,0.00016340532,0.0001347149,0.000015449654,0.000027742246,0.02107864,0.0000023921812,0.001419529],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9990551,0.000026767033,0.00016049825,0.00045289425,0.00011080749,0.00019394589],"domain_scores_gemma":[0.9994927,0.00006652635,0.000040597613,0.0003627541,0.0000069020425,0.000030533432],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046997433,0.00007564161,0.00010612622,0.00003126215,0.00030078195,0.000076818265,0.00037626878,0.000026675958,0.00004432919],"category_scores_gemma":[0.000059487687,0.000060355575,0.0000060858424,0.00018301177,0.00010687617,0.00020225167,0.00065482093,0.000046071513,0.000012751873],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016415945,0.000070643495,0.5263965,0.000050084356,0.000021816786,0.0000035458352,0.00020023808,0.00060635153,0.00017769093,0.0005290325,0.4705395,0.0013881313],"study_design_scores_gemma":[0.00063933746,0.000016123271,0.6315808,0.000031084313,0.000022264896,0.0000028109275,0.00070666615,0.017614111,0.000029144221,0.00032154308,0.34885505,0.00018104316],"about_ca_topic_score_codex":0.07734619,"about_ca_topic_score_gemma":0.99646133,"teacher_disagreement_score":0.9191151,"about_ca_system_score_codex":0.00009499063,"about_ca_system_score_gemma":0.00005030752,"threshold_uncertainty_score":0.92879784},"labels":[],"label_agreement":null},{"id":"W4410414373","doi":"10.1038/s41597-025-05052-2","title":"A collection of FAIR Dutch Freedom of Information Act documents","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Data Quality and Management","field":"Decision 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":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Canadian Institute of Steel Construction","keywords":"Metadata; Computer science; World Wide Web; Standardization; Information retrieval; Publishing; Quality (philosophy); Process (computing); Metadata repository; Political science","score_opus":0.1328692685136867,"score_gpt":0.42210031862309055,"score_spread":0.28923105010940386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410414373","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":[0.15377128,0.00022500292,0.4645215,0.006626419,0.03169719,0.0032167947,0.037307378,0.00018510445,0.30244932],"genre_scores_gemma":[0.95077693,0.000010910801,0.0055714003,0.00016384994,0.000017703192,0.000009711443,0.0045501706,0.0000030661217,0.038896244],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972411,0.000120500794,0.00082240533,0.0003741871,0.0013125612,0.000129273],"domain_scores_gemma":[0.9962247,0.00024151983,0.00039446604,0.0027521625,0.00035504444,0.000032085747],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009052688,0.00006455895,0.0001777234,0.0007412124,0.00016404934,0.00047444724,0.0028737755,0.000031972588,0.0003829104],"category_scores_gemma":[0.003559891,0.00005128905,0.00003777591,0.0028446624,0.00026664758,0.0031639002,0.0020229127,0.000046136876,0.00020217836],"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":[0.000025726005,0.00006933449,0.0007010252,0.000037580474,0.000020682137,1.0480466e-7,0.00036145322,0.00003833878,0.00021182813,0.009029287,0.9336239,0.055880755],"study_design_scores_gemma":[0.00043304966,0.000023451794,0.008052328,0.0000462414,0.000023774082,2.0222586e-7,0.0019263768,0.0050157756,0.0022720713,0.01810139,0.96403486,0.00007045928],"about_ca_topic_score_codex":0.0002892763,"about_ca_topic_score_gemma":0.00029887582,"teacher_disagreement_score":0.79700565,"about_ca_system_score_codex":0.000022762588,"about_ca_system_score_gemma":0.00017036144,"threshold_uncertainty_score":0.53402376},"labels":[],"label_agreement":null},{"id":"W4410464763","doi":"10.1038/s41597-025-05188-1","title":"Transcriptome data from the interdigital webs of the Chinese Soft-shell Turtle (Pelodiscus sinensis)","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Turtle Biology and Conservation","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Liaoning Revitalization Talents Program","keywords":"Turtle (robot); Shell (structure); Biology; Transcriptome; Ecology; Engineering; Gene","score_opus":0.026948280065522405,"score_gpt":0.26446882480081324,"score_spread":0.23752054473529083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410464763","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":[0.9594944,0.00031194312,0.0007988362,0.0094327815,0.0045056283,0.00034224213,0.016610201,0.00003687838,0.008467097],"genre_scores_gemma":[0.98822546,0.0000028340812,0.000097126554,0.0005207408,0.00003305381,0.0000021481117,0.0036346065,0.0000039337065,0.007480101],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9986649,0.00008741066,0.00021361555,0.00064454565,0.00022914681,0.00016034211],"domain_scores_gemma":[0.9956131,0.00012865503,0.00007278503,0.004151748,0.000010075196,0.000023663812],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069581094,0.00010307105,0.000102349775,0.000016161272,0.00029703815,0.00012248517,0.005058322,0.000049383405,0.00083027023],"category_scores_gemma":[0.0002857723,0.000050222934,0.000035499463,0.0006037254,0.001079863,0.0006145591,0.0037008713,0.00012681102,0.0003001299],"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":[0.000035422305,0.00010583382,0.16416675,0.000005180481,0.000041321357,8.507733e-7,0.0003653542,0.000014577144,0.03791923,0.0001294302,0.78236395,0.014852104],"study_design_scores_gemma":[0.00023874376,0.000005959573,0.5543981,0.000031014624,0.000049820293,0.0000013088495,0.00018690187,0.0036860392,0.0009900357,0.0034471515,0.43684992,0.000114982504],"about_ca_topic_score_codex":0.0002973411,"about_ca_topic_score_gemma":0.002705681,"teacher_disagreement_score":0.39023137,"about_ca_system_score_codex":0.000018357434,"about_ca_system_score_gemma":0.00004505049,"threshold_uncertainty_score":0.9399705},"labels":[],"label_agreement":null},{"id":"W4410573777","doi":"10.1038/s41597-025-05184-5","title":"Global Impacts Dataset of Invasive Alien Species (GIDIAS)","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Species Distribution and Climate Change","field":"Environmental Science","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":"Canadian Armed Forces","funders":"Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"Alien; Biodiversity; Invasive species; Alien species; Taxon; Ecology; Ecosystem; Ecosystem services; Introduced species; Geography; Livelihood; Global change; Environmental resource management; Invertebrate; Biology; Climate change; Environmental science; Agriculture; Political science","score_opus":0.06371622324894954,"score_gpt":0.313654097728842,"score_spread":0.24993787447989246,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410573777","genre_codex":"dataset","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":[0.3348571,0.00016194869,0.00017009096,0.001113415,0.0018713161,0.00031214464,0.5144269,0.000049585906,0.14703748],"genre_scores_gemma":[0.8176684,0.00008016287,0.00024682516,0.0006106396,0.00002698628,0.000006313886,0.1744559,0.0000062639283,0.0068985424],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985075,0.00003093933,0.00023320482,0.0005631062,0.00038903978,0.00027623537],"domain_scores_gemma":[0.99787354,0.000034782268,0.00009061413,0.0018922355,0.00001571886,0.00009312031],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0005855473,0.00010097975,0.00012601275,0.000034089626,0.00017753811,0.00016041801,0.0017321031,0.000036520316,0.045096524],"category_scores_gemma":[0.00034642822,0.00008887736,0.0000258836,0.0010166175,0.0008178073,0.0004725957,0.0028124894,0.00003841312,0.0016488471],"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":[0.000006321383,0.000068008456,0.02074577,0.0000127914045,0.0000077103705,0.0000022743461,0.000027134272,0.0000025663878,0.0037830335,0.0011477194,0.9736938,0.0005028727],"study_design_scores_gemma":[0.00019118135,0.0000095110345,0.16192125,0.000016393562,0.000018685376,0.0000017413332,0.0008836852,0.000033540517,0.004315074,0.00027416678,0.8322369,0.0000978769],"about_ca_topic_score_codex":0.0003178122,"about_ca_topic_score_gemma":0.004511253,"teacher_disagreement_score":0.48281124,"about_ca_system_score_codex":0.00025144636,"about_ca_system_score_gemma":0.000055463097,"threshold_uncertainty_score":0.99912846},"labels":[],"label_agreement":null},{"id":"W4410641159","doi":"10.1038/s41597-025-04833-z","title":"Open multi-center intracranial electroencephalography dataset with task probing conscious visual perception","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"EEG and Brain-Computer Interfaces","field":"Neuroscience","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":"Canadian Institute for Advanced Research","funders":"National Institute of Neurological Disorders and Stroke; National Institute of Mental Health; National Institute of General Medical Sciences; Templeton World Charity Foundation; Max-Planck-Gesellschaft","keywords":"Electroencephalography; Computer science; Perception; Task (project management); Stimulus (psychology); Consciousness; Cognitive psychology; Brain activity and meditation; Visual perception; Psychology; Artificial intelligence; Neuroscience","score_opus":0.04741419624711331,"score_gpt":0.3439156638838501,"score_spread":0.2965014676367368,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410641159","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":[0.8967768,0.00004839119,0.043093797,0.0020076218,0.004957664,0.0026047928,0.04905577,0.0003291802,0.0011259663],"genre_scores_gemma":[0.97718996,0.000007231829,0.0073446142,0.0015628369,0.000065704895,0.000029885527,0.012819014,0.000017173617,0.0009635661],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9970286,0.00015032502,0.000275203,0.0017054565,0.00034712264,0.00049328833],"domain_scores_gemma":[0.9980268,0.0000861869,0.00010220062,0.0016400391,0.00005457951,0.00009021866],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00081728224,0.00020035765,0.0001917768,0.00028770056,0.00068194076,0.0026042424,0.0046097906,0.00004577726,0.00008373501],"category_scores_gemma":[0.0001475466,0.00015447313,0.000024113167,0.001045397,0.0007541795,0.0016792073,0.0029621515,0.00024036104,0.00012519516],"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":[0.0001679092,0.0011711512,0.0011851729,0.0000467068,0.000025515757,0.000059428825,0.0004211463,0.000009983434,0.6120684,0.00019213544,0.3689732,0.0156792],"study_design_scores_gemma":[0.011169225,0.00086598896,0.0049623474,0.00085788494,0.00016431509,0.00043085817,0.001008492,0.09160759,0.11846195,0.00057893316,0.76817584,0.0017165818],"about_ca_topic_score_codex":0.00005652539,"about_ca_topic_score_gemma":0.0003094314,"teacher_disagreement_score":0.49360648,"about_ca_system_score_codex":0.00003027082,"about_ca_system_score_gemma":0.00017316417,"threshold_uncertainty_score":0.99843115},"labels":[],"label_agreement":null},{"id":"W4410831600","doi":"10.1038/s41597-025-05098-2","title":"Monthly hydropower generation data for Western Canada to support Western-US interconnect power system studies","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Hydrology and Watershed Management Studies","field":"Environmental Science","cited_by":1,"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":"Pacific Northwest National Laboratory; Laboratory Directed Research and Development; U.S. Army Corps of Engineers; Bureau of Reclamation","keywords":"Hydropower; Hydroelectricity; Streamflow; Electricity generation; Environmental science; Surface runoff; Resource (disambiguation); Water resources; Water resource management; Environmental resource management; Hydrology (agriculture); Computer science; Geography; Power (physics); Engineering; Drainage basin; Ecology; Cartography","score_opus":0.06278394105957384,"score_gpt":0.31492168670902043,"score_spread":0.2521377456494466,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410831600","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":[0.9022402,0.0007108554,0.00937653,0.017806435,0.029890366,0.0039561633,0.023440666,0.0002839958,0.012294751],"genre_scores_gemma":[0.972149,0.0000050150757,0.00038734626,0.0016839739,0.000055095796,0.00006113027,0.0049065384,0.000012599452,0.02073927],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974424,0.0000620469,0.0003423097,0.0013969275,0.00032776396,0.0004285069],"domain_scores_gemma":[0.9966047,0.000058224017,0.000056354198,0.0031748035,0.000026220276,0.00007969766],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014270687,0.00019440746,0.00025936577,0.00008347409,0.0006214097,0.00018221549,0.0026054126,0.00003761799,0.00009035189],"category_scores_gemma":[0.00017543483,0.00016413636,0.000019571671,0.00029834348,0.00026617627,0.00069962454,0.007555958,0.00006454495,0.00026222644],"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":[0.000018111443,0.000029799217,0.009831166,0.000050104034,0.0001344026,0.000014406485,0.0002611676,0.00045006993,0.0002896702,0.000035846468,0.98822904,0.0006562142],"study_design_scores_gemma":[0.00031040946,0.0000569298,0.0028056626,0.00004675178,0.000104258244,0.0000014081749,0.0008608845,0.003985953,0.00038638033,0.000020378788,0.9911778,0.00024317869],"about_ca_topic_score_codex":0.01746174,"about_ca_topic_score_gemma":0.69100344,"teacher_disagreement_score":0.67354167,"about_ca_system_score_codex":0.00026908808,"about_ca_system_score_gemma":0.000068501504,"threshold_uncertainty_score":0.9890811},"labels":[],"label_agreement":null},{"id":"W4410838461","doi":"10.1038/s41597-025-05178-3","title":"Haplotype resolved chromosome-level genome assembly of the gold barb (Barbodes semifasciolatus)","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","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":"Ministry of Agriculture","funders":"Guangdong Academy of Sciences; National Natural Science Foundation of China","keywords":"Haplotype; Biology; Chromosome; Genome; Genetics; Evolutionary biology; Gene; Allele","score_opus":0.039900493297992064,"score_gpt":0.27230831852169896,"score_spread":0.2324078252237069,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410838461","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":[0.98328644,0.0047877645,0.0003813463,0.00040262047,0.0018355437,0.0003050277,0.0039457977,0.000005959039,0.0050495],"genre_scores_gemma":[0.9890129,0.0001199427,0.0007681493,0.00012706089,0.00008306272,0.00000690987,0.0006104008,0.000011699328,0.0092598945],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985862,0.00005489581,0.00025241214,0.00067719555,0.00017566394,0.0002536553],"domain_scores_gemma":[0.9971021,0.000019295701,0.000094727075,0.0026141214,0.00012917197,0.00004057747],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006303214,0.00013872994,0.00015734966,0.000052728694,0.00022066467,0.00007397422,0.0018606437,0.00008603912,0.000010458858],"category_scores_gemma":[0.00022912986,0.00010372818,0.00007214569,0.00033239753,0.00038430517,0.000002297682,0.0025426676,0.000075474716,0.000009152527],"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":[0.000012973448,0.000036864876,0.0012260338,0.000023430757,0.00008377233,2.3602779e-7,0.000031106152,0.000022316532,0.96880865,0.00023791491,0.02874411,0.0007725763],"study_design_scores_gemma":[0.00041631644,0.000047599166,0.062888905,0.000043136457,0.00007710253,0.0000019467436,0.000112976275,0.00021233446,0.3435148,0.0004026808,0.59204286,0.00023934474],"about_ca_topic_score_codex":0.00003020109,"about_ca_topic_score_gemma":0.00018546311,"teacher_disagreement_score":0.62529385,"about_ca_system_score_codex":0.000010237194,"about_ca_system_score_gemma":0.00023256983,"threshold_uncertainty_score":0.42299125},"labels":[],"label_agreement":null},{"id":"W4411183390","doi":"10.1038/s41597-025-05143-0","title":"SEEDNet: Covariate-free multi-country settlement-level epidemiological estimates datasets for network analysis","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Health, Environment, Cognitive Aging","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":"McGill University; McGill University Health Centre; Hospital for Sick Children; Public Health Ontario; SickKids Foundation; Toronto Metropolitan University; University of Toronto","funders":"Global Affairs Canada","keywords":"Covariate; Settlement (finance); Geography; Statistics; Epidemiology; Econometrics; Computer science; Mathematics; Medicine; World Wide Web","score_opus":0.12200161197404019,"score_gpt":0.3688138084758872,"score_spread":0.246812196501847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411183390","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":[0.0051536583,0.00024559407,0.78478366,0.002103086,0.0015340429,0.0017396627,0.20325561,0.00013970591,0.0010449797],"genre_scores_gemma":[0.06185621,0.00008566776,0.59252584,0.0071781105,0.00021257042,0.0003084392,0.33316487,0.000060458377,0.0046078344],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99514383,0.00025327955,0.00067508116,0.0023992641,0.0004935585,0.0010349565],"domain_scores_gemma":[0.99394566,0.00095136726,0.00023311326,0.0046224673,0.00001417662,0.00023322603],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008891926,0.00030504548,0.00047453743,0.00014766552,0.0010463498,0.0002608206,0.0032425462,0.00013224129,0.0020267414],"category_scores_gemma":[0.00318564,0.00026810984,0.00009619613,0.001924588,0.00084788474,0.0006432378,0.005039331,0.00023356543,0.0005005625],"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":[0.000030395335,0.00024531793,0.14111371,0.000039802624,0.00032205658,0.000007258915,0.000048253194,0.00970791,0.0005271282,0.00035782476,0.8383445,0.009255804],"study_design_scores_gemma":[0.0009357464,0.000021721498,0.31317514,0.000036752674,0.00070157874,0.0000011539039,0.00007386064,0.28356266,0.00009193228,0.0037356718,0.39727056,0.00039323443],"about_ca_topic_score_codex":0.00046137196,"about_ca_topic_score_gemma":0.0017269314,"teacher_disagreement_score":0.44107398,"about_ca_system_score_codex":0.00023189926,"about_ca_system_score_gemma":0.000063825544,"threshold_uncertainty_score":0.9999771},"labels":[],"label_agreement":null},{"id":"W4411277392","doi":"10.1038/s41597-025-05333-w","title":"Spatial occurrence records and distributions of tropical Asian butterflies","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Species Distribution and Climate Change","field":"Environmental 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":"The Scarborough Hospital","funders":"U.S. Geological Survey; University of Hong Kong; National Science Foundation","keywords":"Geography; Ecology; Tropical Asia; Climatology; Biology; Geology","score_opus":0.040857089169196587,"score_gpt":0.2903349810107173,"score_spread":0.24947789184152072,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411277392","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":[0.8892924,0.00010189336,0.008027207,0.0030388199,0.002220151,0.00025761503,0.060507283,0.00005846589,0.036496133],"genre_scores_gemma":[0.9943374,0.000015425945,0.00013754821,0.00003599012,0.0000083730965,0.0000040947134,0.004331945,0.0000012904254,0.0011279755],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99904144,0.000024669473,0.00016041678,0.00041684296,0.00018822809,0.00016837506],"domain_scores_gemma":[0.9990987,0.00002144724,0.000043463468,0.0007670408,0.000011892957,0.00005742627],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00020111431,0.000067325134,0.00009058803,0.000029706389,0.00021767337,0.00010200695,0.0005871874,0.000030199673,0.010973106],"category_scores_gemma":[0.00016180555,0.000060589333,0.000016773853,0.0003916106,0.0009473732,0.00019526797,0.0011547077,0.00005882231,0.00019150389],"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":[0.000013212149,0.00015748857,0.2787847,0.000025367443,0.000008669484,0.0000015164889,0.00008739849,2.5690457e-7,0.0028418058,0.00424765,0.6632278,0.050604142],"study_design_scores_gemma":[0.00013870736,0.000011736156,0.63122743,0.00001222448,0.000013202829,0.0000012920669,0.00030963754,0.00019749075,0.0010087638,0.00031466148,0.3666945,0.000070347494],"about_ca_topic_score_codex":0.00017495351,"about_ca_topic_score_gemma":0.0011808892,"teacher_disagreement_score":0.35244274,"about_ca_system_score_codex":0.00006759742,"about_ca_system_score_gemma":0.00001819203,"threshold_uncertainty_score":0.989931},"labels":[],"label_agreement":null},{"id":"W4411377134","doi":"10.1038/s41597-025-05301-4","title":"The Austronesian and the Micronesian Comparative Dictionaries as CLDF datasets","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Ministry of Education, India; Ministry of Education - Singapore","keywords":"Micronesian; Austronesian languages; Interoperability; Computer science; Comparative method; Linguistics; Comparative linguistics; Usability; Information retrieval; World Wide Web; History; Genealogy; Sociology; Philology","score_opus":0.0220802469138846,"score_gpt":0.3009350242765415,"score_spread":0.2788547773626569,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411377134","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":[0.8881877,0.047769755,0.0013927504,0.024354707,0.00552183,0.0016072401,0.019400368,0.00001538382,0.011750265],"genre_scores_gemma":[0.9906091,0.00032566255,0.00015198885,0.0001924047,0.00006976854,0.000017075517,0.0033149295,0.0000035828627,0.0053155064],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99915284,0.00006935142,0.00012288672,0.00041863153,0.000080093596,0.0001561729],"domain_scores_gemma":[0.99853927,0.000053268654,0.000041514675,0.001303667,0.000037076563,0.000025233983],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00062502443,0.00008814784,0.000084752304,0.000016192718,0.0012275024,0.00029044188,0.00079992093,0.000027676466,0.0000030526198],"category_scores_gemma":[0.000074094496,0.00004911638,0.000018850664,0.000098992496,0.0015832394,0.0000018719267,0.0013122137,0.000049644434,0.000009887714],"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":[0.00023535926,0.000036433838,0.0014992995,0.000011141309,0.00030537922,7.566402e-7,0.00034889692,0.000009416773,0.048553262,0.02121127,0.9226094,0.005179414],"study_design_scores_gemma":[0.00039201032,0.000012960776,0.005297362,0.000003872785,0.00003319746,0.0000039148144,0.00086108193,0.000086552056,0.003610535,0.0012794572,0.9883537,0.000065331675],"about_ca_topic_score_codex":0.00004881163,"about_ca_topic_score_gemma":0.0004086789,"teacher_disagreement_score":0.10242138,"about_ca_system_score_codex":0.0000032429127,"about_ca_system_score_gemma":0.00008272292,"threshold_uncertainty_score":0.94410795},"labels":[],"label_agreement":null},{"id":"W4411455735","doi":"10.1038/s41597-025-05330-z","title":"The Open Aurignacian Project: 3D scanning and the digital preservation of the Italian Paleolithic record","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Pleistocene-Era Hominins and Archaeology","field":"Social Sciences","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":"Université de Montréal","funders":"Università degli Studi di Ferrara; Eberhard Karls Universität Tübingen; European Commission; Social Sciences and Humanities Research Council of Canada; Université de Montréal; Università degli Studi di Siena; Deutsche Forschungsgemeinschaft; Università degli Studi di Genova; Ministero della cultura","keywords":"Aurignacian; Upper Paleolithic; Archaeology; 3d scanning; Middle Paleolithic; 3d model; Geography; Focus (optics); Computer science; Geology; Artificial intelligence","score_opus":0.06706645450932129,"score_gpt":0.35285486443349146,"score_spread":0.28578840992417015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411455735","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":[0.6746003,0.00070106593,0.00015597863,0.059759334,0.0049808626,0.0035064153,0.0016477583,0.00004602817,0.25460225],"genre_scores_gemma":[0.95816714,0.00003120961,0.00015495023,0.00014825657,0.000053300035,0.000030974803,0.000081825354,0.0000036284214,0.041328713],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985473,0.00033724256,0.00022013047,0.00036275867,0.00028726415,0.00024531185],"domain_scores_gemma":[0.99809754,0.00040963525,0.00014388545,0.0012383048,0.00008407067,0.000026579291],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":["sts"],"category_scores_codex":[0.0046195923,0.000065230175,0.00011016434,0.000039086175,0.002814065,0.0011390521,0.0040894845,0.00003803703,0.000010623966],"category_scores_gemma":[0.001808248,0.000031075004,0.000024249484,0.0007602677,0.0047504012,0.00073803985,0.0034286033,0.00011269028,0.0000021223498],"study_design_candidate":"not_applicable","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":[0.00013341139,0.000063291416,0.24287556,0.000035289646,0.00007238445,0.0000010344733,0.028039142,0.0000022998026,0.000053156695,0.41928115,0.13951033,0.16993295],"study_design_scores_gemma":[0.00037864133,0.0000079674055,0.04744101,0.00007018316,0.000017219498,3.953398e-7,0.0062360237,0.0006953131,0.00002243434,0.028923437,0.916136,0.000071337876],"about_ca_topic_score_codex":0.0009194825,"about_ca_topic_score_gemma":0.051009133,"teacher_disagreement_score":0.7766257,"about_ca_system_score_codex":0.00001775613,"about_ca_system_score_gemma":0.00063245837,"threshold_uncertainty_score":0.99989784},"labels":[],"label_agreement":null},{"id":"W4411509208","doi":"10.1038/s41597-025-05332-x","title":"A