{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":591,"total_is_capped":false,"direct_labels_cover":48,"predictions_cover":591,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"93e5f7b86fa9","filters":{"venue":"Scientific Data"}},"results":[{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1084604384544312,"gpt":0.394378858073248,"spread":0.2859184196188168,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.005600492,0.0001940348,0.0002451416,0.0004769062,0.0009377874,0.001439758,0.01116972,0.00005771188,0.0001424637],"category_scores_gemma":[0.0004761938,0.000185929,0.00003199316,0.003804527,0.0001295335,0.001850088,0.006284131,0.0005169722,0.003042193],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001306413,"about_ca_system_score_gemma":0.001479707,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001757818,"about_ca_topic_score_gemma":0.002827747,"domain_scores_codex":[0.995101,0.0003357362,0.0004676923,0.002000083,0.000790122,0.00130542],"domain_scores_gemma":[0.991106,0.0001615558,0.0002402856,0.00810606,0.00007451415,0.0003115478],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000002172786,0.00002213878,0.0009818457,0.00006472769,0.000006191384,0.00001021691,0.0001496708,0.00002721395,0.00003158246,0.003108268,0.9066598,0.08893617],"study_design_scores_gemma":[0.0001377995,0.00005366227,0.001847208,0.00003510739,0.000002029203,0.0000102856,0.00002263191,0.1945719,0.00001323535,0.00240736,0.8007212,0.0001774829],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"dataset","genre_scores_codex":[0.03996133,0.005842596,0.3477876,0.3347527,0.05828557,0.005968166,0.188605,0.01430354,0.004493384],"genre_scores_gemma":[0.192336,0.0008353312,0.1521422,0.01372749,0.001564086,0.0002205124,0.6028111,0.0002574167,0.03610581],"genre_candidate":"dataset","genre_consensus":null,"teacher_disagreement_score":0.4142061,"threshold_uncertainty_score":0.9995968,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.3746125090311491,"gpt":0.4171929214087385,"spread":0.04258041237758942,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.01730626,0.0001662846,0.0002092513,0.0002907842,0.001401446,0.003643148,0.009571965,0.00001707841,0.00003227778],"category_scores_gemma":[0.01460732,0.00008661395,0.00002905372,0.000900101,0.0007178492,0.002864442,0.01420809,0.00006040803,0.00002422771],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000208022,"about_ca_system_score_gemma":0.00009439235,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002015696,"about_ca_topic_score_gemma":0.0000519922,"domain_scores_codex":[0.9950618,0.0001485618,0.0007867189,0.002082815,0.001399791,0.000520381],"domain_scores_gemma":[0.9863386,0.002616302,0.000419711,0.01020317,0.0002961953,0.0001260624],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001193782,0.00001285545,0.001454192,0.000006708324,0.00001042373,0.000001240039,0.0002939908,0.000001043953,0.01920833,0.0008636277,0.4967037,0.4814319],"study_design_scores_gemma":[0.001051576,0.00001632182,0.001679601,0.0001538734,0.00003412857,0.00002175737,0.003134538,0.1051636,0.005445844,0.01178277,0.8711683,0.0003477191],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1827933,0.002636875,0.7403448,0.01845552,0.02063818,0.001839564,0.03248518,0.0002301544,0.0005764322],"genre_scores_gemma":[0.985862,0.000006960131,0.01087435,0.0001936721,0.0001047792,0.000003032845,0.0008861596,0.00002236758,0.002046642],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8030688,"threshold_uncertainty_score":0.9998986,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.06542144998765222,"gpt":0.2774303750916456,"spread":0.2120089251039934,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002195716,0.00008903423,0.00008708836,0.000006675333,0.0009574164,0.0007717479,0.003147122,0.0000228452,0.00004409259],"category_scores_gemma":[0.0002943601,0.00004730801,0.000008131192,0.0002506366,0.0009211249,0.0007389096,0.003574482,0.00009719732,0.000106713],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009674654,"about_ca_system