minimum data standard for wildlife disease research and surveillance","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Zoonotic diseases and public health","field":"Medicine","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":"Université de Montréal","funders":"National Science Foundation","keywords":"Metadata; Wildlife; Data sharing; Wildlife disease; Computer science; Transparency (behavior); Best practice; Data science; Table (database); Data element; Data mining; Information retrieval; World Wide Web; Ecology; Biology; Medicine","score_opus":0.23073925653850116,"score_gpt":0.47858487912309405,"score_spread":0.2478456225845929,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411509208","genre_codex":"dataset","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":[0.13689366,0.013517599,0.012333931,0.2550463,0.008485946,0.008596753,0.54480684,0.00034380634,0.019975135],"genre_scores_gemma":[0.7441849,0.0004084953,0.007410771,0.0045297765,0.0008652409,0.00010697099,0.1634622,0.000059443544,0.07897215],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99735755,0.000084567255,0.00025137817,0.0012161931,0.00060327316,0.00048703206],"domain_scores_gemma":[0.99308914,0.00041730364,0.00003439965,0.0054716407,0.00037268235,0.0006148499],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006929251,0.00009362099,0.00021667972,0.00022398628,0.00046001642,0.0004385639,0.0012804121,0.00003399365,0.00010938247],"category_scores_gemma":[0.00506663,0.000077749464,0.00001699018,0.0007257211,0.00057191,0.00032156598,0.0020305684,0.00013167624,0.000015920676],"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":[0.0004928952,0.0001317298,0.005577037,0.0005878308,0.00002463648,0.0000083890745,0.000019025385,7.695692e-8,0.000008131886,0.002468896,0.96110547,0.029575877],"study_design_scores_gemma":[0.0010805179,0.000064274886,0.010476105,0.00014671759,0.000026984953,0.0000010719709,0.00019972913,0.006505108,0.0000011427893,0.0023859998,0.97903997,0.00007236642],"about_ca_topic_score_codex":0.00004807762,"about_ca_topic_score_gemma":0.00009606041,"teacher_disagreement_score":0.6072913,"about_ca_system_score_codex":0.000038587652,"about_ca_system_score_gemma":0.0029276453,"threshold_uncertainty_score":0.6065595},"labels":[],"label_agreement":null},{"id":"W4411881942","doi":"10.1038/s41597-025-05365-2","title":"Cross-cultural data on romantic love and mate preferences from 117,293 participants across 175 countries","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Evolutionary Psychology and Human Behavior","field":"Psychology","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":"Saint Mary's University","funders":"Narodowe Centrum Nauki; Eesti Teadusagentuur; Fundacja na rzecz Nauki Polskiej","keywords":"Physical attractiveness; Social psychology; Psychology; Romance; Attractiveness; Jealousy; Generalizability theory; Friendship; Diversity (politics); Trait; Developmental psychology; Sociology","score_opus":0.20308440465524344,"score_gpt":0.482523738825341,"score_spread":0.2794393341700976,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411881942","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":[0.9372137,0.0011472617,0.00002250163,0.000595179,0.0068333144,0.0002302782,0.04876651,0.00007313834,0.005118089],"genre_scores_gemma":[0.9353058,0.000022848788,0.000119393924,0.0002869102,0.00010981967,0.00001078756,0.0144005595,0.00001050903,0.04973341],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99678856,0.00013781694,0.0003758278,0.0018053622,0.00026617004,0.0006262636],"domain_scores_gemma":[0.99504656,0.00018364526,0.00012240955,0.0044556293,0.00009256085,0.00009922161],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0011706068,0.00021022369,0.00024364739,0.00008293163,0.00072500494,0.0010382286,0.002834034,0.00015935683,0.0044011073],"category_scores_gemma":[0.00014257309,0.0001743724,0.000019896841,0.00023369152,0.0024137152,0.0011126455,0.0017946291,0.00025286232,0.004109076],"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":[0.00031214842,0.00046277788,0.26762977,0.00002973033,0.00018354929,0.00004305371,0.0039910376,0.0000010254511,0.00032359152,0.0056053293,0.717935,0.0034829576],"study_design_scores_gemma":[0.00074101944,0.00003470903,0.8488599,0.00007239749,0.0000904063,0.0000045522725,0.0010644582,0.000082858765,0.000047141893,0.0020403224,0.14676112,0.00020110827],"about_ca_topic_score_codex":0.00020757673,"about_ca_topic_score_gemma":0.0009887232,"teacher_disagreement_score":0.5812301,"about_ca_system_score_codex":0.000018281999,"about_ca_system_score_gemma":0.000060309812,"threshold_uncertainty_score":0.9999988},"labels":[],"label_agreement":null},{"id":"W4411881951","doi":"10.1038/s41597-025-05257-5","title":"An Africa-wide agricultural production database to support policy and satellite-based measurement systems","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Agricultural Economics and Policy","field":"Agricultural and Biological Sciences","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 Manitoba","funders":"Hertz Foundation; Bill and Melinda Gates Foundation","keywords":"Agriculture; Agricultural productivity; Satellite; Production (economics); Database; Environmental resource management; Remote sensing; Environmental science; Computer science; Geography; Archaeology; Engineering; Economics","score_opus":0.08821594327494711,"score_gpt":0.27868338972732887,"score_spread":0.19046744645238176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411881951","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":[0.9707089,0.0004917932,0.00002893745,0.015278756,0.0022091244,0.0012462421,0.0056775394,0.00017366007,0.004185024],"genre_scores_gemma":[0.98825693,0.000018718538,0.00012570791,0.00033630666,0.00049810053,0.000029577617,0.006579184,0.0000010047575,0.0041544884],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978014,0.000087365726,0.00031061054,0.001062727,0.0003154478,0.00042240272],"domain_scores_gemma":[0.99882835,0.00005060995,0.000088755645,0.0005415755,0.00020983686,0.00028084728],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001470522,0.00018943958,0.00018820119,0.00006366796,0.0005517902,0.0009787324,0.001044684,0.00005654534,0.00003579797],"category_scores_gemma":[0.00035232902,0.00006984981,0.000030847896,0.0010744641,0.00010714614,0.00063167675,0.0004181244,0.00008219487,0.000088064546],"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":[0.00004281288,0.00027631488,0.002372717,0.00006793698,0.000029273944,0.0000024122087,0.0001835108,0.0000999557,0.49450573,0.003811646,0.4131889,0.08541878],"study_design_scores_gemma":[0.000108677246,0.000105965155,0.0711518,0.00006266212,0.000026324384,0.0000041525723,0.00056355965,0.00024950656,0.0034607502,0.000075806856,0.92388535,0.00030544266],"about_ca_topic_score_codex":0.00082760525,"about_ca_topic_score_gemma":0.0018985443,"teacher_disagreement_score":0.5106965,"about_ca_system_score_codex":0.00011502065,"about_ca_system_score_gemma":0.00008808617,"threshold_uncertainty_score":0.9437939},"labels":[],"label_agreement":null},{"id":"W4411883243","doi":"10.1038/s41597-025-05192-5","title":"De novo Genome Assembly and Annotation of 12 Fungi Associated with Fruit Tree Decline Syndrome in ON, Canada","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Plant Pathogens and Fungal Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Agriculture and Agri-Food Canada","funders":"Agriculture and Agri-Food Canada; Hospital for Sick Children; Ministry of Agriculture, Food and Rural Affairs; McGill University; Génome Québec; Ontario Ministry of Agriculture, Food and Rural Affairs; Government of Canada","keywords":"Biology; Genome; Abiotic component; Ecology; Gene; Genetics","score_opus":0.01485561878516139,"score_gpt":0.23740830898332904,"score_spread":0.22255269019816765,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411883243","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":[0.98310125,0.00041215942,0.00008091199,0.00004806593,0.000077705736,0.000082348466,0.015823573,0.0000024111444,0.00037158132],"genre_scores_gemma":[0.9873347,0.0000150247415,0.0000733689,0.00012789581,0.0000048757506,0.0000025943589,0.011551337,0.000003579891,0.00088658306],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9992653,0.000028901637,0.000118312695,0.0003285308,0.00011773659,0.00014117979],"domain_scores_gemma":[0.99942577,0.00001994813,0.000046786554,0.00042204972,0.000041838313,0.0000436382],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002801511,0.00006627899,0.00008858348,0.00005833508,0.000046960133,0.00003745202,0.00026183695,0.000036824396,0.0000033850554],"category_scores_gemma":[0.00014087536,0.000058506503,0.000008064675,0.00018042805,0.000052114956,0.000005660648,0.00016504755,0.00003107683,3.1994233e-7],"study_design_candidate":"observational","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":[0.00008748641,0.00011837626,0.036769055,0.000030127012,0.00006272243,0.000070245216,0.000008847674,0.00009123754,0.9549808,0.00003882241,0.006674123,0.0010681532],"study_design_scores_gemma":[0.0006277414,0.00008853119,0.9833061,0.00007797249,0.00004214459,0.000011265381,0.000040502855,0.00057246984,0.005901581,0.000020344565,0.009183496,0.00012782143],"about_ca_topic_score_codex":0.003016603,"about_ca_topic_score_gemma":0.36001202,"teacher_disagreement_score":0.9490792,"about_ca_system_score_codex":0.000023894223,"about_ca_system_score_gemma":0.00057119975,"threshold_uncertainty_score":0.65166605},"labels":[],"label_agreement":null},{"id":"W4411885790","doi":"10.1038/s41597-025-05216-0","title":"A Harmonized Dataset of High-Resolution Embodied Life Cycle Assessment Results for Buildings in North America","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Sustainable Building Design and Assessment","field":"Engineering","cited_by":9,"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":"Center for the Built Environment; ClimateWorks Foundation; University of Washington; Alfred P. Sloan Foundation","keywords":"Life-cycle assessment; Reuse; Sustainability; Environmental impact assessment; Building design; Computer science; Built environment; Environmental resource management; Set (abstract data type); Impact assessment; Architectural engineering; Environmental science; Civil engineering; Engineering; Production (economics); Ecology","score_opus":0.0279553434322536,"score_gpt":0.30075236889562457,"score_spread":0.272797025463371,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411885790","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":[0.19834417,0.00078547746,0.5686829,0.0012935124,0.005237057,0.0031489956,0.22018054,0.0005054752,0.0018218483],"genre_scores_gemma":[0.8753043,0.000033723514,0.0510222,0.00006420147,0.00003587128,0.000092683265,0.07311115,0.00002031463,0.00031556777],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981727,0.000039821673,0.00053719134,0.00061483216,0.00025642142,0.00037903435],"domain_scores_gemma":[0.9980492,0.00014784475,0.000096321644,0.0015534853,0.00008051638,0.000072661955],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011477396,0.00014915275,0.00027111205,0.00038831573,0.00012339425,0.00017124554,0.001034893,0.000042859876,0.000011959374],"category_scores_gemma":[0.00034145772,0.00015271906,0.00002870701,0.0011258634,0.000112806556,0.0003568679,0.00042755375,0.00011883509,0.000004629161],"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":[0.00016721504,0.00020208872,0.00015759154,0.00040228156,0.00008830061,0.0000054959773,0.00010290695,0.07480819,0.002212043,0.0014869568,0.90257514,0.017791772],"study_design_scores_gemma":[0.0022881024,0.000036158177,0.0023273474,0.00009590433,0.000051155414,2.2551168e-7,0.00032002368,0.61881673,0.00052466575,0.00066441705,0.3746476,0.00022767944],"about_ca_topic_score_codex":0.00020774067,"about_ca_topic_score_gemma":0.00016764634,"teacher_disagreement_score":0.6769601,"about_ca_system_score_codex":0.00015591443,"about_ca_system_score_gemma":0.00027801434,"threshold_uncertainty_score":0.62277025},"labels":[],"label_agreement":null},{"id":"W4411886742","doi":"10.1038/s41597-025-04941-w","title":"A global assemblage of regional prescribed burn records — GlobalRx","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Fire effects on ecosystems","field":"Environmental Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Parks Canada","funders":"European Commission; Research Councils UK","keywords":"Environmental science; Climate change; Environmental resource management; Global warming; Scale (ratio); Geography; Climatology; Ecology; Cartography","score_opus":0.024384418077484607,"score_gpt":0.28147021078266327,"score_spread":0.2570857927051787,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411886742","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":[0.7852692,0.0003876073,0.004358786,0.0012827815,0.009337146,0.0012650689,0.0076571065,0.00017815417,0.19026414],"genre_scores_gemma":[0.9857187,0.0000036703277,0.0016858403,0.0001317776,0.00003728779,0.000011565039,0.0009043987,0.000007494995,0.011499212],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975754,0.00012523921,0.00034229265,0.00095677335,0.0006592267,0.0003410736],"domain_scores_gemma":[0.99700594,0.00006609447,0.00013534892,0.0026754374,0.000021981667,0.00009520706],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016954691,0.00014110241,0.00019875575,0.0000491995,0.00016977053,0.00015584801,0.00254949,0.00006952586,0.0008208673],"category_scores_gemma":[0.00033611374,0.0001299412,0.0000496659,0.0014540834,0.00047603453,0.000570449,0.0022501247,0.00006640345,0.0006045374],"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":[0.000019448904,0.00011958012,0.025564712,0.000038771803,0.000017752174,0.000006143411,0.000024851575,0.000022044138,0.0057791146,0.00039592994,0.9539215,0.01409016],"study_design_scores_gemma":[0.0005536786,0.000047242494,0.108110316,0.00017529055,0.000046777717,0.00001533969,0.000070705224,0.026065629,0.0013220684,0.0021062794,0.86119974,0.00028695067],"about_ca_topic_score_codex":0.0020216256,"about_ca_topic_score_gemma":0.002719647,"teacher_disagreement_score":0.20044954,"about_ca_system_score_codex":0.0002190759,"about_ca_system_score_gemma":0.000078844256,"threshold_uncertainty_score":0.89879215},"labels":[],"label_agreement":null},{"id":"W4411887324","doi":"10.1038/s41597-025-05423-9","title":"Characterizing organisms from three domains of life with universal primers from throughout the global ocean","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Microbial Community Ecology and Physiology","field":"Environmental Science","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":"St. Francis Xavier University","funders":"Marine National Facility; University of California, Santa Barbara; University of Southern California; Australian Antarctic Division; University of Tasmania; Simons Foundation; Commonwealth Scientific and Industrial Research Organisation; National Science Foundation","keywords":"Archaea; Biology; Amplicon; Ribosomal RNA; Plankton; Bacteria; Evolutionary biology; Gene; Genetics; Ecology; Polymerase chain reaction","score_opus":0.01839102698263867,"score_gpt":0.2514513170836531,"score_spread":0.23306029010101442,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411887324","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":[0.98951054,0.000029034838,0.00075034006,0.0008299869,0.0006606868,0.00015550152,0.0051039797,0.000022873523,0.0029370347],"genre_scores_gemma":[0.9944136,0.000003510427,0.0011640273,0.0005384436,0.000019007646,4.0211856e-7,0.0036889946,0.0000043106206,0.00016769907],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9988918,0.00014554526,0.00015715176,0.00046344948,0.00013615485,0.00020592198],"domain_scores_gemma":[0.997751,0.0001351856,0.00010910363,0.0019487921,0.000009588986,0.000046350728],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00035752825,0.00010839436,0.00016173054,0.000014069394,0.0005209163,0.000057800717,0.002524073,0.00006365444,0.0028246145],"category_scores_gemma":[0.000053254127,0.0000751907,0.000021321754,0.00044348335,0.001603438,0.00028969673,0.0025786625,0.00016277807,0.0001807499],"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":[0.00045917978,0.00042273616,0.49993452,0.000012001315,0.0004337199,0.000008702721,0.0029083893,0.00010309872,0.31182516,0.0028765847,0.17826438,0.0027515253],"study_design_scores_gemma":[0.000912216,0.00006276836,0.8765335,0.00003738594,0.0001446569,8.9256537e-7,0.0014599339,0.00042081636,0.005302848,0.0123752,0.102474175,0.0002756235],"about_ca_topic_score_codex":0.004327205,"about_ca_topic_score_gemma":0.018644076,"teacher_disagreement_score":0.37659895,"about_ca_system_score_codex":0.00006704585,"about_ca_system_score_gemma":0.00010768603,"threshold_uncertainty_score":0.9992631},"labels":[],"label_agreement":null},{"id":"W4411924796","doi":"10.1038/s41597-025-04674-w","title":"An ecological trait matrix of Neotropical freshwater fishes","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Fish biology, ecology, and behavior","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Ontario Museum; University of Toronto","funders":"","keywords":"Ecology; Fauna; Habitat; Biodiversity; Biology; Trophic level; Geography","score_opus":0.03420529127750205,"score_gpt":0.30513441445103523,"score_spread":0.2709291231735332,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411924796","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":[0.9934608,0.000013137183,0.00008543493,0.0007526268,0.0011661598,0.00017391016,0.0020048753,0.00003966806,0.0023034166],"genre_scores_gemma":[0.98821926,0.0000019809643,0.0038898985,0.00020697921,0.000027424643,0.000008990211,0.0012503376,0.0000042260995,0.006390907],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99840343,0.00009971134,0.00026158462,0.00076469884,0.00015947764,0.00031110886],"domain_scores_gemma":[0.9984946,0.000047992868,0.000051436906,0.0013171984,0.000009541339,0.00007922883],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006567561,0.00010136442,0.00017097713,0.000052071293,0.00018824902,0.00007251085,0.0018382316,0.00013490193,0.010630411],"category_scores_gemma":[0.00010017755,0.00007557163,0.0000358316,0.00029421673,0.0015167766,0.00028781765,0.0010698015,0.000118321535,0.00033771075],"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":[0.000023029157,0.0010107098,0.32064041,0.0000109305765,0.000009915527,0.000012701239,0.00004642416,0.000020384326,0.116237134,0.00025064396,0.5553166,0.006421078],"study_design_scores_gemma":[0.00016734637,0.00008535987,0.82307434,0.00000304965,0.00002203606,0.00000244139,0.00004915071,0.0007029016,0.0013899638,0.0006174365,0.17379837,0.000087614986],"about_ca_topic_score_codex":0.00008995809,"about_ca_topic_score_gemma":0.004440642,"teacher_disagreement_score":0.5024339,"about_ca_system_score_codex":0.000037186506,"about_ca_system_score_gemma":0.000025636065,"threshold_uncertainty_score":0.990274},"labels":[],"label_agreement":null},{"id":"W4411976768","doi":"10.1038/s41597-025-05281-5","title":"A Public Dataset of Annotated Orcinus orca Acoustic Signals for Detection and Ecotype Classification","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Animal Vocal Communication and Behavior","field":"Biochemistry, Genetics and Molecular Biology","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":"Fisheries and Oceans Canada; Dalhousie University; Ocean Networks Canada Society; University of Victoria; Simon Fraser University","funders":"","keywords":"Ecotype; Geography; Biology; Ecology","score_opus":0.15728338917184548,"score_gpt":0.3649071657068553,"score_spread":0.2076237765350098,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411976768","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":[0.6078903,0.0019351173,0.31625947,0.0017668732,0.0011641646,0.0019524434,0.06816539,0.00006134205,0.0008048834],"genre_scores_gemma":[0.9541578,0.000021292053,0.00084789365,0.0000503634,0.000010445673,0.00001608416,0.044326395,0.0000040068176,0.0005656743],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99925685,0.000039751678,0.0001734478,0.00036379215,0.0000639613,0.00010219622],"domain_scores_gemma":[0.99855113,0.00001975181,0.00008027813,0.0011507615,0.00016494463,0.000033112003],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056657597,0.000058008234,0.00006853642,0.0000684799,0.00014814998,0.00008095472,0.000529781,0.000058309237,0.000013205541],"category_scores_gemma":[0.00034067733,0.000053811145,0.000013123533,0.00021443883,0.00017520423,0.00001547702,0.00040558333,0.00003535481,0.0000032278574],"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":[0.000040094474,0.000051897718,0.00011291376,0.000024088762,0.000008697961,4.106438e-8,0.0000037837624,6.5252857e-7,0.95128524,0.00008005037,0.032015506,0.01637704],"study_design_scores_gemma":[0.0005659182,0.00017301877,0.005893622,0.000018689423,0.00009395633,0.0000023791245,0.00015404707,0.015222419,0.28130126,0.00014689601,0.6962679,0.00015986753],"about_ca_topic_score_codex":0.000006434808,"about_ca_topic_score_gemma":0.00015524555,"teacher_disagreement_score":0.669984,"about_ca_system_score_codex":0.000005386512,"about_ca_system_score_gemma":0.0000880927,"threshold_uncertainty_score":0.21943548},"labels":[],"label_agreement":null},{"id":"W4412152332","doi":"10.1038/s41597-025-05460-4","title":"100 m soil landscape grids of Canada","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Soil Geostatistics and Mapping","field":"Environmental Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Health Canada; Parks Canada; Agriculture and Agri-Food Canada","funders":"Government of Canada","keywords":"Environmental science; Geography; Soil science; Earth science; Geology","score_opus":0.015791123441894428,"score_gpt":0.23615779145484425,"score_spread":0.22036666801294982,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412152332","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31948256,0.00027510067,0.004246908,0.0017109604,0.009556326,0.0003465275,0.009931183,0.00005469481,0.65439576],"genre_scores_gemma":[0.95449984,0.0000037575571,0.0011488894,0.00018354284,0.000016485581,0.0000022274776,0.0010437991,0.000004186239,0.043097243],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99909925,0.000011453094,0.00012615857,0.0003299439,0.00026417634,0.0001689966],"domain_scores_gemma":[0.9989218,0.000034691613,0.000035870515,0.0009550563,0.000008573227,0.000043967957],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004286071,0.000048539205,0.00006778087,0.000026648031,0.0001480164,0.000048008817,0.00080221967,0.000013011379,0.0010681681],"category_scores_gemma":[0.00013419236,0.00004401734,0.000007319591,0.00040334355,0.00015734498,0.000089070985,0.0009903196,0.00003685714,0.000041210285],"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":[0.0000013045423,0.000012019828,0.0055534616,0.000008959374,0.0000040792374,0.0000022387096,0.000022612709,0.00017049783,0.00065306056,0.00040653424,0.9862687,0.0068965354],"study_design_scores_gemma":[0.000181537,0.0000045186493,0.03762425,0.000022430018,0.000012702537,8.2588275e-7,0.00014820663,0.017688096,0.0010596609,0.0014667012,0.94168615,0.00010489977],"about_ca_topic_score_codex":0.2077477,"about_ca_topic_score_gemma":0.6079672,"teacher_disagreement_score":0.63501734,"about_ca_system_score_codex":0.000045795256,"about_ca_system_score_gemma":0.0002572705,"threshold_uncertainty_score":0.99984497},"labels":[],"label_agreement":null},{"id":"W4412154136","doi":"10.1038/s41597-025-05520-9","title":"A formulation dataset of poly(lactide-co-glycolide) nanoparticles for small molecule delivery","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Nanoparticle-Based Drug Delivery","field":"Materials Science","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":"Structural Genomics Consortium; University of Toronto","funders":"Canada First Research Excellence Fund; Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Lactide; Nanoparticle; Molecule; PLGA; Chemistry; Chemical engineering; Nanotechnology; Materials science; Combinatorial chemistry; Organic