_score_gemma":0.00002964753,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004878303,"about_ca_topic_score_gemma":0.0002567317,"domain_scores_codex":[0.9985541,0.00004568349,0.0001881774,0.0007073788,0.0002892232,0.0002154711],"domain_scores_gemma":[0.9975013,0.0001308671,0.00008321764,0.002196118,0.000008294813,0.00008019803],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005190096,0.00001427268,0.00008432545,0.00001023495,0.000006457416,8.960929e-7,0.0001633913,0.0007950507,0.0002109323,0.0003015207,0.9689587,0.0294023],"study_design_scores_gemma":[0.0002250694,0.000002182798,0.00002502833,0.000002794233,0.00001648218,0.000002268132,0.00002436647,0.5181462,0.000005463345,0.0002606379,0.4812468,0.00004272599],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.004025842,0.002112384,0.2862313,0.06538685,0.001971076,0.003076497,0.6352821,0.0001503916,0.001763554],"genre_scores_gemma":[0.2001196,0.0003204198,0.0418321,0.004803195,0.0006004188,0.00008693576,0.7415663,0.00007066006,0.0106004],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.5173512,"threshold_uncertainty_score":0.7441983,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.058784412206377,"gpt":0.284479141665156,"spread":0.225694729458779,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004823611,0.00007365537,0.00008101165,0.00001462198,0.0004077612,0.0001274861,0.0005585848,0.00003682506,0.009027781],"category_scores_gemma":[0.00002080986,0.00007038742,0.00002499188,0.0001889683,0.001456845,0.0003567674,0.001152061,0.00002091423,0.0002458245],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008214095,"about_ca_system_score_gemma":0.000005589136,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001357109,"about_ca_topic_score_gemma":0.0004618835,"domain_scores_codex":[0.9989394,0.00001049033,0.0001239593,0.0005031853,0.0002161257,0.0002068537],"domain_scores_gemma":[0.9992213,0.00001000819,0.00004832226,0.0006323691,0.000008364755,0.00007958161],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00007240598,0.0002666385,0.8704814,0.00003092749,0.00002005038,7.081286e-7,0.0002400348,0.00001777064,0.03132131,0.0003805092,0.09437155,0.002796714],"study_design_scores_gemma":[0.002186083,0.0002413612,0.588865,0.00002320981,0.0001276072,0.00001541516,0.003728305,0.05394914,0.004720916,0.001814932,0.3435696,0.000758454],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9651699,0.00004390508,0.001060355,0.00006069854,0.0003068583,0.0001539486,0.03127531,0.00001551884,0.001913515],"genre_scores_gemma":[0.9968251,0.00001503128,0.0006109481,0.00004280735,0.00001395939,0.000002323314,0.002217636,0.000002101918,0.0002700692],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2816164,"threshold_uncertainty_score":0.9918781,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.06895880683861093,"gpt":0.3052505647130123,"spread":0.2362917578744014,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007486148,0.0001013733,0.0001098079,0.00001099468,0.0003528449,0.0001247279,0.0009429983,0.00002490657,0.0006077405],"category_scores_gemma":[0.0001585308,0.00006708467,0.00002394973,0.0001509975,0.0004833622,0.0002126553,0.003725741,0.00001964061,0.0002392404],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007428427,"about_ca_system_score_gemma":0.000008291741,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009519706,"about_ca_topic_score_gemma":0.007279411,"domain_scores_codex":[0.9985084,0.00002016085,0.0001646185,0.0007597659,0.0002544482,0.0002925906],"domain_scores_gemma":[0.9987961,0.00003096076,0.00005580083,0.001015214,0.000004247985,0.00009769206],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002312165,0.00005258288,0.07178781,0.000009741029,0.00001159506,0.000002109463,0.00001385928,2.623381e-7,0.002193069,0.000835143,0.6545734,0.2704973],"study_design_scores_gemma":[0.0004820457,0.0000421742,0.1276626,0.00001182675,0.00001237609,0.000002218432,0.000008629738,0.00002003495,0.00006568192,0.003543353,0.8680311,0.0001179299],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9337782,0.0003928357,0.001319575,0.003092902,0.003190281,0.001748657,0.01613598,0.0001581513,0.04018348],"genre_scores_gemma":[0.9867238,0.00003659841,0.003307825,0.0001453636,0.00026031,0.00003581378,0.0005360605,0.00001533671,0.00893887],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2703794,"threshold_uncertainty_score":0.6654332,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.3033096542645218,"gpt":0.4618213139414697,"spread":0.1585116596769479,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.007430441,0.0000817558,0.0001279815,0.0002199775,0.005654069,0.001704287,0.00283783,0.00002189329,0.000006730496],"category_scores_gemma":[0.02438075,0.0000802397,0.000009035674,0.0003037233,0.0006577767,0.001351071,0.002066996,0.0002648317,0.00001238298],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000400324,"about_ca_system_score_gemma":0.0001906722,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002939499,"about_ca_topic_score_gemma":0.002958644,"domain_scores_codex":[0.9972205,0.0004676699,0.0001449087,0.001325038,0.0004188575,0.0004230417],"domain_scores_gemma":[0.9943545,0.003880641,0.00007716699,0.001531623,0.00002441458,0.0001316838],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0005902349,0.001215204,0.09755458,0.0004355589,0.000009470301,0.00001129989,0.0131734,0.0001377662,0.006304896,0.003436552,0.7095942,0.1675368],"study_design_scores_gemma":[0.002301336,0.0009559512,0.05814977,0.0000790593,0.000005904104,0.000005695504,0.003439287,0.01258005,0.0002817797,0.004225035,0.9176087,0.0003673992],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8760987,0.0006835111,0.000202322,0.1082708,0.002282288,0.00436886,0.004110778,0.0000879451,0.003894792],"genre_scores_gemma":[0.9974062,0.0001545023,0.0002839955,0.0003131155,0.00008109813,0.00006178684,0.0003139378,0.0000163252,0.001369052],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2080145,"threshold_uncertainty_score":0.999332,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.08465940337462678,"gpt":0.2972874814971154,"spread":0.2126280781224886,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002337136,0.0001408451,0.0001325582,0.0001381859,0.0007699585,0.00022681,0.0008485333,0.00007307643,0.001511632],"category_scores_gemma":[0.0003844757,0.0001293417,0.00005407528,0.00100127,0.0006086259,0.0004167913,0.0005843412,0.0001003869,0.002369001],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001273695,"about_ca_system_score_gemma":0.00007108033,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003497401,"about_ca_topic_score_gemma":0.0006159175,"domain_scores_codex":[0.9976709,0.0000630031,0.0002536107,0.001079032,0.000455365,0.0004780889],"domain_scores_gemma":[0.9977878,0.0001986556,0.00006902524,0.001812245,0.00001856642,0.0001137636],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006577038,0.0004214646,0.000582324,0.00005421023,0.000011903,0.000004065941,0.0002238319,0.03402742,0.01714303,0.002208308,0.9399233,0.005334345],"study_design_scores_gemma":[0.0009363323,0.0001029879,0.003993369,0.00003657881,0.00003735864,0.000002061341,0.000141512,0.72266,0.0007375223,0.007594323,0.2634199,0.0003380718],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4947998,0.00002763654,0.0738288,0.02896175,0.02997977,0.01348486,0.291318,0.003419047,0.06418035],"genre_scores_gemma":[0.9230788,0.000003979293,0.01341757,0.0004859703,0.0001566279,0.0002753999,0.04925799,0.00004423481,0.01327942],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6886326,"threshold_uncertainty_score":0.9994011,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1079127095226008,"gpt":0.3747868602896041,"spread":0.2668741507670033,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001026105,0.00006129961,0.00006167914,0.00002781071,0.0004614379,0.00009089709,0.0007859019,0.00003843705,0.000009352568],"category_scores_gemma":[0.00006175422,0.0000446872,0.00002758409,0.00007593916,0.0008812596,0.000007296551,0.001297802,0.00005518748,0.000005155058],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