chemistry; Polymer; Engineering; Copolymer","score_opus":0.04680186697591612,"score_gpt":0.30648978730054166,"score_spread":0.2596879203246255,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412154136","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":[0.9395991,0.00037458524,0.0044245417,0.000205556,0.0010679441,0.00062776747,0.05353552,0.00007340818,0.000091564645],"genre_scores_gemma":[0.97425425,0.0000028111588,0.008733275,0.0001802686,0.000034944696,0.00004127127,0.016170125,0.000016046446,0.0005670047],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9975363,0.00009123494,0.00061473803,0.0009147139,0.00036681828,0.0004762163],"domain_scores_gemma":[0.9965825,0.00029483304,0.0002280291,0.0025863436,0.00020734897,0.000100946716],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022586435,0.0001637939,0.00024226545,0.00024812194,0.0003379575,0.000345378,0.0016234872,0.00005815753,0.00015506477],"category_scores_gemma":[0.00056583266,0.00015725486,0.00004982451,0.0006197919,0.00027786288,0.0009994128,0.00076748256,0.00005438365,0.00019738634],"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":[0.000148101,0.00015353884,0.00014831492,0.00008602815,0.000010960398,0.0000020631473,0.000045978362,0.000037604626,0.8796287,0.000636743,0.11681057,0.0022913574],"study_design_scores_gemma":[0.0006968077,0.00003946652,0.0001882907,0.000053807424,0.00007112849,0.0000013675196,0.00008028896,0.007256998,0.96050453,0.0005646411,0.030386422,0.00015625943],"about_ca_topic_score_codex":0.00016412693,"about_ca_topic_score_gemma":0.00021502114,"teacher_disagreement_score":0.08642415,"about_ca_system_score_codex":0.000057244903,"about_ca_system_score_gemma":0.00036387786,"threshold_uncertainty_score":0.6412667},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W4412156013","doi":"10.1038/s41597-025-05453-3","title":"Wave 2 of the Multilingual Eye-Movement Corpus (MECO): New text reading data across languages","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Reading and Literacy Development","field":"Psychology","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":"McMaster University","funders":"Social Sciences and Humanities Research Council of Canada; Agencia Nacional de Investigación y Desarrollo; Det Obelske Familiefond; Ministry of Education, India; Azrieli Foundation; Ministarstvo Prosvete, Nauke i Tehnološkog Razvoja; Norges Forskningsråd; Israel Science Foundation; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Aalborg Universitet; Bundesministerium für Bildung und Forschung; National Research University Higher School of Economics; Canada Research Chairs; Government of Canada","keywords":"Reading (process); Computer science; Eye movement; Movement (music); Natural language processing; Linguistics; Artificial intelligence; Art","score_opus":0.08484770351577375,"score_gpt":0.42346698270580246,"score_spread":0.3386192791900287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412156013","genre_codex":"empirical","genre_gemma":"other","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":[0.85472596,0.0033555368,0.0015609564,0.0034079577,0.040642366,0.0015282294,0.030106645,0.00024504616,0.06442728],"genre_scores_gemma":[0.47834682,0.00000944101,0.0031090432,0.0005905284,0.00019035742,0.000008395558,0.0072654034,0.000023392404,0.5104566],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974996,0.0001059236,0.00046837717,0.0011306042,0.0003617522,0.000433734],"domain_scores_gemma":[0.9926254,0.00014851287,0.00018861165,0.0068975817,0.00006484639,0.00007501933],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021600868,0.00015847775,0.00020652344,0.00009976693,0.00034172967,0.00029255537,0.0038523828,0.000067935,0.00046977785],"category_scores_gemma":[0.00049050665,0.0001128858,0.000036486155,0.0006675051,0.0002711555,0.00024300205,0.0040853396,0.000186485,0.00016544564],"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":[0.00002611644,0.00013258593,0.005432424,0.000034948076,0.000118575896,0.00001229242,0.007856251,0.0000021372998,0.0026462495,0.0011678088,0.7248392,0.25773138],"study_design_scores_gemma":[0.00069845887,0.000009757653,0.03807539,0.00024630607,0.00004389255,0.0000041808576,0.0044486877,0.0005290084,0.0048260554,0.0002720589,0.95065033,0.00019586843],"about_ca_topic_score_codex":0.00088544324,"about_ca_topic_score_gemma":0.00032591113,"teacher_disagreement_score":0.44602934,"about_ca_system_score_codex":0.000040137824,"about_ca_system_score_gemma":0.00025339224,"threshold_uncertainty_score":0.71587497},"labels":[],"label_agreement":null},{"id":"W4412363010","doi":"10.1038/s41597-025-05540-5","title":"A Cross-Species Brain Magnetic Resonance Imaging and Histology Database of Vertebrates","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"MRI in cancer diagnosis","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":"Université du Québec à Trois-Rivières","funders":"Japan Society for the Promotion of Science; Ministry of Education, Culture, Sports, Science and Technology; Mochida Memorial Foundation for Medical and Pharmaceutical Research; Japan Agency for Medical Research and Development; Takeda Science Foundation","keywords":"Magnetic resonance imaging; Histology; Functional magnetic resonance imaging; Nuclear magnetic resonance; Biology; Neuroscience; Medicine; Pathology; Physics; Radiology","score_opus":0.03809466685632366,"score_gpt":0.34249371533526757,"score_spread":0.3043990484789439,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412363010","genre_codex":"review","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":[0.40636587,0.414293,0.0015827062,0.09584995,0.011694709,0.002147872,0.036496103,0.0003032771,0.031266514],"genre_scores_gemma":[0.64808506,0.0041480795,0.023437701,0.007861955,0.00035477526,0.00012918368,0.015018286,0.00008962975,0.30087534],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985425,0.000034016044,0.00025720336,0.00073343696,0.00021207721,0.00022076054],"domain_scores_gemma":[0.99742925,0.00022413819,0.00005645653,0.002110863,0.00011584181,0.00006343846],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00076628936,0.000096759635,0.00021933347,0.00021463743,0.00012910173,0.00009806996,0.00056765147,0.000027538455,0.0007374924],"category_scores_gemma":[0.000738496,0.000090987,0.000017713168,0.00053519715,0.0014158719,0.00025872965,0.0009424034,0.00009908997,0.00001878651],"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":[0.000038538277,0.000059713653,0.14505723,0.00022350569,0.0000055922937,0.0000207788,0.0000912716,1.1027432e-7,0.013744102,0.0008524971,0.8155818,0.024324846],"study_design_scores_gemma":[0.0008040918,0.000022898543,0.12125164,0.00034925944,0.000047637484,0.000017055563,0.000085786436,0.0016979508,0.0045653107,0.00021324697,0.8708647,0.000080409816],"about_ca_topic_score_codex":0.00011952735,"about_ca_topic_score_gemma":0.00016400778,"teacher_disagreement_score":0.41014493,"about_ca_system_score_codex":0.000041015814,"about_ca_system_score_gemma":0.00024835294,"threshold_uncertainty_score":0.80750245},"labels":[],"label_agreement":null},{"id":"W4412392585","doi":"10.1038/s41597-025-05350-9","title":"In vivo submillimeter diffusion MRI dataset of 9 macaque brains curated for tractography","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Advanced Neuroimaging 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":"Université de Sherbrooke","funders":"HORIZON EUROPE Framework Programme; Université de Bordeaux; Alliance de recherche numérique du Canada; Conseil Régional Aquitaine; European Commission","keywords":"Macaque; Tractography; Diffusion MRI; Neuroscience; Computer science; Biology; Nuclear magnetic resonance; Magnetic resonance imaging; Medicine; Physics; Radiology","score_opus":0.11451306423913672,"score_gpt":0.4241875787324237,"score_spread":0.309674514493287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412392585","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12930393,0.00029307778,0.37439775,0.018027492,0.0013250671,0.0057388265,0.46851596,0.0003274571,0.002070419],"genre_scores_gemma":[0.54517883,0.0002492461,0.18943024,0.00374334,0.00009423334,0.00033963638,0.25344628,0.000064224645,0.007453929],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989466,0.0000118669095,0.00025899473,0.0005169056,0.0001139572,0.0001516979],"domain_scores_gemma":[0.9980247,0.000072579,0.00006780041,0.0017403008,0.000056620585,0.00003799158],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002897019,0.0000764698,0.00014971643,0.00031777442,0.00007354404,0.000026906657,0.00049092947,0.000032430475,0.000049221057],"category_scores_gemma":[0.00011200889,0.00006603564,0.000030212967,0.00094385043,0.00018083966,0.00019409758,0.0002692876,0.00008853611,0.000002153737],"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":[0.000037768255,0.00024278669,0.0012148903,0.00008223394,0.0000067616775,0.0000021116482,0.000014624788,5.272583e-7,0.20786153,0.001094669,0.7876167,0.0018253857],"study_design_scores_gemma":[0.0005706169,0.000023987535,0.0015034316,0.00009797268,0.00003690633,0.0000026883229,0.000021790653,0.0029135349,0.06616281,0.0023674439,0.9262298,0.00006903692],"about_ca_topic_score_codex":0.000023614746,"about_ca_topic_score_gemma":0.00002832444,"teacher_disagreement_score":0.41587493,"about_ca_system_score_codex":0.000010026727,"about_ca_system_score_gemma":0.000052872107,"threshold_uncertainty_score":0.26928553},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W4412430220","doi":"10.1038/s41597-025-05510-x","title":"Publication of data sharing statements in clinical trials by cardiovascular journals: a quantitative and qualitative analysis","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; St. Joseph’s Healthcare Hamilton; Impact","funders":"Natural Science Foundation of Guangdong Province; National Natural Science Foundation of China","keywords":"Clinical trial; Qualitative analysis; Data sharing; Computer science; Information retrieval; Data science; Qualitative research; Medicine; Alternative medicine; Internal medicine; Sociology; Pathology; Social science","score_opus":0.9769527842570832,"score_gpt":0.7718171202364945,"score_spread":0.2051356640205887,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412430220","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":[0.09535729,0.038931124,0.82186985,0.0026704408,0.001254835,0.0025168536,0.035177547,0.000008147024,0.0022138979],"genre_scores_gemma":[0.84845084,0.0013036352,0.08974826,0.00030815395,0.000071557726,0.00008326407,0.0317865,0.000027127126,0.02822064],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.8417537,0.097707294,0.042413063,0.0070297355,0.010605748,0.0004904276],"domain_scores_gemma":[0.8140636,0.061215647,0.0310329,0.085505635,0.007641905,0.0005402963],"candidate_categories":["metaresearch","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.85106504,0.00018623593,0.005277797,0.0020689985,0.00016532291,0.003566845,0.01037954,0.0000679886,0.0013011183],"category_scores_gemma":[0.42478552,0.000102058635,0.0010988268,0.010951685,0.000328841,0.0028442952,0.003628083,0.00017738335,0.00011370296],"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":[0.000026773378,0.00026751382,0.05134483,0.00009709599,0.015036096,0.0000014212768,0.0032101886,0.00006198958,0.00011025809,0.0026053125,0.8090407,0.11819778],"study_design_scores_gemma":[0.0016300478,0.000038733386,0.046866972,0.00027401978,0.012909067,7.8197075e-7,0.034910116,0.39411128,0.000027852804,0.022933852,0.48584715,0.00045013175],"about_ca_topic_score_codex":0.00013904372,"about_ca_topic_score_gemma":0.00024812686,"teacher_disagreement_score":0.75309354,"about_ca_system_score_codex":0.000021981125,"about_ca_system_score_gemma":0.00018254503,"threshold_uncertainty_score":0.99961185},"labels":[],"label_agreement":null},{"id":"W4412479567","doi":"10.1038/s41597-025-05571-y","title":"Correction: An ecological trait matrix of Neotropical freshwater fishes","year":2025,"lang":"en","type":"erratum","venue":"Scientific Data","topic":"Fish biology, ecology, and behavior","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Ontario Museum; University of Toronto","funders":"","keywords":"Trait; Ecology; Geography; Biology; Computer science","score_opus":0.03664765482473346,"score_gpt":0.2940788143301705,"score_spread":0.25743115950543705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412479567","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.073048994,0.00040319745,0.00014225896,0.0029947758,0.6865661,0.0021546632,0.0752278,0.00048230158,0.15897988],"genre_scores_gemma":[0.00316416,0.000031996253,0.0014150944,0.00021253356,0.0006565257,0.000030939304,0.03949204,0.000020546951,0.95497614],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99640435,0.00022917692,0.00056202634,0.0018160574,0.00042882096,0.00055957935],"domain_scores_gemma":[0.99695766,0.00009013614,0.00022451839,0.0025352617,0.000029199862,0.00016325159],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00090169074,0.0003135575,0.0005259019,0.00012641093,0.00036142173,0.00016889947,0.0035741844,0.0008868429,0.03096376],"category_scores_gemma":[0.00031390152,0.00024843603,0.0001123586,0.00045843556,0.002391572,0.00036618565,0.0027436789,0.0008121383,0.00059592235],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012929601,0.0004913981,0.0047236304,0.000021902337,0.0000126406485,0.000017657776,0.000021120903,0.0000041920175,0.00051783706,0.000006063181,0.99159366,0.002576949],"study_design_scores_gemma":[0.0001236007,0.00016189419,0.19972025,0.00002280137,0.00008217429,0.000012512329,0.000041527168,0.0007453389,0.000044972665,0.00010206422,0.79871786,0.00022502046],"about_ca_topic_score_codex":0.00027792726,"about_ca_topic_score_gemma":0.022871219,"teacher_disagreement_score":0.7959963,"about_ca_system_score_codex":0.00013750416,"about_ca_system_score_gemma":0.00015795376,"threshold_uncertainty_score":0.9999968},"labels":[],"label_agreement":null},{"id":"W4412490415","doi":"10.1038/s41597-025-05582-9","title":"A Machine Learning-Reconstructed Dataset of River Discharge, Temperature, and Heat Flux into the Arctic Ocean","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Climate change and permafrost","field":"Earth and Planetary Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"European Centre for Medium-Range Weather Forecasts; National Natural Science Foundation of China; Grains Research and Development Corporation; ArcticNet","keywords":"Arctic; Environmental science; Discharge; Climatology; Climate change; Arctic vegetation; Marine ecosystem; Oceanography; Global warming; Ecosystem; Geology; Geography; Ecology","score_opus":0.028587561589018144,"score_gpt":0.2568026545127386,"score_spread":0.22821509292372044,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412490415","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":[0.6937888,0.003539012,0.0000040570458,0.00087165245,0.0012634598,0.00021228765,0.29978,0.00001916797,0.0005215459],"genre_scores_gemma":[0.5746065,0.00018419593,0.00011388409,0.00020280272,0.00003827834,2.858249e-7,0.42291108,0.0000023613936,0.0019406432],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988591,0.000088659894,0.00019618295,0.0004737032,0.00018636047,0.00019599858],"domain_scores_gemma":[0.99873227,0.00014722798,0.000044384426,0.00097332505,0.00003727987,0.000065532346],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00078413123,0.00010816254,0.00013848161,0.000107530264,0.0005177725,0.00027984433,0.0008330143,0.000036433445,0.00312489],"category_scores_gemma":[0.00013664474,0.00006611381,0.00001660728,0.0005094539,0.00075544004,0.00035505978,0.00027193458,0.00017944272,0.00007723805],"study_design_candidate":"observational","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":[0.00003129819,0.000018433262,0.78412455,0.00011460352,0.000033394645,0.000003742362,0.0008860822,0.00001866164,0.001117641,0.00004194095,0.20558316,0.008026488],"study_design_scores_gemma":[0.0005439671,0.0000483753,0.3060575,0.0001327107,0.00009156,0.00002664484,0.0008564754,0.031583503,0.00028949737,0.0008003911,0.65931076,0.0002585886],"about_ca_topic_score_codex":0.0065058656,"about_ca_topic_score_gemma":0.019927666,"teacher_disagreement_score":0.47806704,"about_ca_system_score_codex":0.0000018623819,"about_ca_system_score_gemma":0.000049638846,"threshold_uncertainty_score":0.9979561},"labels":[],"label_agreement":null},{"id":"W4412520569","doi":"10.1038/s41597-025-05597-2","title":"A multi-source melt pool compilation for vision-based analytics applications in additive manufacturing","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Additive Manufacturing Materials and Processes","field":"Engineering","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":"McGill University","funders":"Alliance de recherche numérique du Canada; Mitacs; McGill University","keywords":"Analytics; Computer science; Process (computing); Process analytical technology; Standardization; Process engineering; Data mining; Work in process","score_opus":0.032198137681128336,"score_gpt":0.3008100488377761,"score_spread":0.2686119111566478,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412520569","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":[0.0141016655,0.00007151529,0.9659549,0.000061524705,0.00056868594,0.00071490556,0.017980522,0.0002044586,0.00034180563],"genre_scores_gemma":[0.97323847,0.0000039092483,0.008170143,0.00003021657,0.000041163534,0.00010794505,0.017806934,0.000018231249,0.0005830163],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99904966,0.000014017882,0.00022069283,0.00041325847,0.000103625716,0.00019873252],"domain_scores_gemma":[0.99898446,0.00022395211,0.00003858167,0.00067066506,0.000048073,0.00003427053],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033726502,0.00012412443,0.00014124648,0.0002442925,0.00018981505,0.000249228,0.0005184858,0.0000452831,0.00006196222],"category_scores_gemma":[0.000074186486,0.00012103368,0.000023120045,0.00025932625,0.000074379335,0.00017103842,0.00013385135,0.00006636134,0.000018493232],"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":[0.000108462555,0.00051698583,0.00033627363,0.0032850988,0.00023220484,0.0000042299584,0.00067982305,0.43217367,0.025283735,0.0007762471,0.22361453,0.31298876],"study_design_scores_gemma":[0.00040072785,0.0000051994634,0.0039120577,0.0000984705,0.000025287876,1.0363725e-7,0.00008702294,0.4542841,0.24418947,0.00033866108,0.29648864,0.000170241],"about_ca_topic_score_codex":0.000010004193,"about_ca_topic_score_gemma":0.00009438878,"teacher_disagreement_score":0.9591368,"about_ca_system_score_codex":0.00004951745,"about_ca_system_score_gemma":0.000048870883,"threshold_uncertainty_score":0.49356103},"labels":[],"label_agreement":null},{"id":"W4412571399","doi":"10.1038/s41597-025-05575-8","title":"A high-resolution database of historical and future climate for Africa developed with deep neural networks","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Climate variability and models","field":"Environmental Science","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":"Government of British Columbia; University of British Columbia; University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Downscaling; Climate model; Orographic lift; Climate change; Computer science; Database; Precipitation; Climatology; Grid; Artificial neural network; Meteorology; Environmental science; Data mining; Remote sensing; Geography; Machine learning; Geology","score_opus":0.03540132981286964,"score_gpt":0.25168378708427913,"score_spread":0.2162824572714095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412571399","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":[0.3049515,0.0018094535,0.6592076,0.0070186774,0.007892565,0.0030933742,0.0123943975,0.00021492376,0.00341754],"genre_scores_gemma":[0.9021036,0.00010336255,0.09005696,0.00011516917,0.00013275219,0.00006552704,0.005807835,0.0000208428,0.0015939279],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986636,0.000034445187,0.00020117944,0.0006462529,0.00018186796,0.00027265452],"domain_scores_gemma":[0.9987785,0.0000735812,0.0000671208,0.0009994957,0.000017855342,0.000063450556],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009814912,0.00009496885,0.00013830428,0.000042317628,0.00029234798,0.000065271495,0.00052819884,0.000045361077,0.00008193717],"category_scores_gemma":[0.00005698577,0.00007447896,0.000013948521,0.00045257265,0.0002860657,0.00039945258,0.0010980366,0.00006938543,0.000002914026],"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":[0.0024408076,0.0019181499,0.022824373,0.001217036,0.00014339102,0.000020748108,0.0019812384,0.051759344,0.013777582,0.024885982,0.7170801,0.16195124],"study_design_scores_gemma":[0.00058918574,0.000043875578,0.0032656011,0.000023737699,0.000069591995,0.000002444178,0.00007470376,0.7916718,0.000042328615,0.0004407437,0.20361432,0.0001616757],"about_ca_topic_score_codex":0.00012328419,"about_ca_topic_score_gemma":0.00060364895,"teacher_disagreement_score":0.73991245,"about_ca_system_score_codex":0.00011618918,"about_ca_system_score_gemma":0.000018652549,"threshold_uncertainty_score":0.3037164},"labels":[],"label_agreement":null},{"id":"W4412630680","doi":"10.1038/s41597-025-05638-w","title":"Mesopelagic Mesozooplankton and Micronekton Database","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Marine Invertebrate Physiology and Ecology","field":"Earth and Planetary Sciences","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":"Broadcom (Canada); University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mesopelagic zone; Oceanography; Database; Environmental science; Geology; Pelagic zone; Computer science","score_opus":0.024746571007223696,"score_gpt":0.250270855309319,"score_spread":0.22552428430209528,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412630680","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":[0.8984868,0.0040813996,0.00026729886,0.0033933362,0.006632651,0.000460961,0.010979538,0.00014115001,0.07555685],"genre_scores_gemma":[0.9477233,0.000090689864,0.00093876047,0.0009262144,0.000060188846,8.790971e-7,0.03702986,0.0000021325186,0.013227942],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99875766,0.00007070086,0.00014612,0.0006793239,0.00008083479,0.00026533793],"domain_scores_gemma":[0.99865985,0.00009487428,0.000033928092,0.0011219025,0.000019117148,0.00007035843],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00078193576,0.000094648836,0.00012918927,0.0001247002,0.00039116727,0.00014159903,0.0008582063,0.000053985696,0.004372613],"category_scores_gemma":[0.000094281866,0.000077644625,0.000010481005,0.00031347506,0.00044045056,0.00040801545,0.00039837186,0.000120795194,0.0006989499],"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":[0.000039665527,0.00002634785,0.19950499,0.00005433281,0.000033528235,0.000017025119,0.000040024057,0.000013210189,0.00082946854,0.0009963779,0.74860704,0.049838003],"study_design_scores_gemma":[0.00039742878,0.00003308102,0.4150251,0.000018888963,0.00004559567,0.000019120524,0.00010076787,0.034751378,0.00047526046,0.0071326625,0.5417757,0.00022505353],"about_ca_topic_score_codex":0.0008161641,"about_ca_topic_score_gemma":0.0073072976,"teacher_disagreement_score":0.21552008,"about_ca_system_score_codex":0.0000015582397,"about_ca_system_score_gemma":0.00008899863,"threshold_uncertainty_score":0.9965375},"labels":[],"label_agreement":null},{"id":"W4412761082","doi":"10.1038/s41597-025-05619-z","title":"High-Resolution Ultrasound Data for AI-Based Segmentation in Mouse Brain Tumor","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","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":"Izaak Walton Killam Health Centre; Dalhousie University","funders":"Canadian Institutes of Health Research; Dalhousie University","keywords":"Segmentation; Ultrasound; Artificial intelligence; Computer science; Computational biology; Pattern recognition (psychology); Biology; Medicine; Radiology","score_opus":0.021195710511228493,"score_gpt":0.32581800951468665,"score_spread":0.30462229900345816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412761082","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":[0.22370704,0.0005072477,0.7545063,0.0018374248,0.0004899457,0.001501815,0.017094072,0.00009348138,0.00026269592],"genre_scores_gemma":[0.48408276,0.000015790605,0.044528455,0.0018387777,0.00010248106,0.00008053767,0.45939317,0.00002461855,0.009933417],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9984593,0.00005974907,0.00022573338,0.00094002316,0.00012769629,0.00018751062],"domain_scores_gemma":[0.9964264,0.000041885614,0.00006701957,0.003360062,0.00007770607,0.000026893877],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014292188,0.000096129435,0.000102379105,0.00016485914,0.00011467073,0.00020486125,0.0014395027,0.000050044164,0.00001663208],"category_scores_gemma":[0.00085965166,0.00010035473,0.000025478912,0.00033601472,0.00012991026,0.000034634628,0.000667423,0.000050615672,0.000005430174],"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":[0.000019662757,0.000053661046,0.00016326504,0.00001537589,0.000010403614,3.9624263e-7,0.0000018581989,0.000033314736,0.5985102,0.00001913887,0.40025553,0.0009171926],"study_design_scores_gemma":[0.00048758916,0.00002272682,0.00014057575,0.000014765957,0.00002710911,4.6784845e-7,0.000029369374,0.010589801,0.82231504,0.00015066496,0.16610083,0.000121089426],"about_ca_topic_score_codex":0.000121623736,"about_ca_topic_score_gemma":0.0014921223,"teacher_disagreement_score":0.7099778,"about_ca_system_score_codex":0.000025729105,"about_ca_system_score_gemma":0.0001736953,"threshold_uncertainty_score":0.4092347},"labels":[],"label_agreement":null},{"id":"W4412779950","doi":"10.1038/s41597-025-05653-x","title":"Sea