003565205,"about_ca_system_score_gemma":0.00008989121,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000207356,"about_ca_topic_score_gemma":0.0002243618,"domain_scores_codex":[0.9991477,0.00002885975,0.0001463361,0.0003436797,0.0001259856,0.000207437],"domain_scores_gemma":[0.9984988,0.000009928855,0.00005723871,0.001252909,0.0001087634,0.00007237843],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00007261429,0.0001046968,0.002961515,0.00005924756,0.00009962804,3.957493e-7,0.0003423789,0.000002478016,0.5035619,0.0004072721,0.4819424,0.01044546],"study_design_scores_gemma":[0.002458186,0.0002639687,0.04917125,0.0001375967,0.0001807132,0.000007255309,0.0006555872,0.05764876,0.06385111,0.001888778,0.823218,0.0005187515],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9877251,0.002101774,0.002359853,0.0003746038,0.001262376,0.0008799248,0.004899387,0.000006586793,0.0003904025],"genre_scores_gemma":[0.9954665,0.000007783878,0.001401901,0.00004243516,0.0001903989,0.000006620783,0.001654387,0.000007988578,0.001221999],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4397108,"threshold_uncertainty_score":0.3549054,"prediction_status":"machine_predicted_unvalidated"},"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":"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01102404109151187,"gpt":0.2050639716969465,"spread":0.1940399306054346,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000591943,0.0001403017,0.0001412417,0.00002493185,0.0004418435,0.00006735733,0.0005538641,0.00005808804,0.001255416],"category_scores_gemma":[0.00001873302,0.0001276771,0.00001727444,0.0001154213,0.001086919,0.0004198123,0.003891431,0.000062671,0.004231803],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000190963,"about_ca_system_score_gemma":0.000003377731,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004261335,"about_ca_topic_score_gemma":0.0003161995,"domain_scores_codex":[0.9982145,0.00005962846,0.0001672582,0.0008893519,0.0003363679,0.0003328291],"domain_scores_gemma":[0.9988104,0.00001479881,0.00007627899,0.001021289,0.00000159165,0.0000756555],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00005984955,0.00008999251,0.9120167,0.000009799681,0.00002495529,0.00001322123,0.0001548409,0.00003890341,0.003569285,0.00005657278,0.07825549,0.005710395],"study_design_scores_gemma":[0.0003449432,0.00003625896,0.8942804,0.000005173582,0.00003348536,0.000005865954,0.00001831235,0.002990055,0.0001449704,0.0002938725,0.1016744,0.0001721975],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9946918,0.00002467337,0.0001293454,0.0003809076,0.001019086,0.0002392623,0.001703411,0.00003132131,0.001780159],"genre_scores_gemma":[0.9929016,0.00002455488,0.0001869565,0.0001223049,0.00003345637,0.000003300257,0.002610924,0.000006324856,0.004110554],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02341895,"threshold_uncertainty_score":0.9996576,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.0590641367720697,"gpt":0.3058474073492359,"spread":0.2467832705771662,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.000832086,0.00008652054,0.0001168723,0.00003139432,0.001609811,0.0005928107,0.002844292,0.00003946277,0.0002128035],"category_scores_gemma":[0.0008470828,0.00005585076,0.00004337438,0.0001571195,0.0008061797,0.0006906871,0.0003289637,0.00008040385,0.00003990757],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003623879,"about_ca_system_score_gemma":0.0001592947,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001284193,"about_ca_topic_score_gemma":0.03493645,"domain_scores_codex":[0.9988682,0.00005312631,0.0001729132,0.0004523381,0.0002336537,0.0002197227],"domain_scores_gemma":[0.9958192,0.0001243715,0.0001760013,0.003756423,0.00005607987,0.00006790127],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00009184222,0.00003483497,0.8690559,0.00006590968,0.00002561227,0.000002499129,0.00004399192,0.00006272725,0.001065979,0.0002144866,0.07363285,0.05570341],"study_design_scores_gemma":[0.0003293651,0.00001624362,0.9365037,0.00007380939,0.00003038754,0.00002861924,0.0001010733,0.004774453,0.000669819,0.0004216048,0.05693275,0.0001181559],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8138793,0.0001472166,0.00001431126,0.00069739,0.003999238,0.0003470089,0.1797361,0.00002401985,0.001155355],"genre_scores_gemma":[0.9905133,0.000006036882,0.004236239,0.00002102808,0.0000667341,0.000001268888,0.004412326,0.00000215826,0.0007408584],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.176634,"threshold_uncertainty_score":0.9996899,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1423463828689606,"gpt":0.3469814610188182,"spread":0.2046350781498576,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04595133,0.0001399891,0.0002112855,0.0002132811,0.001525177,0.002060755,0.004274282,0.00003792934,0.00001623727],"category_scores_gemma":[0.3108275,0.0001324092,0.0000140344,0.001319847,0.002403673,0.004385597,0.005526684,0.0001713256,0.000007350997],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001183759,"about_ca_system_score_gemma":0.0003268488,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001282189,"about_ca_topic_score_gemma":0.0004813072,"domain_scores_codex":[0.9916981,0.0003175534,0.0003218209,0.006628861,0.0006015148,0.0004321669],"domain_scores_gemma":[0.980438,0.008017742,0.0001496038,0.01095768,0.0002518007,0.0001851568],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0009550698,0.001402519,0.03802828,0.0001948047,0.000006193299,0.000002710221,0.001423122,0.002011527,0.6608348,0.04915056,0.2010748,0.0449156],"study_design_scores_gemma":[0.002000842,0.0003539762,0.1142181,0.00005487966,0.00001748294,0.00002283995,0.0006455712,0.2092962,0.06193011,0.06711411,0.5436053,0.0007405782],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.985036,0.00001339333,0.002085725,0.005758423,0.002693885,0.001260108,0.001488212,0.00009328441,0.001570948],"genre_scores_gemma":[0.9956545,6.985337e-7,0.00250692,0.001009734,0.000111871,0.00004510213,0.0001865978,0.00001257746,0.0004720448],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5989047,"threshold_uncertainty_score":0.9997747,"prediction_status":"machine_predicted_unvalidated"},"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":"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.0338103432655551,"gpt":0.316685081902095,"spread":0.2828747386365399,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006058047,0.0001145007,0.0001486892,0.00004774235,0.0003616654,0.000126299,0.001660411,0.00007568687,0.0003361716],"category_scores_gemma":[0.0001138604,0.0001123876,0.0000316016,0.0002302711,0.0002035915,0.0001541969,0.0007226968,0.000128051,0.00006555283],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002521244,"about_ca_system_score_gemma":0.00002880652,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001078957,"about_ca_topic_score_gemma":0.00001584874,"domain_scores_codex":[0.9984258,0.00001513795,0.0003184794,0.0007478725,0.0002723788,0.0002203715],"domain_scores_gemma":[0.996201,0.00002491402,0.0001683093,0.003404773,0.00009256523,0.0001084298],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000003272037,0.0000592708,0.0000544173,0.00003850667,0.000004027866,2.342962e-7,0.000030573,0.000002020926,0.877018,0.001662895,0.1196503,0.001476503],"study_design_scores_gemma":[0.0000547423,0.000009946832,0.000008662037,0.00003053007,0.000005845116,0.000001066065,0.000009653272,0.000249987,0.5564508,0.0009346473,0.4421516,0.00009250574],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5064597,0.0002175361,0.2687805,0.00184692,0.0005885308,0.002480518,0.02884113,0.001281253,0.1895039],"genre_scores_gemma":[0.8253529,0.000002067454,0.08990715,0.00004211338,0.0002039768,0.0003022744,0.005890697,0.00005088648,0.07824796],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3225014,"threshold_uncertainty_score":0.4583034,"prediction_status":"machine_predicted_unvalidated"},"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":"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1784396269167