lice infestation dataset for wild and farmed salmon populations on the Pacific coast of Canada (2001–2023)","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Parasite Biology and Host Interactions","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto; Health PEI; University of Prince Edward Island","funders":"","keywords":"Infestation; Fishery; Biology; Aquaculture; Lepeophtheirus; Juvenile; Fishing; Geography; Ecology; Fish <Actinopterygii>","score_opus":0.056472108171808345,"score_gpt":0.35384665693180073,"score_spread":0.29737454875999236,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412779950","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":[0.7354906,0.000034664852,0.0010418864,0.006608402,0.002697628,0.0008022475,0.24764454,0.000014795096,0.0056652403],"genre_scores_gemma":[0.93702257,0.000004300308,0.00038077362,0.00035766713,0.000011873839,0.000023054388,0.05479186,0.0000032305134,0.0074046985],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992768,0.000041677522,0.00012933729,0.00030318557,0.00011070329,0.0001382516],"domain_scores_gemma":[0.9989648,0.00021731007,0.000060980172,0.0007114069,0.000011668342,0.000033822773],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004959169,0.000055755503,0.00005691679,0.00003276808,0.00050956313,0.000043990443,0.00038838212,0.000022934475,0.0002250599],"category_scores_gemma":[0.00031414503,0.000041436575,0.0000071975796,0.00025272215,0.00024509575,0.00018200881,0.00023399421,0.00005850504,0.000017789933],"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":[0.000013247837,0.000030368836,0.034268633,0.0000039088136,0.000006859337,1.9909922e-7,0.000035096036,0.00006411158,0.0013193861,0.00047439258,0.96236324,0.0014205428],"study_design_scores_gemma":[0.000096653406,0.000013502975,0.23476405,0.000014396118,0.000019832856,0.0000011051874,0.0003467699,0.0034076183,0.0003417498,0.00035374553,0.76057947,0.00006111082],"about_ca_topic_score_codex":0.05686276,"about_ca_topic_score_gemma":0.6563703,"teacher_disagreement_score":0.5995075,"about_ca_system_score_codex":0.000046947327,"about_ca_system_score_gemma":0.00008256844,"threshold_uncertainty_score":0.94941765},"labels":[],"label_agreement":null},{"id":"W4412810094","doi":"10.1038/s41597-025-05669-3","title":"Genome-wide analysis of host-encoded microRNAs modulating SARS-CoV-2 infection","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"SARS-CoV-2 and COVID-19 Research","field":"Medicine","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":"Peter MacCallum Cancer Centre; Australian Government; Commonwealth Scientific and Industrial Research Organisation; Canada Excellence Research Chairs, Government of Canada; Australian Cancer Research Foundation; University of Melbourne","keywords":"microRNA; Genome; Biology; Host (biology); Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Computational biology; Coronavirus disease 2019 (COVID-19); Virology; Genetics; Gene; Medicine; Infectious disease (medical specialty)","score_opus":0.08601688917498375,"score_gpt":0.3898502404357454,"score_spread":0.30383335126076166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412810094","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":[0.9907099,0.00024505684,0.0038984467,0.0001904012,0.0005030346,0.0003433053,0.0005029457,0.00005953691,0.0035473837],"genre_scores_gemma":[0.9947347,0.000003163544,0.00066602556,0.0029140639,0.000040505776,0.000010277271,0.0010945548,0.0000127296535,0.0005239655],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9976436,0.00007569558,0.00046024894,0.00088359794,0.00057778426,0.00035909627],"domain_scores_gemma":[0.99675524,0.00013560266,0.00012994518,0.00261313,0.0003407915,0.000025287367],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018566508,0.00014296653,0.00041584775,0.0016579803,0.00022913047,0.00017636694,0.00072019163,0.000085222426,0.000022310876],"category_scores_gemma":[0.0011042829,0.00013044417,0.0001547141,0.0057014516,0.0003149011,0.00027599317,0.000830938,0.00020889218,0.00006914734],"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":[0.000043115393,0.00012650886,0.1499022,0.00011499522,0.0005523885,0.0000074515997,0.00012394445,0.000005143327,0.8435042,0.000025277648,0.0033774285,0.0022173563],"study_design_scores_gemma":[0.0006632186,0.00003633968,0.16680546,0.00009175881,0.0010309316,0.0000020244322,0.00007619638,0.02468342,0.6425644,0.00010800724,0.16378978,0.0001484794],"about_ca_topic_score_codex":0.0009479312,"about_ca_topic_score_gemma":0.0009114883,"teacher_disagreement_score":0.2009398,"about_ca_system_score_codex":0.000114703886,"about_ca_system_score_gemma":0.00042298101,"threshold_uncertainty_score":0.53193593},"labels":[],"label_agreement":null},{"id":"W4412843976","doi":"10.1038/s41597-025-05617-1","title":"Tsunami Runup Survey Data From The Taan Fjord Landslide Event","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Landslides and related hazards","field":"Environmental Science","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":"Selkirk College","funders":"Division of Civil, Mechanical and Manufacturing Innovation; National Park Service; National Science Foundation","keywords":"Fjord; Geology; Landslide; Event (particle physics); Oceanography; Geography; Seismology; Physics","score_opus":0.05290228076373086,"score_gpt":0.30273011749594375,"score_spread":0.2498278367322129,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412843976","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":[0.7192302,0.003158169,0.010050858,0.012091183,0.026671905,0.0019780477,0.15045743,0.00043126792,0.07593097],"genre_scores_gemma":[0.87136567,0.000128353,0.00072705426,0.0008399547,0.0001346296,0.0000068271224,0.08169763,0.000023103981,0.045076773],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972976,0.00021147811,0.00029265386,0.001271431,0.00055312435,0.00037373253],"domain_scores_gemma":[0.9924485,0.00029420495,0.00008238657,0.007068794,0.000012463063,0.00009362488],"candidate_categories":["open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.0040508956,0.00015415695,0.00015264291,0.000030500758,0.00066911645,0.0005348319,0.006995403,0.00008031552,0.0033218216],"category_scores_gemma":[0.0004679785,0.00008958152,0.000029015617,0.0008273408,0.0004853873,0.0005383941,0.00945554,0.00023861506,0.0022384732],"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":[0.000014717258,0.000054136926,0.115442865,0.0000019677734,0.000034375524,0.0000047053986,0.000069402755,0.00007292454,0.00019371463,0.000020477333,0.8754817,0.008609003],"study_design_scores_gemma":[0.00022364495,0.000004270162,0.2823023,0.000025811853,0.00003858037,9.3664687e-7,0.000060803883,0.008342546,0.0000422348,0.00046994,0.70836526,0.00012369265],"about_ca_topic_score_codex":0.0073899194,"about_ca_topic_score_gemma":0.020755703,"teacher_disagreement_score":0.16711646,"about_ca_system_score_codex":0.00005429974,"about_ca_system_score_gemma":0.000074793374,"threshold_uncertainty_score":0.99921995},"labels":[],"label_agreement":null},{"id":"W4412958423","doi":"10.1038/s41597-025-05131-4","title":"A global dataset of terrestrial biological nitrogen fixation","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Soil Carbon and Nitrogen Dynamics","field":"Agricultural and Biological Sciences","cited_by":14,"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; Dalhousie University","funders":"Leverhulme Trust","keywords":"Biome; Terrestrial ecosystem; Abundance (ecology); Terrestrial plant; Environmental science; Lichen; Litter; Nitrogen fixation; Ecosystem; Ecology; Relative species abundance; Nitrogen; Biology; Chemistry","score_opus":0.060609636333438084,"score_gpt":0.2954699647597412,"score_spread":0.2348603284263031,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412958423","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":[0.93893903,0.000092549286,0.000018535486,0.00024293442,0.00076933135,0.00012305568,0.05927178,0.00002967153,0.0005131301],"genre_scores_gemma":[0.8979178,0.0000059461904,0.00022190543,0.00009210646,0.00007398045,0.0000030272456,0.101616725,1.9090496e-7,0.00006828034],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99888045,0.000067375324,0.00022979079,0.00046628586,0.00018481727,0.0001713032],"domain_scores_gemma":[0.9993999,0.000074519834,0.000081354476,0.00036591984,0.000031940774,0.000046355504],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00060984096,0.00007827146,0.00011912613,0.000013943885,0.00013418762,0.00010943908,0.0011842134,0.00006774835,0.00013862578],"category_scores_gemma":[0.0002713992,0.000029630004,0.000036385685,0.00082075136,0.00021448877,0.00013255145,0.0007141435,0.000039306484,0.000023094106],"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":[0.000235941,0.0004253845,0.20294294,0.00001316083,0.00007271351,0.0000066102325,0.000013506232,0.000005112275,0.060731217,0.0030979228,0.5528099,0.17964561],"study_design_scores_gemma":[0.001092922,0.00025477397,0.2878515,0.00006665493,0.00011583959,0.000009078277,0.0004002428,0.020563375,0.004423384,0.029123968,0.6555262,0.0005720094],"about_ca_topic_score_codex":0.00039987496,"about_ca_topic_score_gemma":0.0015745183,"teacher_disagreement_score":0.1790736,"about_ca_system_score_codex":0.000016799575,"about_ca_system_score_gemma":0.00003007718,"threshold_uncertainty_score":0.22005829},"labels":[],"label_agreement":null},{"id":"W4413054501","doi":"10.1038/s41597-025-05750-x","title":"Correction: Global Impacts Dataset of Invasive Alien Species (GIDIAS)","year":2025,"lang":"en","type":"erratum","venue":"Scientific Data","topic":"Species Distribution and Climate Change","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Armed Forces","funders":"","keywords":"Alien; Ecology; Alien species; Invasive species; Geography; Data science; Biology; Computer science; Political science","score_opus":0.05863488910597562,"score_gpt":0.30234846505438717,"score_spread":0.24371357594841156,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413054501","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00015003633,0.0003248095,0.000020070902,0.00028497784,0.07665555,0.0002474607,0.56790304,0.000040421855,0.35437363],"genre_scores_gemma":[0.00026455056,0.0003908761,0.00002867641,0.00018061059,0.00020659687,0.0000065776026,0.6044522,0.000009401388,0.39446053],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.996377,0.0000780653,0.0005259415,0.0014106181,0.001085969,0.0005224432],"domain_scores_gemma":[0.99525815,0.00006917838,0.00041988466,0.0039993427,0.00005043472,0.00020302064],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00082363567,0.00033288632,0.00041446835,0.00008145393,0.00035317685,0.00040721893,0.0037449773,0.00027097363,0.124195985],"category_scores_gemma":[0.0009623383,0.00031098013,0.00008741565,0.0014778449,0.0013470262,0.0005971063,0.0058691315,0.00033752696,0.0036512301],"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":[0.000009397503,0.00009852338,0.00061658624,0.00007074959,0.000026594178,0.000008965627,0.000030917345,0.0000013372508,0.00009698685,0.00005793149,0.9984409,0.000541113],"study_design_scores_gemma":[0.00014475507,0.00002155717,0.009704911,0.00013839103,0.00007769113,0.000008889268,0.00069710583,0.00004956073,0.00025440092,0.00004031236,0.98858774,0.0002746898],"about_ca_topic_score_codex":0.000867829,"about_ca_topic_score_gemma":0.014891849,"teacher_disagreement_score":0.120544754,"about_ca_system_score_codex":0.00094447477,"about_ca_system_score_gemma":0.0003647401,"threshold_uncertainty_score":0.99993426},"labels":[],"label_agreement":null},{"id":"W4413054850","doi":"10.1038/s41597-025-05543-2","title":"MRS-BIDS, an extension to the Brain Imaging Data Structure for magnetic resonance spectroscopy","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Advanced MRI Techniques and Applications","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":"McGill University; Montreal Neurological Institute and Hospital; Western University","funders":"National Institute on Aging; U.S. Department of Health and Human Services; National Institutes of Health; Austrian Science Fund; National Institute of Biomedical Imaging and Bioengineering; Wellcome Trust; Wellcome","keywords":"Extension (predicate logic); Nuclear magnetic resonance; Magnetic resonance imaging; Spectroscopy; Nuclear magnetic resonance spectroscopy; Materials science; Physics; Computer science; Medicine; Astronomy; Radiology","score_opus":0.048309771907065105,"score_gpt":0.40685938455419296,"score_spread":0.35854961264712787,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413054850","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":[0.004408034,0.0040879194,0.8580927,0.09482022,0.0012353247,0.0037787165,0.032537498,0.0003188231,0.0007207191],"genre_scores_gemma":[0.02893439,0.000056903686,0.8985341,0.009867809,0.00045857148,0.000111700305,0.040910516,0.0000467114,0.02107929],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983199,0.000015239038,0.00017198017,0.0010669704,0.00018297177,0.00024289802],"domain_scores_gemma":[0.99252164,0.000057741185,0.00003528847,0.007213932,0.00009473391,0.000076642544],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006927212,0.00009990248,0.00012105969,0.00008175348,0.00041070246,0.00015774358,0.0018370099,0.000024354425,0.000052351705],"category_scores_gemma":[0.00037658185,0.00007005312,0.000014117877,0.00058436586,0.00015046772,0.00025855078,0.0012074512,0.00011790227,0.000011781849],"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":[0.00002491859,0.000028127615,0.000040943178,0.000012260671,8.841404e-7,0.0000011120089,0.000022087423,0.0000025799702,0.074653335,0.0020886231,0.80218834,0.120936796],"study_design_scores_gemma":[0.00020286525,0.00002937162,0.0012042025,0.0000747258,0.000031805917,0.000007192679,0.00008483509,0.018314982,0.0054976237,0.0060210363,0.96845585,0.00007553217],"about_ca_topic_score_codex":0.000016089136,"about_ca_topic_score_gemma":0.00013253714,"teacher_disagreement_score":0.1662675,"about_ca_system_score_codex":0.000024191886,"about_ca_system_score_gemma":0.00011754408,"threshold_uncertainty_score":0.34136522},"labels":[],"label_agreement":null},{"id":"W4413055262","doi":"10.1038/s41597-025-05699-x","title":"Baseline high-resolution maps of soil nutrients in Morocco to support sustainable agriculture","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Soil Geostatistics and Mapping","field":"Environmental Science","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 Laval","funders":"","keywords":"Agriculture; Baseline (sea); Sustainability; Environmental science; Precision agriculture; Bootstrapping (finance); Vegetation (pathology); Digital soil mapping; Fertilizer; Environmental resource management; Soil map; Agricultural engineering; Computer science; Soil science; Geography; Mathematics; Soil water; Ecology; Econometrics; Engineering","score_opus":0.012705279275881866,"score_gpt":0.24755638078252454,"score_spread":0.23485110150664268,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413055262","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":[0.8502973,0.00022911666,0.053849824,0.004789679,0.0064244447,0.0032185356,0.024243701,0.00017132303,0.056776088],"genre_scores_gemma":[0.9169227,0.000008272232,0.0049085086,0.00025423313,0.000025675983,0.00002150646,0.008790146,0.000007687649,0.06906127],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99841696,0.00003553963,0.0002615933,0.00059706444,0.00033984546,0.00034901203],"domain_scores_gemma":[0.99886936,0.000031498686,0.000058204514,0.00092934864,0.00003565204,0.000075929755],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001371817,0.0000902134,0.00012426649,0.00013275589,0.00014439304,0.00008519496,0.00085797335,0.00003919583,0.00040376114],"category_scores_gemma":[0.00039019785,0.00007964016,0.00001407659,0.0014492685,0.00013638262,0.00027498987,0.0017565794,0.000071440874,0.00019446165],"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":[0.000012874918,0.00014218838,0.005563345,0.00004072983,0.000003679295,0.000012169005,0.00012958643,0.0022597178,0.0028807707,0.0020917477,0.9825408,0.0043224148],"study_design_scores_gemma":[0.00067632075,0.0000438897,0.052356936,0.00007696693,0.000022622224,0.000001258735,0.0010660492,0.006242078,0.003107768,0.005186268,0.9309826,0.00023728181],"about_ca_topic_score_codex":0.0035303493,"about_ca_topic_score_gemma":0.0019498143,"teacher_disagreement_score":0.06662541,"about_ca_system_score_codex":0.00012319622,"about_ca_system_score_gemma":0.000053687312,"threshold_uncertainty_score":0.53368556},"labels":[],"label_agreement":null},{"id":"W4413112481","doi":"10.1038/s41597-025-05652-y","title":"Phased genome assemblies and pangenome graphs of human populations of Japan and Saudi Arabia","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Genomics and Rare Diseases","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":"Institute of Genetics; Japan Science and Technology Agency; National Bioscience Database Center; King Salman Center for Disability Research; Dalian Institute of Chemical Physics; King Abdullah University of Science and Technology; Japan Society for the Promotion of Science; Ministry of Education, Culture, Sports, Science and Technology; King Fahad Medical City; Japan Agency for Medical Research and Development","keywords":"Biology; Haplotype; Reference genome; Genome; Population; Graph; Human genome; Computational biology; Gene; Genetics; Computer science; Allele; Theoretical computer science; Medicine","score_opus":0.039620647400108455,"score_gpt":0.31301324952601484,"score_spread":0.2733926021259064,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413112481","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":[0.99278617,0.0035795153,0.00006266186,0.000034132623,0.00011611609,0.00009901377,0.002951473,0.000002536337,0.00036835414],"genre_scores_gemma":[0.9950731,0.0000730934,0.00025635018,0.000012511081,0.00000952909,0.00000191436,0.0039834375,0.000003921558,0.00058617705],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9993139,0.00001694734,0.000165094,0.00034757875,0.00006300982,0.000093454735],"domain_scores_gemma":[0.9991056,0.0000046879486,0.00007064833,0.00071733334,0.000062158855,0.000039625644],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020232201,0.00006585935,0.0001054681,0.00010928766,0.00013168018,0.000042693315,0.0002772025,0.000035359422,0.000007532715],"category_scores_gemma":[0.000041324947,0.00006214189,0.000022424383,0.0001447205,0.0003020445,0.000006219532,0.0003256365,0.000018258123,2.514404e-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":[0.0000071992877,0.00005159313,0.007963478,0.000056948735,0.00003118326,1.5158561e-7,0.000034305187,0.0000012044003,0.9889382,0.00094608293,0.001330477,0.00063913706],"study_design_scores_gemma":[0.0016816596,0.00027646834,0.7592636,0.000094816976,0.00033735408,0.000007590512,0.0009675815,0.000081660735,0.16517186,0.009069426,0.06253317,0.00051487325],"about_ca_topic_score_codex":0.00003131996,"about_ca_topic_score_gemma":0.0001057631,"teacher_disagreement_score":0.8237664,"about_ca_system_score_codex":0.0000016183701,"about_ca_system_score_gemma":0.00004504315,"threshold_uncertainty_score":0.25340727},"labels":[],"label_agreement":null},{"id":"W4413116177","doi":"10.1038/s41597-025-05792-1","title":"A dataset of high-resolution plantar pressures for gait analysis across varying footwear and walking speeds","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Diabetic Foot Ulcer Assessment and Management","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":"University of New Brunswick","funders":"New Brunswick Innovation Foundation; Natural Sciences and Engineering Research Council of Canada; Atlantic Canada Opportunities Agency; Government of Canada","keywords":"Gait; Gait analysis; Plantar pressure; Physical medicine and rehabilitation; Plantar flexion; Preferred walking speed; Computer science; Medicine; Ankle; Engineering; Anatomy","score_opus":0.04221187040446684,"score_gpt":0.3595110626952025,"score_spread":0.31729919229073567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413116177","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":[0.58926606,0.0025134915,0.10316849,0.0026789103,0.0037334776,0.0038996907,0.29158023,0.0001554784,0.003004179],"genre_scores_gemma":[0.8690285,0.00002510839,0.009216277,0.00008832254,0.000041275925,0.000017382217,0.11825714,0.00000794786,0.0033180146],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985462,0.00002191452,0.00028528742,0.00060465146,0.0002849808,0.00025699873],"domain_scores_gemma":[0.99832016,0.00008334132,0.00010010586,0.0013798496,0.00006308097,0.000053467695],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014449056,0.000100501165,0.00029043562,0.0003234327,0.00019481457,0.000174322,0.00043395636,0.000033442568,0.000045621793],"category_scores_gemma":[0.00011174092,0.00008844281,0.00004098872,0.00074866595,0.00018524908,0.00022917739,0.00095225003,0.0000520989,0.0000022625193],"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":[0.000477979,0.00041380097,0.012900798,0.001751312,0.0037981682,0.000009192619,0.00041030822,0.00011962539,0.0034502216,0.0022631069,0.930076,0.044329494],"study_design_scores_gemma":[0.003981943,0.00017397938,0.057723723,0.00046946117,0.00997632,0.0000020149487,0.00070595706,0.06932598,0.0057508843,0.001263646,0.8502813,0.0003447774],"about_ca_topic_score_codex":0.00019404566,"about_ca_topic_score_gemma":0.00018806622,"teacher_disagreement_score":0.27976248,"about_ca_system_score_codex":0.000016732625,"about_ca_system_score_gemma":0.000048281112,"threshold_uncertainty_score":0.3606593},"labels":[],"label_agreement":null},{"id":"W4413312032","doi":"10.1038/s41597-025-05791-2","title":"Hierarchical Event Descriptor library schema for EEG data annotation","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"EEG and Brain-Computer Interfaces","field":"Neuroscience","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":"Montreal Neurological Institute and Hospital","funders":"National Institutes of Health; University of Electronic Science and Technology of China; National Institute of Mental Health; U.S. Department of Health and Human Services","keywords":"Schema (genetic algorithms); Annotation; Computer science; Information retrieval; Electroencephalography; Natural language processing; Artificial intelligence; Psychology; Neuroscience","score_opus":0.11280935658473884,"score_gpt":0.35039420488544903,"score_spread":0.2375848483007102,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413312032","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":[0.43731272,0.0011608634,0.33234188,0.042302426,0.046759494,0.0042515583,0.12263183,0.0015685878,0.011670644],"genre_scores_gemma":[0.81311494,0.000023844475,0.06961208,0.004993822,0.0004885487,0.00006498372,0.03136962,0.000059811435,0.08027238],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973514,0.000099452984,0.0002989656,0.0016011478,0.00031306222,0.0003359632],"domain_scores_gemma":[0.99578476,0.0003876011,0.00007252916,0.003640476,0.000028583472,0.00008604128],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0007996449,0.00013190093,0.00013690189,0.00019596839,0.00043559345,0.001144462,0.0053007468,0.000048083035,0.00008464196],"category_scores_gemma":[0.0012152444,0.00011434568,0.000030695388,0.0006852568,0.00033623484,0.002321925,0.0042004357,0.00014248946,0.000088874964],"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":[0.000030560244,0.000115952076,0.000056494984,0.000057778543,0.000005890662,0.0000030084605,0.00006818482,0.000006582681,0.12339218,0.004491976,0.8482599,0.023511492],"study_design_scores_gemma":[0.00028957642,0.00002305053,0.00019855906,0.00008030846,0.000012697357,0.0000032037217,0.00003085183,0.0970431,0.14108346,0.0037479098,0.75735337,0.00013390633],"about_ca_topic_score_codex":0.0000023681825,"about_ca_topic_score_gemma":0.000004686578,"teacher_disagreement_score":0.3758022,"about_ca_system_score_codex":0.000011856692,"about_ca_system_score_gemma":0.00024060135,"threshold_uncertainty_score":0.9998925},"labels":[],"label_agreement":null},{"id":"W4413341034","doi":"10.1038/s41597-026-07298-w","title":"VO: The Vaccine Ontology","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","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":"Ontario Institute for Cancer Research","funders":"","keywords":"Ontology; Vaccine adjuvant; Compendium; Computer science; Adjuvant; Medicine; DNA vaccination; Immune