633,"gpt":0.2946546232915195,"spread":0.1162149963747562,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002020033,0.0001221417,0.0001414001,0.00001334187,0.0003730951,0.0002302103,0.002759824,0.00004258676,0.0003703336],"category_scores_gemma":[0.0003654689,0.0000784884,0.00001160277,0.0001785061,0.0007626168,0.000370933,0.005323387,0.00009181135,0.0001047344],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005528624,"about_ca_system_score_gemma":0.0001557141,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.2996491,"about_ca_topic_score_gemma":0.7394986,"domain_scores_codex":[0.997919,0.00009415684,0.0001992438,0.0009849817,0.0004748604,0.0003277339],"domain_scores_gemma":[0.9961951,0.0002235118,0.00006761497,0.00329718,0.00002127603,0.0001953312],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003528082,0.00005915961,0.003226515,0.00001192835,0.00001569132,0.000003592013,0.0005838881,0.001603786,0.0008410178,0.00004979647,0.9906765,0.002892869],"study_design_scores_gemma":[0.0003137011,0.00002677635,0.0008243298,0.000003451289,0.00002691441,0.000008334529,0.0003563746,0.2232056,0.00001597875,0.001818464,0.7732543,0.0001457607],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.916321,0.0001527219,0.001970247,0.009997201,0.001422343,0.001059776,0.06807809,0.00004859822,0.000949953],"genre_scores_gemma":[0.97872,0.000009213819,0.004124031,0.001131629,0.00006338502,0.00002095753,0.01462946,0.00001696787,0.001284332],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4398495,"threshold_uncertainty_score":0.7050146,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.2872569636919766,"gpt":0.3757555810503705,"spread":0.08849861735839387,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","open_science"],"consensus_categories":["scholarly_communication","open_science"],"category_scores_codex":[0.002147771,0.00007645638,0.00006558477,0.00003154868,0.0009497717,0.03837242,0.01526573,0.00001304801,0.000001967453],"category_scores_gemma":[0.006170863,0.00005060746,0.00002346914,0.0006003391,0.0002592145,0.04000018,0.01025894,0.00008066493,0.00007849642],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000011219,"about_ca_system_score_gemma":0.0001221455,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003639181,"about_ca_topic_score_gemma":0.000009160065,"domain_scores_codex":[0.9978414,0.00003923405,0.0002062888,0.0009667238,0.0006246713,0.0003216393],"domain_scores_gemma":[0.9943673,0.0004363721,0.0001152713,0.004846899,0.0001048473,0.0001293331],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0000182429,0.00002992879,0.0001968107,0.00003707585,0.0000348169,0.00001005414,0.0002488848,0.000007382684,0.0001887925,0.4258383,0.5179107,0.05547902],"study_design_scores_gemma":[0.00007565916,0.00002441888,0.0001751642,0.000003098945,0.000003187548,0.000001173154,0.00007910952,0.04619589,0.0002360177,0.0005813912,0.9525578,0.00006707858],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0005563246,0.0004394346,0.9210995,0.06060238,0.003790907,0.0009658859,0.002989911,0.0003062158,0.009249465],"genre_scores_gemma":[0.3362477,0.000683527,0.3351711,0.002322791,0.004216848,0.0004623708,0.02062322,0.000130461,0.300142],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5859284,"threshold_uncertainty_score":0.9977459,"prediction_status":"machine_predicted_unvalidated"},"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":"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Nutrition International","funders":"","keywords":"Environmental science; Work (physics); Product (mathematics); Computer science; Remote sensing; Meteorology; Geography; Engineering; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01738024928083664,"gpt":0.2687381877762346,"spread":0.251357938495398,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001470008,0.0001168507,0.0002188216,0.00002802186,0.0002250523,0.0001707683,0.001667309,0.0000427342,0.0004554468],"category_scores_gemma":[0.00012472,0.00008016959,0.00005210548,0.001109425,0.0003933559,0.0004842093,0.001330977,0.00004106362,0.0001393417],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004404216,"about_ca_system_score_gemma":0.00001698285,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002594437,"about_ca_topic_score_gemma":0.001522121,"domain_scores_codex":[0.9982765,0.00004904518,0.0002163597,0.0008035307,0.0004117935,0.0002427521],"domain_scores_gemma":[0.9965863,0.0001753572,0.0001459375,0.003015778,0.00000662916,0.00007004285],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.00001529204,0.00005951494,0.340115,0.00002574994,0.0001593317,0.000001242665,0.00008650283,0.0001192566,0.0001299163,0.00001266873,0.6315981,0.0276774],"study_design_scores_gemma":[0.0002884927,0.00004011199,0.4833711,0.00002181717,0.0007676762,0.000004528702,0.000163432,0.3564608,0.00003568302,0.00002601544,0.1586393,0.0001810465],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8871987,0.0002553989,0.00004862342,0.0002667935,0.0005906475,0.0006257305,0.1108992,0.00001328797,0.000101516],"genre_scores_gemma":[0.9786838,0.000005988511,0.0002712818,0.00004094448,0.00001203777,0.00001319977,0.01991089,0.000006237693,0.001055641],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4729588,"threshold_uncertainty_score":0.4986823,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.08039608286432703,"gpt":0.3263989378373338,"spread":0.2460028549730068,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0008677685,0.00009885571,0.000184093,0.00008755303,0.00136187,0.0001907545,0.001581307,0.00008140565,0.0004051741],"category_scores_gemma":[0.0002762745,0.00008069646,0.00002508053,0.00003537716,0.001837314,0.0003985989,0.0009135972,0.0001007976,0.00008487485],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004167295,"about_ca_system_score_gemma":0.00004937516,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003690922,"about_ca_topic_score_gemma":0.00008391684,"domain_scores_codex":[0.9990539,0.0000973687,0.0001990637,0.0003985531,0.00003719808,0.0002139208],"domain_scores_gemma":[0.9968587,0.00005538745,0.0001910799,0.002839446,0.00004500735,0.00001037493],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00005923555,0.00005129056,0.001706296,0.00001870064,0.00005496746,7.730594e-7,0.0002770536,1.216792e-8,0.9733546,0.0007245474,0.01641228,0.007340266],"study_design_scores_gemma":[0.0006681205,0.00006226732,0.03259525,0.0000374493,0.00001957261,0.00001245547,0.0002285719,0.000001358288,0.7778276,0.0001368141,0.1882828,0.0001278004],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9912811,0.003955258,0.00001842092,0.00009833983,0.0007884635,0.0001494361,0.003118836,0.00002536953,0.0005647884],"genre_scores_gemma":[0.9661128,0.00007619117,0.0001040605,0.00001032887,0.000009507888,0.000003316096,0.00194655,0.000008799429,0.03172846],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.195527,"threshold_uncertainty_score":0.9999382,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.09744670688283534,"gpt":0.2975397882923794,"spread":0.200093081409544,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000814366,0.00016235,0.0004029033,0.00004814952,0.0002627726,0.0002505286,0.0007585775,0.000107926,0.0001292999],"category_scores_gemma":[0.0001234395,0.000134939,0.0002096064,0.0002876117,0.0001290028,0.0000148172,0.001621076,0.0001416494,0.00001652053],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000002978461,"about_ca_system_score_gemma":0.0000269263,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006946477,"about_ca_topic_score_gemma":0.00007995674,"domain_scores_codex":[0.9982917,0.00007832288,0.0003415708,0.0007493508,0.0001913897,0.0003476941],"domain_scores_gemma":[0.9981415,0.00003235624,0.0001064942,0.001419929,0.00003598459,0.0002637648],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00006796868,0.0001929591,0.1051665,0.0003341782,0.09285961,0.00002331404,0.001852331,0.0001305502,0.03792099,0.002200532,0.7566428,0.002608263],"study_design_scores_gemma":[0.002361736,0.0003919054,0.05338264,0.00001877209,0.1207715,0.00002287096,0.001359581