system; Immunology; Immunization","score_opus":0.03379012968567952,"score_gpt":0.33427289494916207,"score_spread":0.30048276526348255,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413341034","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":[0.65698195,0.04238237,0.06455355,0.112557955,0.0367685,0.0014170146,0.0048106024,0.00039099978,0.08013708],"genre_scores_gemma":[0.9025893,0.00009845294,0.0033725232,0.0026463745,0.00032793308,0.000018741197,0.0055127945,0.000011373644,0.08542246],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990746,0.000048030015,0.00011797331,0.0004852573,0.00008656193,0.00018761886],"domain_scores_gemma":[0.9980083,0.000025742978,0.000028075918,0.0018721111,0.00003716872,0.000028573488],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069600873,0.00006724728,0.00007379513,0.00003260441,0.00022302047,0.00007308835,0.0014852394,0.00008374079,0.000042044023],"category_scores_gemma":[0.0005559796,0.000041239047,0.00002264578,0.0002059811,0.00033393735,0.000002010178,0.0011137193,0.000072396986,0.0000419968],"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":[0.000013389506,0.000023110275,0.00061399513,0.0000053364524,0.000025320713,0.0000011172541,0.000012022514,4.3995024e-7,0.02082567,0.00036831852,0.9097601,0.06835117],"study_design_scores_gemma":[0.00016322665,0.000021206177,0.0024946458,0.0000062003205,0.000012516721,0.0000040751474,0.000079297526,0.00011119784,0.0055253226,0.00040221,0.99112886,0.000051243474],"about_ca_topic_score_codex":0.000018236218,"about_ca_topic_score_gemma":0.00029893077,"teacher_disagreement_score":0.24560742,"about_ca_system_score_codex":0.0000033051506,"about_ca_system_score_gemma":0.00010639038,"threshold_uncertainty_score":0.2759969},"labels":[],"label_agreement":null},{"id":"W4413398865","doi":"10.1038/s41597-025-05798-9","title":"Whole genome sequencing and annotations of Trametes sanguinea ZHSJ","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Insect and Arachnid Ecology and Behavior","field":"Biochemistry, Genetics and Molecular Biology","cited_by":62,"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":"Natural Science Foundation of Shandong Province; National Natural Science Foundation of China","keywords":"Biology; Genome; Computational biology; DNA sequencing; Whole genome sequencing; Evolutionary biology; Genetics; Gene","score_opus":0.029939659394598944,"score_gpt":0.29708225111537623,"score_spread":0.26714259172077726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413398865","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":[0.9965509,0.00058946817,0.00032618718,0.00009921504,0.00029778024,0.00007307145,0.0015798665,0.0000049304467,0.00047856435],"genre_scores_gemma":[0.9893781,0.000008803219,0.0009824138,0.000066591296,0.00002339114,0.000003518639,0.004821365,0.0000025152276,0.004713313],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99945617,0.000016783923,0.00010647547,0.0002818654,0.00003750543,0.00010122489],"domain_scores_gemma":[0.9993768,0.000007426166,0.0000303534,0.0005232092,0.00004343572,0.000018800436],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027475404,0.000048082842,0.00006230924,0.00005255808,0.000153685,0.000031608266,0.00026773033,0.00005012263,0.000021285747],"category_scores_gemma":[0.00007511799,0.000044436474,0.0000150351225,0.00012709126,0.00022786538,0.0000073244687,0.00023539843,0.000034619126,0.0000040491036],"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":[0.000004337868,0.000021548167,0.0015181054,0.000012926049,0.000009947818,5.791755e-7,0.00003815188,0.0000025559261,0.99029046,0.000084474246,0.0066202753,0.0013966287],"study_design_scores_gemma":[0.0006329335,0.00013717971,0.03654608,0.00003313607,0.00012796742,0.000010223018,0.0007531262,0.0004254886,0.7681944,0.00060363574,0.19225582,0.000280046],"about_ca_topic_score_codex":0.0000060206826,"about_ca_topic_score_gemma":0.000065426066,"teacher_disagreement_score":0.22209612,"about_ca_system_score_codex":0.0000030333088,"about_ca_system_score_gemma":0.000084498184,"threshold_uncertainty_score":0.18120669},"labels":[],"label_agreement":null},{"id":"W4413450650","doi":"10.1038/s41597-025-05123-4","title":"High-resolution Canada domain disturbance forcings suitable for land surface modeling applications","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Cryospheric studies and observations","field":"Earth and Planetary Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Canadian Forest Service; Natural Resources Canada; Carleton University; Environment and Climate Change Canada","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Disturbance (geology); Carbon cycle; Environmental science; Climatology; Geography; Computer science; Environmental resource management; Physical geography; Ecology; Geology; Ecosystem","score_opus":0.028931366953676554,"score_gpt":0.23325200072650848,"score_spread":0.20432063377283194,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413450650","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":[0.268071,0.005939062,0.66890585,0.004595159,0.004754028,0.0016870932,0.04427999,0.00010342547,0.0016644216],"genre_scores_gemma":[0.92406756,0.0000413899,0.035610557,0.0003255129,0.00013376112,0.000022584569,0.026388798,0.0000048961306,0.013404935],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988926,0.000010935617,0.00017464883,0.00046956158,0.00017678083,0.00027543938],"domain_scores_gemma":[0.9989645,0.00012747492,0.00004259759,0.00073349563,0.00008423022,0.00004768452],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005036638,0.000078660756,0.000105843086,0.000014869848,0.0011338883,0.00018238169,0.0006276206,0.000022939945,0.00008093199],"category_scores_gemma":[0.00006288003,0.0000693887,0.00001592246,0.0005191141,0.00006293465,0.00023064391,0.0000866421,0.000049159025,0.000008507517],"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":[0.000020040092,0.00002093774,0.083696604,0.00007791732,0.000038882437,4.746799e-7,0.00006454851,0.29097813,0.000025627012,0.0030135855,0.6150928,0.0069704503],"study_design_scores_gemma":[0.00014833295,0.000003509936,0.015514904,0.000011414381,0.000015614627,1.5569732e-7,0.00021513463,0.47479883,0.000004353539,0.0024450026,0.50675327,0.0000895141],"about_ca_topic_score_codex":0.549762,"about_ca_topic_score_gemma":0.9300997,"teacher_disagreement_score":0.65599656,"about_ca_system_score_codex":0.000018809831,"about_ca_system_score_gemma":0.0003284834,"threshold_uncertainty_score":0.8721066},"labels":[],"label_agreement":null},{"id":"W4413491796","doi":"10.1038/s41597-025-05509-4","title":"Plant traits and associated ecological data from global change experiments and climate gradients in Norway","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Remote Sensing in Agriculture","field":"Environmental Science","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":"University of British Columbia","funders":"Senter for Internasjonalisering av Utdanning; Norges Forskningsråd; Universitetet i Bergen","keywords":"Ecology; Plant functional type; Environmental science; Ecosystem; Climate change; Plant community; Plant ecology; Global change; Global warming; Environmental gradient; Physical geography; Geography; Biology; Ecological succession","score_opus":0.06794931172273355,"score_gpt":0.2938196451764213,"score_spread":0.22587033345368773,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413491796","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":[0.9796002,0.00017461111,0.0000040781842,0.00026145868,0.0006270471,0.00028292745,0.017375564,0.000025297168,0.0016488077],"genre_scores_gemma":[0.9884535,0.000059766422,0.0010060548,0.00021275974,0.000019546595,0.0000017894245,0.0099700745,0.000004028485,0.00027246875],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9977874,0.00009295379,0.00020038342,0.0012586572,0.00029454983,0.0003660626],"domain_scores_gemma":[0.99893016,0.00004790885,0.00006448891,0.00085554464,0.000004324505,0.00009756448],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007080273,0.00014273194,0.0001696676,0.000028267557,0.00022479691,0.000279806,0.0012295293,0.00009831236,0.00013996019],"category_scores_gemma":[0.00017368478,0.00010860775,0.0000075900193,0.00047741708,0.0003821033,0.0005970273,0.0052295206,0.00010666594,0.000100624646],"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":[0.00004511409,0.00076253875,0.64180386,0.000016220834,0.000048618356,0.00009789692,0.0008741142,0.0000036426263,0.013186578,0.00005718528,0.31093585,0.03216837],"study_design_scores_gemma":[0.0004020741,0.000009914708,0.9817719,0.000049304872,0.000014454365,0.0000027691442,0.000102868864,0.006927567,0.000041138646,0.00015449722,0.0103977015,0.00012585252],"about_ca_topic_score_codex":0.0006974954,"about_ca_topic_score_gemma":0.009822872,"teacher_disagreement_score":0.339968,"about_ca_system_score_codex":0.0001270726,"about_ca_system_score_gemma":0.000008366141,"threshold_uncertainty_score":0.6518223},"labels":[],"label_agreement":null},{"id":"W4413494925","doi":"10.1038/s41597-025-05866-0","title":"Full Field Digital Mammography Dataset from a Population Screening Program","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"AI in cancer detection","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"St. John’s Health Sciences Centre; Newfoundland and Labrador Centre for Applied Health Research; Memorial University of Newfoundland","funders":"Memorial University of Newfoundland","keywords":"Mammography; Field (mathematics); Population; Digital mammography; Mammography screening; Data science; Computer science; Medical physics; Medicine; Environmental health; Mathematics; Breast cancer; Internal medicine; Cancer","score_opus":0.03314364068906861,"score_gpt":0.3164268363211404,"score_spread":0.28328319563207177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413494925","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":[0.0062026507,0.00016584483,0.96846485,0.0012108614,0.004623555,0.00043410223,0.017676786,0.0005257687,0.00069557526],"genre_scores_gemma":[0.57830596,0.0000056172844,0.2589408,0.00059884647,0.00026536183,0.000069559,0.16098075,0.000017555152,0.0008155547],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.998037,0.000029190544,0.0002220891,0.0010907005,0.00037584396,0.00024517457],"domain_scores_gemma":[0.9961559,0.00008858781,0.00008209547,0.003568927,0.000043868018,0.00006061106],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00042776891,0.00010969905,0.00009979219,0.00026297267,0.0003255818,0.0027725063,0.0032371625,0.000052606054,0.000025642403],"category_scores_gemma":[0.00012742852,0.000109592605,0.000031334912,0.0015628515,0.000074797405,0.0029957716,0.0023677498,0.00012872808,0.000051236944],"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":[0.000010505273,0.00003953295,0.0015002136,0.000006475723,0.000016506474,0.0000023016244,0.000019913576,0.000013752397,0.00006165675,0.00033513003,0.29901826,0.69897574],"study_design_scores_gemma":[0.00027113696,0.00007354476,0.0064625,0.00008243545,0.000019007955,0.0000026436212,0.00002820922,0.17356075,0.00035670918,0.005900313,0.812998,0.00024474048],"about_ca_topic_score_codex":0.00034683052,"about_ca_topic_score_gemma":0.00026642045,"teacher_disagreement_score":0.7095241,"about_ca_system_score_codex":0.0000225506,"about_ca_system_score_gemma":0.000050376813,"threshold_uncertainty_score":0.9982627},"labels":[],"label_agreement":null},{"id":"W4413910953","doi":"10.1038/s41597-025-05445-3","title":"The Indo-European Cognate Relationships dataset","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Language and cultural evolution","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Lexeme; Cognate; Metadata; Computer science; Benchmark (surveying); Lexicon; Language family; Natural language processing; Interoperability; Linguistics; Artificial intelligence; Information retrieval; World Wide Web; Geography; Cartography","score_opus":0.10680086555281473,"score_gpt":0.37512981886630353,"score_spread":0.2683289533134888,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413910953","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014096931,0.0038468663,0.0007692762,0.033592198,0.012100729,0.0010103087,0.032211613,0.0003741948,0.90199786],"genre_scores_gemma":[0.8048254,0.00009860945,0.00019367847,0.00040996165,0.00028296545,0.0000057973466,0.05046454,0.0000062759323,0.14371273],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986374,0.0004869459,0.00011829223,0.00029950432,0.00026391144,0.00019394586],"domain_scores_gemma":[0.9986113,0.00013782766,0.00004137331,0.0011092053,0.000056369652,0.000043970987],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.005107426,0.000041860967,0.000034827714,0.000029916824,0.004490871,0.00083316053,0.001619631,0.000021980235,0.0001171336],"category_scores_gemma":[0.0016422061,0.000026408316,0.000011734764,0.00061872747,0.0005852276,0.00053414056,0.0005291944,0.0001239484,0.0006720495],"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":[0.0000015528334,0.000006927021,0.00013907746,0.0000011239579,0.000004841295,0.000001346082,0.0010117057,3.954102e-7,0.00004618296,0.02264076,0.95948625,0.01665987],"study_design_scores_gemma":[0.00005348981,8.299506e-7,0.0023013742,0.000009388202,0.00001050859,1.4302215e-7,0.0043683015,0.000048466438,0.000008110883,0.0014975508,0.9916624,0.00003947418],"about_ca_topic_score_codex":0.00034861444,"about_ca_topic_score_gemma":0.0075139445,"teacher_disagreement_score":0.7907285,"about_ca_system_score_codex":0.000027443619,"about_ca_system_score_gemma":0.00013659806,"threshold_uncertainty_score":0.99680513},"labels":[],"label_agreement":null},{"id":"W4414357588","doi":"10.1038/s41597-025-05962-1","title":"A dataset from a coordinated multi-site laboratory study investigating the Hue-Heat-Hypothesis","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Building Energy and Comfort Optimization","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"HORIZON EUROPE Framework Programme; Magyar Tudományos Akadémia Számítástechnikai és Automatizálási Kutatóintézet; Magyar Tudományos Akadémia; European Commission; Ministério da Ciência, Tecnologia e Inovação; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Villum Fonden; National Science Foundation","keywords":"Metadata; Documentation; Perception; Protocol (science); Test (biology); Resource (disambiguation)","score_opus":0.046110205236155985,"score_gpt":0.26668603584685574,"score_spread":0.22057583061069974,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414357588","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":[0.81064147,0.0010035326,0.04391569,0.0005104016,0.00546445,0.0009986064,0.13607779,0.0010240634,0.00036401534],"genre_scores_gemma":[0.94762826,0.0000075185067,0.009442104,0.0002854306,0.000055078897,0.000042869207,0.04196075,0.00003145098,0.0005465636],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989811,0.000071186216,0.000192644,0.00043886522,0.0001425716,0.0001736006],"domain_scores_gemma":[0.9977703,0.00010682609,0.000022223083,0.002022035,0.000038339862,0.000040266907],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00068301393,0.00011811074,0.000109730616,0.0000988562,0.00037860277,0.00037258342,0.0011479998,0.000042104348,0.000044574135],"category_scores_gemma":[0.00020968476,0.00009446259,0.000010481227,0.0010476423,0.000114870345,0.00034659833,0.0004971746,0.00014332766,0.000023232817],"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":[0.0000042458623,0.00014736566,0.0049047796,0.000024462603,0.00016962746,0.0000050766603,0.0005694878,0.18538362,0.0058961194,0.00006358201,0.80027103,0.0025605995],"study_design_scores_gemma":[0.0004245321,0.000005134728,0.0031638003,0.000059395483,0.00008225008,2.035251e-7,0.00043137427,0.93604016,0.0014488338,0.00008749969,0.05807304,0.00018376762],"about_ca_topic_score_codex":0.00023818352,"about_ca_topic_score_gemma":0.00096193224,"teacher_disagreement_score":0.75065655,"about_ca_system_score_codex":0.0000244337,"about_ca_system_score_gemma":0.00005372895,"threshold_uncertainty_score":0.3852073},"labels":[],"label_agreement":null},{"id":"W4414418843","doi":"10.1038/s41597-025-05840-w","title":"A regional ocean database for the Coastal China Sea","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Oceanographic and Atmospheric Processes","field":"Earth and Planetary 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":"Dalhousie University; National Key Research and Development Program of China; National Aeronautics and Space Administration","keywords":"NetCDF; Biogeochemical cycle; Longitude; China; Relational database; Range (aeronautics); Seawater; Particulates","score_opus":0.03477501683651092,"score_gpt":0.260077505257286,"score_spread":0.2253024884207751,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414418843","genre_codex":"dataset","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":[0.24824022,0.041615546,0.17538442,0.052685775,0.03331444,0.0049625034,0.39838558,0.0009435066,0.044468023],"genre_scores_gemma":[0.9161001,0.00018358229,0.0067887907,0.0013310878,0.0002838499,0.0000021792405,0.057234824,0.000005823891,0.018069765],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99875736,0.000021081947,0.00014241664,0.0005447346,0.00026219795,0.0002722098],"domain_scores_gemma":[0.9983929,0.0002401511,0.000047553876,0.0012093628,0.000046520152,0.000063513],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010183599,0.00009745775,0.0000870275,0.000026922427,0.00093166856,0.00039086243,0.0018054266,0.000023539515,0.00045394438],"category_scores_gemma":[0.00017817365,0.00005937396,0.000035229074,0.0008134901,0.000502349,0.00049643364,0.00017099098,0.00008592473,0.000040655836],"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":[0.000031630345,0.000021074306,0.06956647,0.00004667132,0.00002852701,0.0000017008842,0.00004026645,0.00007706081,0.0000030407498,0.00045744842,0.9000771,0.029648982],"study_design_scores_gemma":[0.00022480106,0.000015021079,0.077171475,0.00003141582,0.000039668615,0.0000038599624,0.0002789913,0.072692476,0.000016980945,0.0019988182,0.8474157,0.00011080202],"about_ca_topic_score_codex":0.00047953735,"about_ca_topic_score_gemma":0.0028134205,"teacher_disagreement_score":0.6678599,"about_ca_system_score_codex":6.595715e-7,"about_ca_system_score_gemma":0.00024068526,"threshold_uncertainty_score":0.7165736},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W4414465667","doi":"10.1038/s41597-025-05428-4","title":"Quantum mechanical dataset of 836k neutral closed-shell molecules with up to 5 heavy atoms from C, N, O, F, Si, P, S, Cl, Br","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Machine Learning in Materials Science","field":"Materials Science","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":"Structural Genomics Consortium; Vector Institute; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Basic Energy Sciences; Office of Science; Canada First Research Excellence Fund; University of Toronto; Argonne National Laboratory; U.S. Department of Energy; European Commission; Compute Canada; Government of Canada; Canadian Institute for Advanced Research; Laboratory Directed Research and Development","keywords":"Conformational isomerism; Quantum Monte Carlo; Molecule; Multipole expansion; Quantum; Quantum chemistry; Quantum chemical; Diffusion Monte Carlo","score_opus":0.027421716630805924,"score_gpt":0.30673603416352735,"score_spread":0.2793143175327214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414465667","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":[0.8827944,0.000092579605,0.027081247,0.0009063623,0.0059466967,0.00053518097,0.08230233,0.00015224371,0.00018898209],"genre_scores_gemma":[0.9064083,0.000006266177,0.06248545,0.0009950454,0.00015812725,0.000030695344,0.028301587,0.000048730097,0.0015658096],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9952037,0.00036735449,0.00073447905,0.0020949966,0.0009017385,0.0006977344],"domain_scores_gemma":[0.99416137,0.00021551645,0.0002739197,0.0049426467,0.00015142081,0.00025510142],"candidate_categories":["open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0037105011,0.00030712862,0.00048750459,0.00024412521,0.00040690048,0.000997091,0.0057750707,0.00009366732,0.0012032967],"category_scores_gemma":[0.00067597785,0.00024401322,0.000037362,0.0011245572,0.00080572336,0.000782752,0.0034159452,0.00019460547,0.00088895496],"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":[0.00018636021,0.00009291785,0.00013131436,0.00005270824,0.0000101553715,0.000011586436,0.000108188695,0.00027474167,0.80026335,0.0064798524,0.19210805,0.00028078404],"study_design_scores_gemma":[0.00084757846,0.00021360889,0.0013491827,0.00034966666,0.00009698975,0.000009719631,0.00023416535,0.024469307,0.80392134,0.0055261147,0.16232534,0.0006569778],"about_ca_topic_score_codex":0.0013971806,"about_ca_topic_score_gemma":0.0006775685,"teacher_disagreement_score":0.054000746,"about_ca_system_score_codex":0.00004033095,"about_ca_system_score_gemma":0.00038858582,"threshold_uncertainty_score":0.99988896},"labels":[],"label_agreement":null},{"id":"W4414533842","doi":"10.1038/s41597-025-05759-2","title":"A global database of soil microbial phospholipid fatty acids and enzyme activities","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Soil Carbon and Nitrogen Dynamics","field":"Agricultural and Biological Sciences","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":"Estonian Research Competency Council; Fundação para a Ciência e a Tecnologia; Natural Environment Research Council; Deutsches Zentrum für integrative Biodiversitätsforschung Halle-Jena-Leipzig; Japan Society for the Promotion of Science; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Ministério da Ciência, Tecnologia e Inovação; Generalitat Valenciana; China Postdoctoral Science Foundation; Austrian Science Fund; Eidgenössische Technische Hochschule Zürich; Academy of Finland; Eesti Teadusagentuur; Svenska Forskningsrådet Formas; Universität Kassel; Ministerstvo Školství, Mládeže a Tělovýchovy; Vetenskapsrådet; U.S. Department of Energy; National Natural Science Foundation of China; Agencia Estatal de Investigación; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Institute of Food and Agriculture; Ministerio de Ciencia, Tecnología e Innovación Productiva; Sight Research UK; Deutsche Forschungsgemeinschaft; European Commission; Division of Environmental Biology; Research Councils UK; Canadian Institute for Advanced Research; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Agence Nationale de la Recherche; Illinois Nutrient Research and Education Council; King Abdullah University of Science and Technology; Styrelsen för Internationellt Utvecklingssamarbete; Faculdade de Ciências e Tecnologia, Universidade Nova de Lisboa; Qatar Petroleum; U.S. Department of Agriculture; National Science Foundation","keywords":"Metadata; Ecosystem; Biomass (ecology); Georeference; Enzyme; Microbial ecology; Soil test","score_opus":0.023116330271086262,"score_gpt":0.25035119321967,"score_spread":0.22723486294858372,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414533842","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":[0.9825443,0.0004150808,0.000013901379,0.00023826672,0.0008010856,0.00009163351,0.014868264,0.0000322832,0.0009951993],"genre_scores_gemma":[0.9955755,0.000039278184,0.00021230483,0.000114213566,0.00005072958,0.000002332736,0.0033678778,4.1704584e-7,0.00063734275],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99887824,0.00004044584,0.00016228398,0.0005257563,0.0001796818,0.00021360026],"domain_scores_gemma":[0.9994136,0.00006461739,0.000057588888,0.0003608604,0.00004127094,0.00006204502],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047757014,0.00010427981,0.00014460635,0.000016033817,0.00020027312,0.00018555776,0.0007933867,0.000051843388,0.00008920952],"category_scores_gemma":[0.000088265006,0.00004644403,0.000033678814,0.0006277893,0.000422385,0.0002644534,0.0011463091,0.000055376277,0.0000050297754],"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":[0.00016326335,0.0003216699,0.05565445,0.00007786376,0.00006991711,0.0000068525783,0.00008380265,0.0000029521664,0.75151646,0.0034925977,0.08803459,0.10057556],"study_design_scores_gemma":[0.0019076373,0.00024010903,0.42632747,0.00040145812,0.00024009007,0.000054161475,0.0030537967,0.020898486,0.26038492,0.0044954605,0.28064027,0.0013561232],"about_ca_topic_score_codex":0.00073842803,"about_ca_topic_score_gemma":0.006162082,"teacher_disagreement_score":0.49113154,"about_ca_system_score_codex":0.000017668463,"about_ca_system_score_gemma":0.000041275332,"threshold_uncertainty_score":0.34385863},"labels":[],"label_agreement":null},{"id":"W4414606635","doi":"10.1038/s41597-025-05869-x","title":"Description of the monthly spatial dynamics of commercial and bycatch demersal species in the Bay of Biscay","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Marine and fisheries research","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Fisheries and Oceans Canada; Memorial University of Newfoundland","funders":"Institut Français de Recherche pour l'Exploitation de la Mer","keywords":"Demersal zone; Bycatch; Bay; Fishing; Demersal fish; Cuckoo; Key (lock); Carpentaria","score_opus":0.03688700128157619,"score_gpt":0.26206275582751365,"score_spread":0.22517575454593747,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414606635","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":[0.93472075,0.000011370305,0.00028514,0.0012765905,0.0003177015,0.00023278916,0.0009273745,0.00000159119,0.062226698],"genre_scores_gemma":[0.9978201,0.0000069532275,0.00009751219,0.00001576679,0.0000047334283,0.0000015765889,0.00015476988,0.0000015267192,0.0018970723],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9990528,0.00009193615,0.00019139232,0.00019556505,0.00036040726,0.00010784709],"domain_scores_gemma":[0.9990153,0.000051143405,0.00006189387,0.0008478982,0.000012038835,0.000011755378],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011260548,0.000044048655,0.00008737286,0.000041864,0.00008537138,0.00003700857,0.0012041506,0.000023495826,0.0003752243],"category_scores_gemma":[0.00012436451,0.00002653542,0.000017095961,0.0005790705,0.0013023838,0.00015683792,0.0016692205,0.000083665785,0.0000012074855],"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":[0.000019501485,0.00007733539,0.9702959,0.00002565288,0.000004209439,2.0040332e-7,0.00047781217,0.000011525968,0.001394652,0.00051185576,0.014041401,0.013139946],"study_design_scores_gemma":[0.00014706986,0.000016918797,0.9610393,0.000011024592,0.000009282015,1.9530336e-7,0.000797324,0.013754571,0.0005841567,0.00048008194,0.023125077,0.000035013254],"about_ca_topic_score_codex":0.0031447355,"about_ca_topic_score_gemma":0.051964443,"teacher_disagreement_score":0.06309934,"about_ca_system_score_codex":0.000020829104,"about_ca_system_score_gemma":0.000026498268,"threshold_uncertainty_score":0.9653347},"labels":[],"label_agreement":null},{"id":"W4414664181","doi":"10.1038/s41597-025-05877-x","title":"Soil carbon stock densities in mangrove and forested wetland ecosystems of Panama","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Coastal wetland ecosystem dynamics","field":"Environmental 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":"McGill University","funders":"Horizon 2020 Framework Programme; Smithsonian Tropical Research Institute; Secretaria Nacional de Ciencia y Tecnología; European Commission; Inter-American Development Bank; Ministry of Environment; Department for Environment, Food and Rural Affairs, UK Government; Smithsonian Institution","keywords":"Wetland; Soil carbon; Mangrove; Ecosystem; Peat; Blue carbon; Histosol; Carbon stock; Soil organic matter; Carbon sequestration","score_opus":0.013690570068821151,"score_gpt":0.22979700522102864,"score_spread":0.21610643515220748,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414664181","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":[0.990707,0.000062773805,0.00006371681,0.00007022896,0.00067309773,0.0002484164,0.0006946678,0.000015821974,0.007464301],"genre_scores_gemma":[0.99603146,0.0000069148955,0.0000692821,0.0000082793795,0.000007791726,0.000005516788,0.00037472384,0.0000059063295,0.0034901502],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986233,0.000050719318,0.00029585246,0.0005520974,0.00024193348,0.00023609714],"domain_scores_gemma":[0.9987221,0.000058056565,0.0000809943,0.0010808059,0.000008761763,0.000049284197],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00082554726,0.00010603554,0.00019394094,0.0001338664,0.00008096614,0.00010539241,0.0005850096,0.00004910492,0.000052519204],"category_scores_gemma":[0.00006554786,0.0000963095,0.000015081619,0.0004838596,0.00020742798,0.00022358783,0.0016518111,0.00006726538,0.000015743659],"study_design_candidate":"observational","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":[0.000041368952,0.000091437454,0.9678124,0.00032006257,0.000024371506,0.000017859591,0.00057437015,0.00039798627,0.007655525,0.00017483158,0.013416141,0.0094736535],"study_design_scores_gemma":[0.0010069154,0.000039242153,0.25943372,0.00034738268,0.000039218525,0.000014929603,0.0012328287,0.72282964,0.00056760374,0.0011563083,0.012993154,0.00033906705],"about_ca_topic_score_codex":0.0053371075,"about_ca_topic_score_gemma":0.25294283,"teacher_disagreement_score":0.72243166,"about_ca_system_score_codex":0.00008008482,"about_ca_system_score_gemma":0.000026267315,"threshold_uncertainty_score":0.80681455},"labels":[],"label_agreement":null},{"id":"W4414786104","doi":"10.1038/s41597-026-07582-9","title":"Persistent hindrances to data re-use in single-cell genomics","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; National Institutes of Health","keywords":"Raw data; Genomics; USable; Data sharing; Transcriptome; Functional genomics","score_opus":0.0914354641283294,"score_gpt":0.2841214691485495,"score_spread":0.19268600502022012,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414786104","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":[0.984193,0.001147186,0.0022971686,0.00054929696,0.002995897,0.00037873074,0.0053462666,0.000020147923,0.003072287],"genre_scores_gemma":[0.9632265,0.000057338726,0.0051732706,0.0006714409,0.000118206015,0.0000049538776,0.018481662,0.000020156443,0.012246481],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99801004,0.000045141576,0.00025740007,0.0012314357,0.0001518191,0.00030417176],"domain_scores_gemma":[0.9959616,0.000017023824,0.000040902454,0.003843806,0.00005287747,0.00008381081],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006737664,0.00013898317,0.0001370438,0.0001257374,0.00013810545,0.00036647872,0.0027050362,0.00009009101,0.00002034695],"category_scores_gemma":[0.00020554308,0.00014016085,0.000037362795,0.0003446595,0.00013869448,0.00003190136,0.0018176867,0.00009035446,0.000032061493],"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":[0.00008467322,0.0002987917,0.0025383416,0.00003796986,0.000025253361,0.0000042888178,0.00010696233,0.0001456265,0.82247454,0.000011848771,0.17065825,0.0036134585],"study_design_scores_gemma":[0.0005436978,0.000065473214,0.0005038086,0.000043673466,0.000031461142,0.0000012966707,0.0002446389,0.002923355,0.06844411,0.000018800036,0.9269307,0.0002489284],"about_ca_topic_score_codex":0.000118034346,"about_ca_topic_score_gemma":0.0028272884,"teacher_disagreement_score":0.7562725,"about_ca_system_score_codex":0.00002976335,"about_ca_system_score_gemma":0.00019035256,"threshold_uncertainty_score":0.57155937},"labels":[],"label_agreement":null},{"id":"W4414964998","doi":"10.1038/s41597-025-06046-w","title":"Aerodynamic dataset for selected doubly curved membrane canopy structures","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Wind and Air Flow Studies","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Western University","funders":"HORIZON EUROPE Framework Programme; Horizon 2020 Framework Programme; European Commission","keywords":"Aerodynamics; Wind tunnel; Ridge; Flow (mathematics); Scale (ratio); Arch; Boundary (topology); Canopy; Conical surface","score_opus":0.02408599901505776,"score_gpt":0.28398071527915625,"score_spread":0.2598947162640985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414964998","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":[0.5564262,0.00052880245,0.0036855368,0.0048761433,0.011254157,0.0028355906,0.411156,0.00036798164,0.008869558],"genre_scores_gemma":[0.80408,0.00001491201,0.006011331,0.0005851452,0.00011791845,0.000055484576,0.16960545,0.000024658406,0.019505119],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99815756,0.00003286415,0.0001994498,0.00094908685,0.00027605056,0.0003849668],"domain_scores_gemma":[0.9981348,0.00006613761,0.00005192599,0.0016645945,0.000018879202,0.00006369789],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005874112,0.00014889371,0.00015668634,0.00006321746,0.00067749474,0.00023425937,0.0016913912,0.000039869807,0.00065035373],"category_scores_gemma":[0.0002296958,0.00012188803,0.000023050976,0.0008656417,0.00036499032,0.0004024475,0.0015962272,0.00008117344,0.00015796455],"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":[0.000021391263,0.00003309802,0.0012490744,0.000021365442,0.000024581223,0.0000010295818,0.0000387722,0.000114240094,0.02659322,0.000096454714,0.969054,0.002752807],"study_design_scores_gemma":[0.0005709828,0.000014127974,0.030857919,0.000015196437,0.00004847074,0.0000011996907,0.00005226577,0.005000469,0.003718583,0.000717786,0.9587817,0.00022127555],"about_ca_topic_score_codex":0.0002878926,"about_ca_topic_score_gemma":0.0034785767,"teacher_disagreement_score":0.24765375,"about_ca_system_score_codex":0.000057237787,"about_ca_system_score_gemma":0.00005728414,"threshold_uncertainty_score":0.71209174},"labels":[],"label_agreement":null},{"id":"W4415040514","doi":"10.1038/s41597-025-05924-7","title":"CanCPLD: Convective Parameters and Lightning Data to Support Future Thunderstorm Projections in North America","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Fire effects on ecosystems","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 British Columbia; Environment and Climate Change Canada","funders":"Environment and Climate Change Canada","keywords":"Thunderstorm; Lightning (connector); Climate change; Climate model; Nowcasting; Convection; Severe weather; Statistical model","score_opus":0.03515086346564959,"score_gpt":0.28131441501360893,"score_spread":0.24616355154795933,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415040514","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":[0.9744786,0.00008843559,0.0011820217,0.0025024007,0.0060868934,0.0020610422,0.0069916532,0.00012806393,0.006480882],"genre_scores_gemma":[0.99111617,0.0000075842127,0.0028457176,0.00044693873,0.00004503094,0.000049902712,0.0032596183,0.000014682656,0.0022143726],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99755996,0.00008805563,0.00022970814,0.001435667,0.00031281635,0.0003737664],"domain_scores_gemma":[0.9968627,0.0000863073,0.000067535875,0.0028489092,0.000008882182,0.00012563242],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009211411,0.00014886838,0.00018428492,0.00020183227,0.00031793522,0.00027677076,0.0018684756,0.00004209421,0.00014327143],"category_scores_gemma":[0.00021612959,0.00013859344,0.000011310221,0.002006032,0.00033076658,0.000954127,0.003385209,0.00017151402,0.00031857291],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029339773,0.00014479707,0.15880026,0.00005744676,0.00003954404,0.00002568725,0.003141502,0.00014623451,0.0013105726,0.000019368286,0.7635726,0.07271268],"study_design_scores_gemma":[0.00037272036,0.00009037558,0.15610701,0.00005794053,0.000035923615,0.000009311712,0.00281007,0.022271529,0.00013997605,0.000022314092,0.81771326,0.00036955927],"about_ca_topic_score_codex":0.0047245747,"about_ca_topic_score_gemma":0.13165297,"teacher_disagreement_score":0.1269284,"about_ca_system_score_codex":0.00025645655,"about_ca_system_score_gemma":0.00010331542,"threshold_uncertainty_score":0.8841921},"labels":[],"label_agreement":null},{"id":"W4415265664","doi":"10.1038/s41597-025-05854-4","title":"Lung Ultrasound Imaging Dataset for Accurate Detection and Localization of LUS Vertical Artifact","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Ultrasound in Clinical Applications","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Makerere University; International Development Research Centre","keywords":"Artifact (error); Lung ultrasound; Ultrasound; Pattern recognition (psychology); Economic shortage; Deep learning","score_opus":0.05532807895029387,"score_gpt":0.3994944132357846,"score_spread":0.34416633428549076,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415265664","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":[0.052379183,0.00024375085,0.9146061,0.0010385626,0.00084278634,0.0011022682,0.029498484,0.000053148386,0.0002357503],"genre_scores_gemma":[0.949311,0.000016222619,0.0024828813,0.00022371691,0.000034936947,0.000020713644,0.047681276,0.000007447917,0.00022177825],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99881387,0.000020703315,0.00033698496,0.0005275529,0.0001540342,0.00014683003],"domain_scores_gemma":[0.99779093,0.00070216245,0.00005156179,0.0012559836,0.00012934371,0.000070039605],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00082778465,0.00007215527,0.00014336355,0.00009616221,0.00019667545,0.00010593008,0.00025991295,0.00003824276,0.0000562741],"category_scores_gemma":[0.0028151344,0.000064261294,0.000020093159,0.00042983674,0.00039256993,0.0002659897,0.0001776387,0.00007794778,0.000009937246],"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":[0.00037473856,0.0006438016,0.04176588,0.0008218375,0.00016439585,0.0000012181146,0.0001080621,0.00004266099,0.37851185,0.001981304,0.5307128,0.044871494],"study_design_scores_gemma":[0.0022238004,0.000067970825,0.035860248,0.00022927609,0.00082257617,0.000026114694,0.00021551915,0.29948688,0.07098061,0.0059027104,0.5839327,0.00025158696],"about_ca_topic_score_codex":0.000019026,"about_ca_topic_score_gemma":0.00003905588,"teacher_disagreement_score":0.9121232,"about_ca_system_score_codex":0.000026245647,"about_ca_system_score_gemma":0.00009635142,"threshold_uncertainty_score":0.33701822},"labels":[],"label_agreement":null},{"id":"W4415648821","doi":"10.1038/s41597-025-05976-9","title":"A global database on land use and management change effects on soil KMnO4-oxidisable organic carbon (POXC)","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Soil Carbon and Nitrogen Dynamics","field":"Agricultural and Biological 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":"Smiths Detection (Canada)","funders":"Agence Nationale de la Recherche; European Commission","keywords":"Soil carbon; Arable land; Land use; Land use, land-use change and forestry; Soil health; Land management; Soil management; Soil organic matter; Soil quality","score_opus":0.04532416565877685,"score_gpt":0.25302777723991243,"score_spread":0.2077036115811356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415648821","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":[0.9937365,0.00013006048,7.917689e-7,0.0009496961,0.0008519092,0.00037145842,0.0022287308,0.000072896444,0.0016579623],"genre_scores_gemma":[0.9927628,0.00009886644,0.000036328838,0.0010620477,0.000114529255,0.000023773,0.0038748165,0.0000014633955,0.0020253675],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99833643,0.00007067745,0.000110940004,0.0008586219,0.00030594014,0.00031738635],"domain_scores_gemma":[0.9991563,0.000115340314,0.00003940447,0.00055457494,0.000027068438,0.00010731334],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044563392,0.00016270594,0.00014102699,0.00003155157,0.00025728846,0.00045911412,0.00067498174,0.00005502626,0.00002731872],"category_scores_gemma":[0.000079788384,0.00007166427,0.000024619354,0.00085632666,0.00010112172,0.00021307381,0.00093553617,0.00007353088,0.00003694855],"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":[0.0008313352,0.00196173,0.21242675,0.0008198687,0.0004246036,0.00041596836,0.00016157095,0.000010206299,0.06885321,0.012624688,0.33748186,0.36398822],"study_design_scores_gemma":[0.0018681986,0.0005754899,0.804316,0.000730811,0.00029813367,0.000010406831,0.00025630434,0.020201063,0.005090613,0.0010359053,0.16451028,0.0011068125],"about_ca_topic_score_codex":0.00075625116,"about_ca_topic_score_gemma":0.009443926,"teacher_disagreement_score":0.5918892,"about_ca_system_score_codex":0.00004764298,"about_ca_system_score_gemma":0.000008543031,"threshold_uncertainty_score":0.5269932},"labels":[],"label_agreement":null},{"id":"W4415657680","doi":"10.1038/s41597-026-07496-6","title":"Characterization of high-resolution AI data center training workloads on single and multiple GPU nodes","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Cloud Computing and Resource Management","field":"Computer 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":"York University; Independent Electricity System Operator","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Session (web analytics); Resilience (materials science); Grid; Data center; Set (abstract data type); Energy consumption; Data set; Training set; Training (meteorology)","score_opus":0.06182922118262564,"score_gpt":0.2691192533714195,"score_spread":0.20729003218879388,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415657680","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":[0.5104805,0.000076553726,0.4808622,0.0031058928,0.0032062682,0.0002739757,0.0012064895,0.00016580735,0.0006222621],"genre_scores_gemma":[0.9912755,0.0000021581868,0.0052935383,0.00021493499,0.000049503753,9.256962e-7,0.002061936,0.0000047306194,0.0010967943],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998208,0.00006890068,0.00024434383,0.00096717273,0.00028914105,0.00022245853],"domain_scores_gemma":[0.9965019,0.00007108422,0.00010864237,0.0032295235,0.00004757919,0.000041230945],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001037031,0.00010401856,0.000135593,0.00022365138,0.00028088363,0.00054780726,0.002835094,0.000033011613,0.0000032899509],"category_scores_gemma":[0.00013759572,0.00009416888,0.0000132795885,0.0006514298,0.00014275627,0.0002155101,0.00477751,0.00008505554,0.000008421562],"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":[0.000039493298,0.00081081287,0.0015775332,0.00017767375,0.00009370812,0.000007606586,0.001770303,0.0021029992,0.059791457,0.009698445,0.03481582,0.88911414],"study_design_scores_gemma":[0.0005264069,0.000027621189,0.0084433,0.00035232215,0.0000149107545,0.0000014282842,0.00006236272,0.9298678,0.001366731,0.00034962196,0.058833048,0.00015445621],"about_ca_topic_score_codex":0.000027395121,"about_ca_topic_score_gemma":0.000018312428,"teacher_disagreement_score":0.9277648,"about_ca_system_score_codex":0.000019141029,"about_ca_system_score_gemma":0.000037767073,"threshold_uncertainty_score":0.59548247},"labels":[],"label_agreement":null},{"id":"W4415702507","doi":"10.1038/s41597-025-06212-0","title":"Author Correction: ROBIN: Reference observatory of basins for international hydrological climate change detection","year":2025,"lang":"en","type":"erratum","venue":"Scientific Data","topic":"Hydrology and Watershed Management Studies","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Climate change; Change detection; Observatory; Drainage basin; Global change; General Circulation Model","score_opus":0.10853584463885262,"score_gpt":0.30733881501489174,"score_spread":0.1988029703760391,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415702507","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017653098,0.00054087245,0.00475,0.007263117,0.7576882,0.0031581928,0.030662255,0.00038301354,0.193789],"genre_scores_gemma":[0.028961726,0.00048629782,0.0009757862,0.00074158784,0.0013129505,0.0004360758,0.033294037,0.000032738557,0.9337588],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975165,0.000077253215,0.00038469024,0.0012447012,0.00040252853,0.0003743012],"domain_scores_gemma":[0.9982382,0.00006835372,0.00029051138,0.001301245,0.00005267027,0.00004901452],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015270499,0.0002293077,0.00030046175,0.00015230649,0.0005453163,0.00008073696,0.0019246745,0.00032211604,0.0007762675],"category_scores_gemma":[0.00039634478,0.00020435688,0.00007231367,0.0003855335,0.0006962219,0.00047017977,0.0037378331,0.00036523535,0.00017002352],"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":[0.000047189034,0.000075237556,0.00079935126,0.00007125542,0.000048396523,0.0000018041118,0.00006638688,0.00001865149,0.00006276752,0.000049265098,0.98907155,0.009688159],"study_design_scores_gemma":[0.00014643816,0.000059823302,0.006209032,0.00007390303,0.000094246534,9.3758064e-7,0.000032446525,0.009680138,0.00007368433,0.00026116884,0.98319006,0.00017815005],"about_ca_topic_score_codex":0.0000828944,"about_ca_topic_score_gemma":0.0011544336,"teacher_disagreement_score":0.75637525,"about_ca_system_score_codex":0.0001227195,"about_ca_system_score_gemma":0.000022571747,"threshold_uncertainty_score":0.8499585},"labels":[],"label_agreement":null},{"id":"W4415707275","doi":"10.1038/s41597-025-06005-5","title":"A Video Dataset for Nearshore Wave Breaking Type Classification","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Ocean Waves and Remote Sensing","field":"Earth and Planetary Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Breaking wave; Workflow; Breaking strength; Limiting; Dissipation; Frame (networking); Wave height","score_opus":0.11903734315670375,"score_gpt":0.315366750120919,"score_spread":0.19632940696421528,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415707275","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21368936,0.0040566833,0.017075216,0.013784024,0.055004444,0.0042685317,0.6394041,0.00047433737,0.052243274],"genre_scores_gemma":[0.5010696,0.000019201987,0.016082436,0.0005311158,0.00024455544,3.3858907e-8,0.47582868,0.0000061005867,0.0062182792],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987362,0.000029444882,0.0001748058,0.0006235564,0.00016963387,0.0002663836],"domain_scores_gemma":[0.9984255,0.00010792525,0.000055417648,0.0012892076,0.00006242899,0.000059510876],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009194596,0.00008463611,0.00009686762,0.00011546508,0.00048291846,0.000525937,0.0006250244,0.00004466092,0.00019959157],"category_scores_gemma":[0.00020795251,0.000068108864,0.000019964096,0.0005403454,0.00016925497,0.00037881185,0.00010055818,0.000071263516,0.00014509067],"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":[0.000027535545,0.0000105153895,0.0006472915,0.000039259325,0.00001608668,0.000002758194,0.00004792153,0.000055829845,0.00025669023,0.0002094441,0.6886208,0.3100659],"study_design_scores_gemma":[0.00009829544,0.000010458664,0.0094983615,0.000029281699,0.000021585205,0.00000374391,0.00013493477,0.35456493,0.00005163185,0.00082016096,0.6346878,0.00007879754],"about_ca_topic_score_codex":0.00017419214,"about_ca_topic_score_gemma":0.0007431113,"teacher_disagreement_score":0.35450912,"about_ca_system_score_codex":0.0000039598394,"about_ca_system_score_gemma":0.00012939403,"threshold_uncertainty_score":0.5071623},"labels":[],"label_agreement":null},{"id":"W4416143213","doi":"10.1038/s41597-025-06045-x","title":"Plant traits and associated ecological data from Afromontane grasslands of Maloti-Drakensberg, South Africa","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Remote Sensing in Agriculture","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Senter for Internasjonalisering av Utdanning; Universitetet i Bergen","keywords":"Trait; Ecosystem; Vegetation (pathology); Vascular plant; Taxon; Climate change; Plant community; Biodiversity; Terrestrial plant","score_opus":0.04068062986498387,"score_gpt":0.23800735297200298,"score_spread":0.1973267231070191,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416143213","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":[0.94900304,0.00018509268,0.00012691582,0.00039771368,0.0008070333,0.00027658668,0.041500416,0.000075172444,0.007628003],"genre_scores_gemma":[0.98128283,0.0000075439198,0.002216831,0.00003146614,0.000020673933,4.0971295e-7,0.013349249,0.000006497733,0.0030844996],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9974726,0.000112435846,0.00031982173,0.0012700268,0.0004932805,0.00033182823],"domain_scores_gemma":[0.99793154,0.00012890612,0.00015379803,0.0016672713,0.00001498837,0.000103507315],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010191634,0.00016690041,0.00027032726,0.000047182082,0.00023171213,0.0001937411,0.002295856,0.00013746787,0.00039751572],"category_scores_gemma":[0.00059456105,0.000118229094,0.000021982843,0.0006619047,0.0006162575,0.0003446065,0.0040110094,0.0001756081,0.00010951219],"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":[0.000029065373,0.00037517477,0.019045321,0.0000123544005,0.000099139674,0.000056904464,0.0009662843,0.000038782015,0.066156186,0.000028957136,0.9094349,0.0037569453],"study_design_scores_gemma":[0.000591847,0.000029417408,0.93087804,0.000095044365,0.00013701516,0.0000067975534,0.0003649604,0.016728241,0.0006516044,0.0007800078,0.04944633,0.00029067686],"about_ca_topic_score_codex":0.00019575514,"about_ca_topic_score_gemma":0.0022866572,"teacher_disagreement_score":0.91183275,"about_ca_system_score_codex":0.000055936198,"about_ca_system_score_gemma":0.00003087608,"threshold_uncertainty_score":0.49994364},"labels":[],"label_agreement":null},{"id":"W4416386449","doi":"10.1038/s41597-025-06115-0","title":"Mouse Hippocampal Sharp-Wave Ripple Dataset Curated From Public Neuropixels Datasets","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Neural dynamics and brain function","field":"Neuroscience","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"CIHR Skin Research Training Centre; Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Hippocampal formation; Task (project management); Hippocampus; Field (mathematics); Raw data; Electrophysiology; Process (computing)","score_opus":0.14175337180313524,"score_gpt":0.3148659871587131,"score_spread":0.17311261535557787,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416386449","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.121972755,0.000038052338,0.0010749672,0.0025108373,0.0062769405,0.00045314152,0.8669478,0.00021691751,0.0005085454],"genre_scores_gemma":[0.27746445,0.000021127784,0.0002409987,0.0031198775,0.000110538,0.000014413037,0.71462923,0.000027170125,0.004372225],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.995871,0.00025808456,0.00041630687,0.0022904107,0.00059362926,0.0005705833],"domain_scores_gemma":[0.9940535,0.00030681957,0.0001496211,0.0052409214,0.000052387626,0.00019675563],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00070268364,0.00025284523,0.00021748093,0.00030318025,0.00078832573,0.0021454857,0.0030244421,0.000072901974,0.00075764174],"category_scores_gemma":[0.0022384564,0.00022637555,0.00003593531,0.0016726526,0.00045885265,0.0021180888,0.0033544279,0.00031760678,0.00083019905],"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":[0.000017434673,0.000115732284,0.000039826868,0.000009150901,0.0000060120838,0.000035320303,0.0000068185705,0.0000038234493,0.26590136,0.0010017189,0.7275247,0.0053381356],"study_design_scores_gemma":[0.0004367311,0.000018617762,0.00026626803,0.000017103444,0.000025244626,0.000008068717,0.000016110629,0.048462983,0.027022947,0.0016454284,0.92181844,0.00026204018],"about_ca_topic_score_codex":0.00015926847,"about_ca_topic_score_gemma":0.0002586731,"teacher_disagreement_score":0.2388784,"about_ca_system_score_codex":0.000039812763,"about_ca_system_score_gemma":0.00019195517,"threshold_uncertainty_score":0.9999478},"labels":[],"label_agreement":null},{"id":"W4416386476","doi":"10.1038/s41597-025-06284-y","title":"14,441 Genomics-Based Validated Automated Comprehensive Clinicopathologic Correlations for Myeloid Neoplasms","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Chronic Myeloid Leukemia Treatments","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Nova Scotia Health Authority; Spinologics (Canada)","funders":"","keywords":"Myeloid; Myeloid leukemia; Dysplasia; Peripheral blood; Myeloid sarcoma; Blood cancer","score_opus":0.08826511586548723,"score_gpt":0.3756117539573349,"score_spread":0.2873466380918477,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416386476","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":[0.9041184,0.0013392658,0.02480339,0.0046298276,0.015895722,0.008004274,0.033796154,0.0030935872,0.004319367],"genre_scores_gemma":[0.66515005,0.0000389517,0.07693612,0.002543989,0.00021157325,0.0003170578,0.21169826,0.00010640666,0.042997576],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99719167,0.00008883787,0.00061636843,0.0012975927,0.00031309042,0.0004924459],"domain_scores_gemma":[0.9954462,0.00055318925,0.00020046049,0.0032204804,0.00041974752,0.00015994042],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008070871,0.00026379814,0.00046567575,0.00037720476,0.00053609046,0.00020145676,0.000858153,0.00018919475,0.00020814668],"category_scores_gemma":[0.00088639476,0.00023736194,0.000119954886,0.0009766392,0.00043852115,0.00018510106,0.00049668655,0.00022850659,0.00046090878],"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":[0.0005394813,0.0008883801,0.0050913775,0.00034450626,0.0003350335,0.00008392264,0.00014168289,0.001086758,0.026243601,0.00033652087,0.9561693,0.008739404],"study_design_scores_gemma":[0.012209726,0.00023836158,0.01602341,0.00031396782,0.0008892423,0.000037734495,0.00016107876,0.5022919,0.0064725955,0.0003175398,0.46067888,0.00036551282],"about_ca_topic_score_codex":0.000029640201,"about_ca_topic_score_gemma":0.000041460957,"teacher_disagreement_score":0.5012052,"about_ca_system_score_codex":0.00061122864,"about_ca_system_score_gemma":0.0024440042,"threshold_uncertainty_score":0.9679339},"labels":[],"label_agreement":null},{"id":"W4416389477","doi":"10.1038/s41597-025-06130-1","title":"Global dataset for realized thermal and aridity niche limits for terrestrial vertebrates","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Species Distribution and Climate Change","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; University of Ottawa","keywords":"Niche; Arid; Climate change; Range (aeronautics); Macroecology; Extinction (optical mineralogy); Ecological niche; Population; Environmental change","score_opus":0.09821407305433746,"score_gpt":0.3473951902289647,"score_spread":0.24918111717462724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416389477","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1412916,0.0001407269,0.003091291,0.0026866377,0.0037437752,0.0014326258,0.8426739,0.00006277676,0.0048766923],"genre_scores_gemma":[0.22243251,0.000046778576,0.0020568233,0.0012932237,0.00019484533,0.00022676316,0.7692852,0.000017447746,0.0044464106],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99875736,0.000023499373,0.00015506143,0.0006453368,0.00015202614,0.00026672438],"domain_scores_gemma":[0.99886304,0.00007776674,0.00004814246,0.0009300095,0.000007958655,0.00007305454],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007311215,0.0000970768,0.00011360139,0.000014930831,0.00039668573,0.00031815842,0.00082031166,0.000047813533,0.0020599104],"category_scores_gemma":[0.0003818859,0.00008360663,0.000025158528,0.00024958677,0.0003798283,0.00031035018,0.0007731009,0.000027182848,0.000074090596],"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":[0.00008979582,0.000051484312,0.0019266173,0.000010843511,0.000008064683,2.4214154e-7,0.000008406298,7.764715e-7,0.0019896552,0.0006296338,0.99088395,0.004400529],"study_design_scores_gemma":[0.0011877993,0.000021583937,0.015429879,0.0000061350574,0.000037552036,6.7596534e-7,0.000108179454,0.0023677552,0.0006574773,0.00086557824,0.97921115,0.00010626054],"about_ca_topic_score_codex":0.00015624188,"about_ca_topic_score_gemma":0.0016616151,"teacher_disagreement_score":0.08114091,"about_ca_system_score_codex":0.000107965185,"about_ca_system_score_gemma":0.000030838557,"threshold_uncertainty_score":0.9988523},"labels":[],"label_agreement":null},{"id":"W4416389566","doi":"10.1038/s41597-025-06106-1","title":"A dataset on metal-related production activities and their socio-environmental impacts in Canada","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Extraction and Separation Processes","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université du Québec à Montréal; Polytechnique Montréal","funders":"Haute école Spécialisée de Suisse Occidentale; Environment and Climate Change Canada; Government of Canada; École Polytechnique Fédérale de Lausanne; Polytechnique Montréal; Université du Québec à Montréal","keywords":"Traceability; Production (economics); Sustainability; Climate change; Environmental impact assessment; Ecological footprint; Code (set theory)","score_opus":0.015998062201415225,"score_gpt":0.2355920694080879,"score_spread":0.2195940072066727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416389566","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":[0.9799125,0.00052298803,0.000040489533,0.00038652893,0.0019508742,0.0001576925,0.015925575,0.000042206662,0.0010611012],"genre_scores_gemma":[0.9871376,0.00005027476,0.0000103397015,0.000035820805,0.0000068751706,0.0000036431115,0.011463665,0.000004111636,0.0012876636],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994219,0.0000149096395,0.00011072695,0.0002561201,0.00009047658,0.00010590021],"domain_scores_gemma":[0.9995016,0.00002439939,0.000016135602,0.00042876828,0.0000023792506,0.000026735079],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020765197,0.000071570816,0.000068346286,0.000094462936,0.00009767048,0.000085701715,0.00015938407,0.00001843063,0.00006686187],"category_scores_gemma":[0.00003356379,0.00006283825,0.0000039484835,0.00018342948,0.000052778574,0.0005279809,0.00006511198,0.00009503393,0.000009104545],"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":[0.000011241765,0.00005446218,0.00084781996,0.00008525162,0.000055867455,0.0000032043672,0.0004727612,0.002918197,0.038421847,0.00007120957,0.94756794,0.009490186],"study_design_scores_gemma":[0.0005986393,0.000012560567,0.010466286,0.000096661555,0.000027124204,0.000012911619,0.009926477,0.0413262,0.049152322,0.00044817015,0.8875276,0.0004050462],"about_ca_topic_score_codex":0.010523368,"about_ca_topic_score_gemma":0.22678122,"teacher_disagreement_score":0.21625784,"about_ca_system_score_codex":0.00018048528,"about_ca_system_score_gemma":0.00017825069,"threshold_uncertainty_score":0.9960656},"labels":[],"label_agreement":null},{"id":"W4416414271","doi":"10.1038/s41597-025-06068-4","title":"The ICGC ARGO data dictionary for standardizing global cancer clinical data","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Indoc Research; University of Toronto; Ontario Institute for Cancer Research","funders":"Government of Ontario","keywords":"Interoperability; Cancer; Clinical Oncology; Argo; Precision oncology; Germline; Genome; Genomics; Metadata","score_opus":0.12173710700112084,"score_gpt":0.456465764786295,"score_spread":0.3347286577851742,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416414271","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009116296,0.034937084,0.06291809,0.0068390737,0.025674587,0.0010375987,0.85724217,0.000035641548,0.002199451],"genre_scores_gemma":[0.13701761,0.02248385,0.015706085,0.0036377267,0.0062632775,0.00012502176,0.79999113,0.00007487826,0.014700402],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.997802,0.00004253349,0.0003354289,0.0013590432,0.0001780262,0.0002829276],"domain_scores_gemma":[0.99106336,0.0001434384,0.00009243779,0.008497741,0.00013066774,0.000072364615],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0026309246,0.00011037725,0.00012250448,0.000015013312,0.00065770274,0.00043281747,0.005604944,0.00008167856,0.000008817845],"category_scores_gemma":[0.0017593831,0.00008791392,0.000034081702,0.00018211137,0.00040269713,0.000023510123,0.00962432,0.00007582407,0.0000056729386],"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":[0.00008068014,0.000035780744,0.0020622436,0.000010745415,0.00009292036,5.213252e-7,0.0000012532737,0.000012218361,0.00047032852,0.0003863214,0.937451,0.05939596],"study_design_scores_gemma":[0.00041161798,0.000020231993,0.0011068422,0.000019218543,0.00007755686,0.0000011019206,0.000039933297,0.004892235,0.00018062764,0.0004913928,0.99265444,0.00010479277],"about_ca_topic_score_codex":0.000091023765,"about_ca_topic_score_gemma":0.0029925623,"teacher_disagreement_score":0.12790132,"about_ca_system_score_codex":0.000028694403,"about_ca_system_score_gemma":0.0012604584,"threshold_uncertainty_score":0.99977523},"labels":[],"label_agreement":null},{"id":"W4416475311","doi":"10.1038/s41597-025-06286-w","title":"AmphiTherm: a comprehensive database of amphibian thermal tolerance and preference","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Amphibian and Reptile Biology","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; Environment and Climate Change Canada","funders":"Fondo Nacional de Desarrollo Científico y Tecnológico; University of New South Wales; Department of Education and Training; Deutsche Forschungsgemeinschaft; Wenner-Gren Foundation","keywords":"Ectotherm; Amphibian; Biodiversity; Preference; Trait; Resource (disambiguation)","score_opus":0.04953360695434261,"score_gpt":0.2723470102566372,"score_spread":0.2228134033022946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416475311","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":[0.986781,0.0003704369,0.0002583701,0.00022199293,0.0006026266,0.0002549849,0.0014636491,0.000026953103,0.010020006],"genre_scores_gemma":[0.9934363,0.00003014814,0.0014139795,0.00017957111,0.000014313435,0.000003985165,0.0005121712,0.000004709245,0.004404831],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9986194,0.00006164296,0.00019578362,0.0007381226,0.00017092173,0.00021416582],"domain_scores_gemma":[0.9982134,0.000047495767,0.00007668451,0.0015832115,0.000014011913,0.00006515829],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003057218,0.0001068791,0.00015207303,0.000047517155,0.00016357123,0.000046872236,0.001011369,0.000046164012,0.00076779985],"category_scores_gemma":[0.00004426882,0.000084562926,0.000016469887,0.00034806173,0.0016582177,0.0002677224,0.0020836554,0.000076041964,0.00011572072],"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":[0.000089092224,0.00022685078,0.090609826,0.00011343108,0.000035370173,0.000009451817,0.00051143474,0.00007164933,0.6845264,0.00082417217,0.13608098,0.08690135],"study_design_scores_gemma":[0.0011557403,0.00007310175,0.608316,0.00025786084,0.00005570552,0.000013395915,0.0004680407,0.006864378,0.01709409,0.00059375615,0.36460817,0.0004997722],"about_ca_topic_score_codex":0.000121065495,"about_ca_topic_score_gemma":0.00027811612,"teacher_disagreement_score":0.6674323,"about_ca_system_score_codex":0.000015789767,"about_ca_system_score_gemma":0.00003193717,"threshold_uncertainty_score":0.840687},"labels":[],"label_agreement":null},{"id":"W4416536103","doi":"10.1038/s41597-025-05513-8","title":"Twenty years (2000–2020) of butterfly monitoring data across the contiguous United States","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Lepidoptera: Biology and Taxonomy","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Cascades (Canada)","funders":"U.S. Geological Survey; U.S. Fish and Wildlife Service; Israel Institute for Biological Research; U.S. Department of the Interior; National Science Foundation","keywords":"Butterfly; Taxonomy (biology); Biodiversity; Population; Taxonomic rank; Occupancy","score_opus":0.04054657016238197,"score_gpt":0.32129642095769834,"score_spread":0.28074985079531634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416536103","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":[0.974581,0.0018130938,0.0014170613,0.0008006685,0.0034910864,0.00028577092,0.016495606,0.000019158264,0.0010965454],"genre_scores_gemma":[0.97023404,0.00012225372,0.0003337331,0.0001433312,0.000121591715,0.0000047466983,0.027229734,0.0000054319767,0.0018051609],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99861,0.000105410094,0.00022338868,0.00069336913,0.000099625366,0.00026815795],"domain_scores_gemma":[0.9960783,0.000047057518,0.00009396747,0.003659359,0.00008542751,0.00003589303],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013335978,0.000104474595,0.00011768197,0.0000368627,0.00023438604,0.00011749127,0.002773899,0.00008662325,0.000012632046],"category_scores_gemma":[0.00027924715,0.00007900928,0.000024771212,0.00032030413,0.00056774647,0.000017708398,0.0029868449,0.00012591231,0.000017359134],"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":[0.0003229952,0.00039416592,0.11475778,0.00013924266,0.0009176727,0.000026858306,0.0009317418,0.0001328272,0.047984667,0.00009637053,0.5093847,0.32491097],"study_design_scores_gemma":[0.00026659397,0.000020521313,0.00292219,0.000026892701,0.000027214279,0.0000025765287,0.00049042155,0.00025937363,0.013712927,0.00003403078,0.98213714,0.00010010177],"about_ca_topic_score_codex":0.00015683791,"about_ca_topic_score_gemma":0.00007558229,"teacher_disagreement_score":0.47275245,"about_ca_system_score_codex":0.000006918018,"about_ca_system_score_gemma":0.00013756675,"threshold_uncertainty_score":0.51546407},"labels":[],"label_agreement":null},{"id":"W4416648216","doi":"10.1038/s41597-025-06269-x","title":"Historical insect disturbance maps from 1985 onwards for Canadian forests derived using earth observation data","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Remote Sensing in Agriculture","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":true,"ca_institutions":"Université Laval; Natural Resources Canada; Canadian Forest Service","funders":"Government of Canada","keywords":"Disturbance (geology); Taiga; Canopy; Satellite imagery; Boreal; Vegetation (pathology); Spruce budworm; Earth observation; Insect pest","score_opus":0.09896318917980036,"score_gpt":0.271258103074513,"score_spread":0.17229491389471263,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416648216","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":[0.93581337,0.00049250596,0.021174517,0.0027630571,0.010888289,0.0013056711,0.025282485,0.00012686278,0.0021532585],"genre_scores_gemma":[0.69328713,0.000012741059,0.18432753,0.00074508064,0.00044777474,0.000006189231,0.09751156,0.0000495068,0.023612507],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975365,0.000053057352,0.00026086366,0.0013371554,0.00039526526,0.000417174],"domain_scores_gemma":[0.9962549,0.00007689525,0.00009657433,0.0033648189,0.00003168481,0.00017510007],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069503294,0.00016085846,0.00016871761,0.000066060216,0.0007071226,0.00038837385,0.0026388466,0.00009639719,0.000071520204],"category_scores_gemma":[0.0006389517,0.00013960792,0.000028524939,0.00076444354,0.00022829902,0.0009931826,0.0014781521,0.00013141456,0.00006191864],"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":[0.000009414145,0.00003154396,0.027909223,0.000010830368,0.000015535798,0.0000052057117,0.00010135778,0.00032670592,0.017343482,0.00002513142,0.94211435,0.012107246],"study_design_scores_gemma":[0.00015893212,0.000004652348,0.20668283,0.000038992534,0.000032598877,0.0000012051364,0.00001932842,0.051255092,0.00039507847,0.00047312895,0.74077004,0.00016814907],"about_ca_topic_score_codex":0.22892424,"about_ca_topic_score_gemma":0.6852789,"teacher_disagreement_score":0.45635465,"about_ca_system_score_codex":0.0009843436,"about_ca_system_score_gemma":0.00023148295,"threshold_uncertainty_score":0.7762104},"labels":[],"label_agreement":null},{"id":"W4416729431","doi":"10.1038/s41597-025-06322-9","title":"Balanced X-ray Security Dataset and Enhanced YOLO for Contraband Detection","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Department of Industrial and Systems Engineering, Hong Kong Polytechnic University; Hong Kong Polytechnic University","keywords":"Undersampling; Class (philosophy); Software deployment; Adaptability; Enhanced Data Rates for GSM Evolution; A priori and a posteriori; Economic shortage; Downgrade","score_opus":0.024705469303074025,"score_gpt":0.31039716708903015,"score_spread":0.2856916977859561,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416729431","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":[0.0029537806,0.0001738346,0.98646533,0.0007242507,0.0010486218,0.000572574,0.007828195,0.000108680666,0.00012474993],"genre_scores_gemma":[0.9517825,0.000029578567,0.036976077,0.00043524947,0.00006970819,0.00015913937,0.009740324,0.000007592098,0.00079981476],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983691,0.000028532948,0.00018126672,0.0010417158,0.00012972181,0.00024966514],"domain_scores_gemma":[0.99713147,0.00018989979,0.00007247134,0.0024731741,0.000069172755,0.00006379347],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005429435,0.00010044271,0.00011967271,0.00008458997,0.0005129928,0.00042154387,0.0017868648,0.000036197853,0.0000030467738],"category_scores_gemma":[0.00015723235,0.00009625244,0.000013467068,0.00066894636,0.0001812321,0.0009466975,0.0010292158,0.000081344115,0.000009012732],"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":[0.000053171832,0.00015961089,0.000032240583,0.00010351511,0.000045521923,0.0000015747282,0.00021924736,0.00016141983,0.17688403,0.034796793,0.44291312,0.34462976],"study_design_scores_gemma":[0.00080656464,0.000027299579,0.00038828532,0.000026733414,0.000020834617,0.0000025015654,0.000020624408,0.25023058,0.049852952,0.039289784,0.65909815,0.0002357293],"about_ca_topic_score_codex":0.000004718233,"about_ca_topic_score_gemma":0.00011920272,"teacher_disagreement_score":0.94948924,"about_ca_system_score_codex":0.000017793665,"about_ca_system_score_gemma":0.000048603724,"threshold_uncertainty_score":0.40649572},"labels":[],"label_agreement":null},{"id":"W4416878460","doi":"10.1038/s41597-025-06332-7","title":"Bulk RNA sequencing dataset of Claudin-low breast cancer cell lines with Neuropilin-1 knockdown","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Barrier Structure and Function Studies","field":"Neuroscience","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Transcriptome; Breast cancer; Gene knockdown; RNA; Paclitaxel; Cell culture; Cancer; Messenger RNA","score_opus":0.048178467584468414,"score_gpt":0.29740879415923926,"score_spread":0.24923032657477084,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416878460","genre_codex":"dataset","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":[0.29256222,0.0020585961,0.0028032954,0.004249631,0.023261234,0.0012813108,0.65749556,0.00036974932,0.015918389],"genre_scores_gemma":[0.9860655,0.00017785133,0.00044929038,0.0012403823,0.00018608039,0.000016487415,0.0031291435,0.000021991282,0.008713237],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9978107,0.00006195594,0.00031529192,0.0011130794,0.00039897778,0.00029999955],"domain_scores_gemma":[0.997392,0.00010567789,0.00016593264,0.0021360258,0.00012894708,0.000071446484],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030513946,0.00017722652,0.00022362586,0.00012403603,0.00048683496,0.00019620216,0.0013734722,0.000036533806,0.00023472765],"category_scores_gemma":[0.0001548609,0.000127976,0.000023908744,0.0010398278,0.0009167077,0.0005977683,0.0010881678,0.0001531279,0.00002686434],"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":[0.00009153516,0.00005702161,0.0008399237,0.0001872552,0.000021261638,0.00001592084,0.00015549347,0.00010628433,0.41615474,0.00032761373,0.57569087,0.006352058],"study_design_scores_gemma":[0.00085637247,0.000046076704,0.0019141268,0.00020457298,0.000151467,0.000036014317,0.00048184444,0.0022725917,0.59924096,0.0001551149,0.39422563,0.00041524513],"about_ca_topic_score_codex":0.0003909283,"about_ca_topic_score_gemma":0.00068501086,"teacher_disagreement_score":0.6935033,"about_ca_system_score_codex":0.000034354714,"about_ca_system_score_gemma":0.0003439129,"threshold_uncertainty_score":0.52187103},"labels":[],"label_agreement":null},{"id":"W4416947312","doi":"10.1038/s41597-025-06191-2","title":"Reconstruction of 1,979 prokaryotic metagenome-assembled genomes from 37 global cave environments","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Subterranean biodiversity and taxonomy","field":"Earth and Planetary Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Trinity Western University; Western University","funders":"Natural Science Foundation of Guangdong Province; National Natural Science Foundation of China; Li Ka Shing Foundation","keywords":"Cave; Phylum; Genome; Metagenomics; Archaea; Phylogenetics; Extremophile; Gene; Biodiversity","score_opus":0.05960361819547653,"score_gpt":0.22325499889342929,"score_spread":0.16365138069795276,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416947312","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":[0.95905024,0.0016531196,0.00055878365,0.00009908532,0.0036451707,0.00032494983,0.01851763,0.000027338414,0.016123656],"genre_scores_gemma":[0.98824495,0.000038244947,0.0036069406,0.000047533766,0.000031977634,4.1018095e-7,0.0068630865,9.442494e-7,0.0011659366],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9986,0.00006926671,0.00022632733,0.0006404474,0.00024618022,0.00021777047],"domain_scores_gemma":[0.9987192,0.000053612323,0.00010965701,0.0010282557,0.00001414017,0.00007513749],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00043873553,0.00011069975,0.0001755388,0.00008277387,0.00027337426,0.00014509578,0.0010639548,0.00005397775,0.003829019],"category_scores_gemma":[0.000031588024,0.00010214977,0.0000424643,0.0004103765,0.00027136723,0.00052238797,0.00018543312,0.00006462326,0.0005510806],"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":[0.000034843015,0.000029148321,0.8461586,0.000013767042,0.000109770845,0.000005248564,0.00005568129,0.000056085544,0.00021550962,0.000015859667,0.004953036,0.14835243],"study_design_scores_gemma":[0.00054689514,0.000027327129,0.9027177,0.000030472993,0.0001673061,0.0000047806607,0.00059844647,0.0035034749,0.00093526737,0.0014700798,0.089783676,0.00021453637],"about_ca_topic_score_codex":0.0014441543,"about_ca_topic_score_gemma":0.0014747976,"teacher_disagreement_score":0.1481379,"about_ca_system_score_codex":0.0000139673775,"about_ca_system_score_gemma":0.00008838153,"threshold_uncertainty_score":0.99708164},"labels":[],"label_agreement":null},{"id":"W4416947530","doi":"10.1038/s41597-025-06194-z","title":"A Unified Cellular Toxic Potency Dataset of PM2.5 across Chemicals, Emission Sources, and Regions in China","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Air Quality and Health Impacts","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Environment and Climate Change Canada","funders":"Fudan University; National Natural Science Foundation of China","keywords":"Human health; Risk assessment; Health risk; Resource (disambiguation); China; Particulates; Health risk assessment; Bioassay; Air quality index","score_opus":0.05077983788302821,"score_gpt":0.3439604614852171,"score_spread":0.2931806236021889,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416947530","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":[0.9742079,0.00048717594,0.0010163159,0.004439314,0.00029551794,0.0003475523,0.017968968,0.000024898583,0.0012123793],"genre_scores_gemma":[0.9718167,0.000103769366,0.0021797884,0.00067187956,0.000017806045,0.0000047868944,0.019249942,0.0000095264795,0.00594576],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99829876,0.000075780605,0.00035538062,0.000642973,0.00027390092,0.00035317836],"domain_scores_gemma":[0.99808127,0.0000466338,0.000103158636,0.0016041276,0.0000043402197,0.00016046302],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002133618,0.000097718425,0.00016071842,0.000053532283,0.00029551698,0.00007616437,0.0009962136,0.000075819145,0.00024106371],"category_scores_gemma":[0.00033862918,0.00008599789,0.000011613219,0.0007344016,0.00069373875,0.00039629993,0.0019653903,0.00015669852,0.000035563182],"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":[0.000036067177,0.00028153646,0.007744958,0.00022915442,0.0000047808235,0.000007523527,0.00169426,0.000035901598,0.057152193,0.00022963047,0.91837955,0.014204442],"study_design_scores_gemma":[0.0009030779,0.000036617952,0.06500984,0.000362795,0.000019699155,0.000004617817,0.0009783306,0.005742984,0.022223497,0.004681267,0.89972574,0.00031155313],"about_ca_topic_score_codex":0.0012010307,"about_ca_topic_score_gemma":0.0004973743,"teacher_disagreement_score":0.05726488,"about_ca_system_score_codex":0.000049438317,"about_ca_system_score_gemma":0.00005987882,"threshold_uncertainty_score":0.35068923},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W4417263449","doi":"10.1038/s41597-025-06289-7","title":"The Ouranos CRCM5-CMIP6 ensemble: A dynamically downscaled ensemble of CMIP6 simulations over North America","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Climate variability and models","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Ouranos","funders":"Alliance de recherche numérique du Canada; Environment and Climate Change Canada; Innovation, Science and Economic Development Canada; Université du Québec à Montréal","keywords":"Downscaling; Coupled model intercomparison project; Climate model; Grid; General Circulation Model; Climate change; Component (thermodynamics); Climate simulation","score_opus":0.02206600415558369,"score_gpt":0.27750294221030913,"score_spread":0.25543693805472545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417263449","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":[0.94525236,0.00005743394,0.02794212,0.002108643,0.0015045867,0.0009061397,0.00601345,0.00009105453,0.016124226],"genre_scores_gemma":[0.99168617,0.000015399582,0.0011059706,0.00015818673,0.000011316509,0.000009377983,0.0012170305,0.000008168713,0.005788369],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977132,0.00011232123,0.00044485918,0.0008187042,0.0005170193,0.00039388041],"domain_scores_gemma":[0.9963077,0.0005167986,0.00013570696,0.0029115886,0.000035971945,0.00009227048],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008046505,0.00014853338,0.00019163481,0.000060153456,0.00076048874,0.00022719985,0.0018231127,0.000056586745,0.0008623063],"category_scores_gemma":[0.00053584354,0.00010940434,0.00006543607,0.001170407,0.001143589,0.00039316062,0.0018816089,0.00014509514,0.00022411723],"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":[0.0002918656,0.0018863914,0.07855688,0.00016147943,0.00021245492,0.000009477591,0.0020537833,0.10192171,0.20033847,0.0036266418,0.4528233,0.15811753],"study_design_scores_gemma":[0.0006597075,0.000036978694,0.045317102,0.000044423683,0.00010798974,0.000001342539,0.00016346663,0.62277097,0.00079755863,0.007417983,0.32234293,0.0003395227],"about_ca_topic_score_codex":0.0004247541,"about_ca_topic_score_gemma":0.0062551093,"teacher_disagreement_score":0.5208493,"about_ca_system_score_codex":0.000086220156,"about_ca_system_score_gemma":0.00008426973,"threshold_uncertainty_score":0.94416493},"labels":[],"label_agreement":null},{"id":"W4417264405","doi":"10.1038/s41597-025-06403-9","title":"Near complete T2T genome assembly of the banded goonch (Bagarius rutilus)","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ministry of Agriculture","funders":"","keywords":"Synteny; Sequence assembly; Genome; Clade; Gene; Reference genome; Nanopore sequencing; Genome size; Structural variation","score_opus":0.03447199554767675,"score_gpt":0.2710889516429916,"score_spread":0.23661695609531488,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417264405","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":[0.98298836,0.0025243242,0.00038138026,0.0005492454,0.0018187105,0.00029420308,0.0034729668,0.0000037934585,0.007966997],"genre_scores_gemma":[0.9930291,0.00003869027,0.00056895963,0.00014829007,0.000046126195,0.000004198987,0.00077270897,0.0000069547164,0.0053849253],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99887013,0.000046020632,0.00020370018,0.0005308383,0.00014120681,0.00020808337],"domain_scores_gemma":[0.99760306,0.00001271688,0.00007924752,0.002179778,0.00009464722,0.000030532126],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004801765,0.00010540809,0.0001306558,0.000027073735,0.0003370711,0.000096940945,0.001547488,0.000053986194,0.000018010456],"category_scores_gemma":[0.00010244267,0.00007863214,0.00005909582,0.00024267912,0.00043683013,0.0000012199969,0.0021659045,0.00005415536,0.000010125042],"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":[0.000011542119,0.000034124107,0.0011217478,0.000018561428,0.00008200218,2.455589e-7,0.000037974307,0.00004424145,0.96518105,0.00026125798,0.032113507,0.0010937437],"study_design_scores_gemma":[0.00032063204,0.000027281665,0.038072444,0.00001224039,0.00004599611,0.0000018199183,0.000057334433,0.00042365855,0.06198533,0.00025225096,0.89867294,0.00012810015],"about_ca_topic_score_codex":0.00003254694,"about_ca_topic_score_gemma":0.0001258588,"teacher_disagreement_score":0.90319574,"about_ca_system_score_codex":0.0000068477125,"about_ca_system_score_gemma":0.00019868955,"threshold_uncertainty_score":0.32065254},"labels":[],"label_agreement":null},{"id":"W4417423520","doi":"10.1038/s41597-025-06375-w","title":"A global dataset of helium isotopic data in tectonically and hydrothermally active geological environments","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Geological and Geochemical Analysis","field":"Earth and Planetary Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"Chinese Academy of Sciences Key Project; National Natural Science Foundation of China","keywords":"Helium; Hydrothermal circulation; Mantle (geology); Isotope; Resource (disambiguation); Range (aeronautics)","score_opus":0.025556245052968756,"score_gpt":0.2548514132141965,"score_spread":0.22929516816122777,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417423520","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":[0.9000167,0.0005766008,0.00018127455,0.00083656644,0.00014560371,0.00017761515,0.09560644,0.000009875004,0.0024492755],"genre_scores_gemma":[0.93734884,0.000038342125,0.00093796605,0.00019529912,0.0000088145025,5.750424e-7,0.06127117,4.8785546e-7,0.00019853114],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9981702,0.000083516024,0.00029748408,0.0009398548,0.0002466007,0.00026234228],"domain_scores_gemma":[0.997975,0.00010955975,0.00006685127,0.0017584873,0.000007992049,0.00008209205],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007503451,0.00010802374,0.00021907156,0.000059510367,0.00008286314,0.00006345611,0.0022094173,0.000065911525,0.002941095],"category_scores_gemma":[0.00030902898,0.00007468596,0.000015306085,0.0005588186,0.00066250557,0.00031521937,0.0014004464,0.000101994556,0.00006924473],"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":[0.000066048284,0.00013121146,0.95120317,0.000021396112,0.00004121122,0.000016258027,0.000008164819,0.00011986713,0.00037550027,0.000075026524,0.0066249324,0.041317225],"study_design_scores_gemma":[0.00027383183,0.000028050186,0.93349177,0.000015903846,0.00003582695,0.000002436489,0.000031037715,0.020472312,0.00008255304,0.006034758,0.039422892,0.00010863153],"about_ca_topic_score_codex":0.002451227,"about_ca_topic_score_gemma":0.012957823,"teacher_disagreement_score":0.04120859,"about_ca_system_score_codex":0.0000033899496,"about_ca_system_score_gemma":0.000044475415,"threshold_uncertainty_score":0.99797034},"labels":[],"label_agreement":null},{"id":"W4417455182","doi":"10.1038/s41597-025-06365-y","title":"An Egocentric Life-Saving Interventional Procedure Dataset of Actions, Medical Questions, Maneuvers and Tools","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"U.S. Army Research Institute of Environmental Medicine; U.S. Army Medical Research and Development Command; Purdue University; School of Medicine, Indiana University; U.S. Department of Defense; National Science Foundation","keywords":"CLIPS; Action (physics); Resource (disambiguation); Object (grammar); Field (mathematics); Metadata","score_opus":0.04955760178494154,"score_gpt":0.3772135807482431,"score_spread":0.32765597896330156,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417455182","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":[0.16725059,0.0011322503,0.7900633,0.015672147,0.0026330273,0.0010359032,0.021144012,0.0005258997,0.0005428425],"genre_scores_gemma":[0.94452786,0.000015574997,0.038796443,0.0002059468,0.00003591373,0.000023548217,0.016180307,0.0000057114503,0.00020871096],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99803823,0.00011717976,0.00034923502,0.0008361574,0.0004830352,0.00017614014],"domain_scores_gemma":[0.99708706,0.00015574136,0.00013036416,0.0023576315,0.00009306795,0.00017612113],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016230427,0.00009611359,0.00011993031,0.00030261747,0.00038005816,0.0006456452,0.0032262176,0.00005754856,0.000097942764],"category_scores_gemma":[0.0016420743,0.00009315918,0.000019630796,0.0009911532,0.00024239747,0.0017359395,0.0017181517,0.00021349791,0.000027127673],"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":[0.000014913522,0.0013280631,0.029798426,0.00041113357,0.00009710309,0.000008707041,0.0002557801,0.00019914517,0.0014064136,0.17437224,0.45244867,0.3396594],"study_design_scores_gemma":[0.00054308015,0.000040498944,0.21843494,0.00028990392,0.000042110376,0.00003129369,0.00014289319,0.65146565,0.00011878681,0.0026996823,0.12592047,0.00027068824],"about_ca_topic_score_codex":0.00019234988,"about_ca_topic_score_gemma":0.00011543911,"teacher_disagreement_score":0.77727723,"about_ca_system_score_codex":0.000026781125,"about_ca_system_score_gemma":0.00045784176,"threshold_uncertainty_score":0.62259716},"labels":[],"label_agreement":null},{"id":"W4417456164","doi":"10.1038/s41597-025-06429-z","title":"Global Ensemble Fire Emission Product Version 1.0 (EnsemFire V1.0)","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Atmospheric chemistry and aerosols","field":"Earth and Planetary 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":"Environment and Climate Change Canada","funders":"NOAA Weather Program Office; National Oceanic and Atmospheric Administration; U.S. Department of Commerce; U.S. Environmental Protection Agency","keywords":"Greenhouse gas; Particulates; Methane; Biomass burning; Air quality index; Aerosol; Carbon dioxide; Carbon fibers; Radiative transfer","score_opus":0.020977967436498504,"score_gpt":0.25195727652020417,"score_spread":0.23097930908370568,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417456164","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":[0.91594344,0.0024401718,0.0002587169,0.0017658946,0.0053589917,0.0002999937,0.0061905007,0.00018118988,0.0675611],"genre_scores_gemma":[0.9486048,0.00001963812,0.0011849308,0.00012193198,0.000115137744,3.7933358e-7,0.009827841,0.0000017050214,0.040123608],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982305,0.00003220105,0.00018188053,0.0009002701,0.00033065912,0.00032445003],"domain_scores_gemma":[0.99815744,0.00003721727,0.000055861983,0.001578555,0.000045816498,0.00012510123],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005247768,0.00013313587,0.00012648907,0.0000062001996,0.0006347957,0.0003035429,0.0012666346,0.00005547571,0.0020094265],"category_scores_gemma":[0.0002149833,0.00010902914,0.000032335487,0.00089326716,0.00021057925,0.00044306467,0.00024688028,0.000088731445,0.00054339203],"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":[0.000029654855,0.000025963147,0.0544426,0.000045442554,0.000009915123,0.000012597889,0.000020406605,0.000107100896,0.0012944362,0.000008294589,0.83289534,0.11110822],"study_design_scores_gemma":[0.0003374036,0.000018078468,0.049430054,0.00014770204,0.000034603847,0.0000147255205,0.00020615892,0.015021503,0.0055819084,0.0007961511,0.9281196,0.00029211753],"about_ca_topic_score_codex":0.00033172985,"about_ca_topic_score_gemma":0.00018961806,"teacher_disagreement_score":0.110816106,"about_ca_system_score_codex":0.000010090123,"about_ca_system_score_gemma":0.00022872868,"threshold_uncertainty_score":0.99890286},"labels":[],"label_agreement":null},{"id":"W4417502311","doi":"10.1038/s41597-025-06349-y","title":"A comprehensive dataset of riverine levee overtopping events for advancing risk assessment","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Dam Engineering and Safety","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"United Nations University Institute for Water, Environment, and Health","funders":"U.S. Army Corps of Engineers; U.S. Department of Defense","keywords":"Levee; Flood myth; Risk assessment; Consistency (knowledge bases); Hydrology (agriculture); Foundation (evidence); Flood control","score_opus":0.02816973448253714,"score_gpt":0.3182483642074622,"score_spread":0.2900786297249251,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417502311","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":[0.030777516,0.0005142961,0.7802961,0.00011826458,0.005404123,0.0005811315,0.18148763,0.00025415406,0.0005668162],"genre_scores_gemma":[0.7064613,0.00019243763,0.15988865,0.00010689742,0.0001378982,0.000067335495,0.13170649,0.00007991891,0.0013590747],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988519,0.000016852437,0.0003025666,0.00038947022,0.00017267145,0.00026653105],"domain_scores_gemma":[0.99813837,0.00016555758,0.000048086436,0.0015286596,0.00006919101,0.00005014388],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004951993,0.00012949192,0.00020563437,0.00015854492,0.00012514074,0.000048378533,0.00079569756,0.0000326568,0.000017496002],"category_scores_gemma":[0.00014778021,0.00013367951,0.00003473325,0.0003454167,0.000046911024,0.000324043,0.00046291304,0.000112140624,0.0000066454922],"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":[0.0000143391935,0.00006286716,0.0005753639,0.0010479416,0.00023293827,0.0000020548102,0.000055278677,0.14513566,0.022605522,0.00057013705,0.80369985,0.025998026],"study_design_scores_gemma":[0.00039406508,0.000008402243,0.0037238193,0.00011614002,0.000034981862,6.0900885e-7,0.000037489335,0.41750887,0.00075604836,0.00023470334,0.5770657,0.00011916872],"about_ca_topic_score_codex":0.000020543883,"about_ca_topic_score_gemma":0.000019810941,"teacher_disagreement_score":0.6756838,"about_ca_system_score_codex":0.00005641155,"about_ca_system_score_gemma":0.000052628377,"threshold_uncertainty_score":0.54512924},"labels":[],"label_agreement":null},{"id":"W4417524405","doi":"10.1038/s41597-025-06447-x","title":"De novo assembly of complete circular mitochondrial genomes from 2,695 fungal species","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Genomics and Phylogenetic Studies","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":"European Regional Development Fund; Ministère de l'Enseignement Supérieur, de la Recherche, de la Science et de la Technologie; Agence Nationale de la Recherche; Austrian Science Fund; European Commission","keywords":"Phylum; Genome; Phylogenetic tree; Mitochondrial DNA; Phylogenetics; Sequence assembly; Fungal Diversity; Whole genome sequencing; Taxonomic rank","score_opus":0.03950466578097342,"score_gpt":0.26856863300109435,"score_spread":0.22906396722012093,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417524405","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":[0.97504455,0.0061798543,0.0020110686,0.00016158266,0.0019153835,0.00018304055,0.0104124015,0.0000044513104,0.004087694],"genre_scores_gemma":[0.98522687,0.00012658237,0.0042308713,0.00010036244,0.00034758772,0.0000064767096,0.003934366,0.000012090828,0.0060147843],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987183,0.000042840293,0.0002246873,0.000636856,0.0001416124,0.00023569565],"domain_scores_gemma":[0.9981945,0.000023460208,0.00007287736,0.0015692741,0.00009423747,0.00004561157],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026036723,0.00012135848,0.0001742925,0.000058252932,0.00016403774,0.000107156346,0.001080039,0.0000683149,0.00006946701],"category_scores_gemma":[0.00011077946,0.00011957002,0.000063409934,0.00015129022,0.0002922138,0.0000018372966,0.001174741,0.000048461872,0.00001845772],"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":[0.000027294891,0.000036222067,0.0024607624,0.000013950412,0.00013520461,0.0000017065765,0.000038397757,0.000017319066,0.9647213,0.00015040788,0.031258576,0.0011388549],"study_design_scores_gemma":[0.00043541528,0.00003719788,0.01713619,0.000014028046,0.00006190309,0.0000020687296,0.00012238091,0.00013872437,0.17126359,0.00039256012,0.8102405,0.00015540555],"about_ca_topic_score_codex":0.00004683778,"about_ca_topic_score_gemma":0.000096736454,"teacher_disagreement_score":0.7934577,"about_ca_system_score_codex":0.000010691288,"about_ca_system_score_gemma":0.00019270377,"threshold_uncertainty_score":0.48759237},"labels":[],"label_agreement":null},{"id":"W7116384933","doi":"10.1038/s41597-025-06021-5","title":"Responsible AI measures dataset for ethics evaluation of AI systems","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Ethics and Social Impacts of AI","field":"Social Sciences","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":"Google (Canada); McGill University","funders":"","keywords":"Normative; Usability; Set (abstract data type); Interpretation (philosophy); Domain (mathematical analysis); Visualization; Corporate governance","score_opus":0.5162686606936119,"score_gpt":0.5809189398766879,"score_spread":0.06465027918307598,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7116384933","genre_codex":"dataset","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":[0.010683495,0.0072200745,0.024564665,0.3845416,0.05044474,0.009683341,0.45049298,0.00027181758,0.062097296],"genre_scores_gemma":[0.94450897,0.000113214744,0.0009343124,0.0027099254,0.0004096088,0.000065782275,0.03866918,0.00001892425,0.012570084],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99587035,0.0011671686,0.00030844615,0.0004868528,0.0018738813,0.00029328527],"domain_scores_gemma":[0.99439895,0.001058678,0.00012760577,0.0014663546,0.00286325,0.00008515205],"candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.072494954,0.00007543205,0.00016396937,0.00018860195,0.0017096393,0.0010486898,0.001588738,0.00022510729,0.000034744142],"category_scores_gemma":[0.038626894,0.00007347399,0.000033212462,0.00079882686,0.0009817804,0.0010138283,0.00032361769,0.0003349465,0.000012151115],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018298528,0.000042207714,0.000054534405,0.000064010375,0.000027454593,1.0576397e-7,0.0036272043,0.000047320238,0.0004515368,0.1988253,0.7948469,0.0019951435],"study_design_scores_gemma":[0.00026124032,0.000011991242,0.00008505619,0.000111115085,0.0001110766,4.0825647e-8,0.003716335,0.0029636354,0.00024063574,0.0705267,0.9218832,0.00008892702],"about_ca_topic_score_codex":0.0033238584,"about_ca_topic_score_gemma":0.013060572,"teacher_disagreement_score":0.9338255,"about_ca_system_score_codex":0.0000973162,"about_ca_system_score_gemma":0.008238133,"threshold_uncertainty_score":0.9999883},"labels":[],"label_agreement":null},{"id":"W7117106493","doi":"10.1038/s41597-025-06301-0","title":"National human footprint maps for Peru and Ecuador","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Environmental Impact and Sustainability","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Northern British Columbia","funders":"","keywords":"Biodiversity; Land cover; Footprint; Ecological footprint; Population; Land use; Population pressure; Sustainable development","score_opus":0.035932136756059996,"score_gpt":0.32784292886499244,"score_spread":0.29191079210893245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117106493","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":[0.97097766,0.000046461697,0.00054167485,0.000907059,0.00039819934,0.0006081333,0.0015281856,0.000033575736,0.024959022],"genre_scores_gemma":[0.9773007,0.0000011793248,0.0017087235,0.00012571982,0.000014143755,0.000018156437,0.00089085614,0.000004335591,0.019936174],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988133,0.000019988272,0.00013123,0.0005808036,0.0002487452,0.0002059571],"domain_scores_gemma":[0.9991598,0.000034282675,0.000025996442,0.0007071472,0.0000074329487,0.00006534183],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011160262,0.000078382036,0.00007081252,0.000037561153,0.00049729506,0.00016677011,0.0005814605,0.000029924278,0.00040335287],"category_scores_gemma":[0.00016957533,0.000071248476,0.000020206371,0.00015721616,0.0006554683,0.00024666305,0.0014858247,0.000049579096,0.000046289406],"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":[0.000045745575,0.00064112566,0.20749663,0.000156115,0.000039880004,0.0000038994717,0.00054619653,0.00011393532,0.038923007,0.009297628,0.6505877,0.09214818],"study_design_scores_gemma":[0.0005768048,0.00003693657,0.45110184,0.000011407945,0.00002021799,0.0000018427315,0.0005225091,0.0015858638,0.002925095,0.052550647,0.49044067,0.00022618595],"about_ca_topic_score_codex":0.00006059072,"about_ca_topic_score_gemma":0.00017204357,"teacher_disagreement_score":0.2436052,"about_ca_system_score_codex":0.00016481552,"about_ca_system_score_gemma":0.000022999295,"threshold_uncertainty_score":0.44164312},"labels":[],"label_agreement":null},{"id":"W7117660909","doi":"10.1038/s41597-025-06463-x","title":"Features of interest from a multi-season satellite survey of baleen whales on the West Antarctic Peninsula","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Marine animal studies overview","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; University of New Brunswick","funders":"World Wildlife Fund","keywords":"Peninsula; Baleen; Satellite; Satellite imagery; Bay; Data processing","score_opus":0.15326359689348787,"score_gpt":0.31867899644264147,"score_spread":0.1654153995491536,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117660909","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":[0.9854462,0.0012215924,0.000021079428,0.00047461354,0.00050835824,0.00034621943,0.0056024245,0.000014204518,0.0063653192],"genre_scores_gemma":[0.9968248,0.00014366912,0.0003921062,0.000101411715,0.000006290634,0.0000034871314,0.0008598598,0.000005948076,0.001662414],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.998372,0.00021609884,0.00027313532,0.0006327465,0.00031101197,0.00019500904],"domain_scores_gemma":[0.99743146,0.00048427362,0.000146026,0.0018703251,0.000029213403,0.000038719903],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0015626635,0.00013201027,0.00021629552,0.000037002836,0.00020016059,0.000105612686,0.0021828678,0.00003191851,0.0014009478],"category_scores_gemma":[0.0009385122,0.00008753511,0.00003914682,0.00067896623,0.0011227588,0.0001725749,0.0037494495,0.00012275307,0.00018436338],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008192846,0.00031365408,0.8791527,0.000058400616,0.00007088848,0.0000024887902,0.00030653944,0.0000038018493,0.0047205747,0.0002789397,0.07334123,0.041668825],"study_design_scores_gemma":[0.00013659977,0.000020799016,0.9603863,0.00010906108,0.00002319692,1.9396283e-7,0.000105508836,0.00019422201,0.0015875873,0.00007011045,0.037290487,0.00007597011],"about_ca_topic_score_codex":0.048680857,"about_ca_topic_score_gemma":0.2036689,"teacher_disagreement_score":0.15498805,"about_ca_system_score_codex":0.000041685613,"about_ca_system_score_gemma":0.000027022857,"threshold_uncertainty_score":0.9995119},"labels":[],"label_agreement":null}]}