,0.05891204,0.005210497,0.001445679,0.7536708,0.002451958],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6045091,0.002240706,0.3466044,0.01253528,0.0003816391,0.0006594813,0.03252362,0.00006063031,0.0004852125],"genre_scores_gemma":[0.9861413,0.00001463816,0.0008297485,0.001030253,0.0001843992,0.000003808055,0.01102019,0.00001329538,0.0007624263],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3816322,"threshold_uncertainty_score":0.5502653,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.07080271622274797,"gpt":0.2205855732676975,"spread":0.1497828570449495,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004895484,0.00003529986,0.00003949469,0.0000120015,0.0004706651,0.0001237789,0.001376586,0.00001089999,0.0007107964],"category_scores_gemma":[0.000584378,0.0000158621,0.00002036219,0.000451153,0.0001877659,0.0001588129,0.0002846895,0.00005315402,0.0003224221],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000001454201,"about_ca_system_score_gemma":0.00001541146,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001324643,"about_ca_topic_score_gemma":0.0002650928,"domain_scores_codex":[0.9992411,0.00002599961,0.00009972144,0.0002043724,0.0003309956,0.00009787868],"domain_scores_gemma":[0.9994256,0.00008620717,0.00005420417,0.0003574938,0.00004165411,0.00003487295],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003585524,0.00001482638,0.3178138,0.000009486914,0.00002372421,9.114907e-7,0.0003354663,0.0004540198,0.00007828513,0.0001818519,0.6379153,0.04313654],"study_design_scores_gemma":[0.00008532237,0.00002823596,0.2687459,0.000004386558,0.000007122652,5.504597e-7,0.0005291628,0.03049988,0.00006719134,0.0003933522,0.6995972,0.0000416205],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8182402,0.002209546,0.0001709058,0.141781,0.01758986,0.0005570404,0.005183967,0.00006334813,0.01420412],"genre_scores_gemma":[0.9985577,0.00004637696,0.00003737046,0.000239374,0.00006957585,6.3745e-8,0.0007077493,4.408453e-7,0.0003412837],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1803176,"threshold_uncertainty_score":0.7782722,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03412224571584795,"gpt":0.2895140590700908,"spread":0.2553918133542428,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006435119,0.00006749765,0.0001275534,0.00002886984,0.0000416456,0.0000262633,0.0006956185,0.00004571206,0.00003988554],"category_scores_gemma":[0.0001655955,0.00005711973,0.00001874025,0.00007299357,0.000308805,0.000007000754,0.0004755792,0.00002782865,0.000008550849],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":8.4892e-7,"about_ca_system_score_gemma":0.00004449527,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001939433,"about_ca_topic_score_gemma":0.00002295609,"domain_scores_codex":[0.9990036,0.00004886777,0.0002787459,0.0003644309,0.0001926463,0.0001116929],"domain_scores_gemma":[0.9984038,0.00001875242,0.0001199625,0.001315117,0.00008951977,0.00005279282],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00004267266,0.0002919515,0.00196846,0.0004508678,0.00004714543,9.593235e-7,0.0000954501,0.0000195339,0.929823,0.00112735,0.03610871,0.03002391],"study_design_scores_gemma":[0.001641233,0.001330358,0.003561747,0.0001049038,0.0001180946,0.00002323712,0.004065963,0.007408432,0.6370715,0.000228144,0.343924,0.0005223138],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9899837,0.0003597979,0.001360525,0.00002931637,0.0005453425,0.00009607892,0.00237262,0.000006033377,0.00524659],"genre_scores_gemma":[0.9896334,0.000009084688,0.0004277851,0.00001876143,0.0000885105,0.000001853256,0.003038267,0.000004900464,0.006777407],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3078153,"threshold_uncertainty_score":0.2329275,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.06975029518787,"gpt":0.2912859466673489,"spread":0.2215356514794788,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008592359,0.00009101792,0.0001660207,0.00003892211,0.000195972,0.00006820965,0.001659836,0.00008297205,0.00538217],"category_scores_gemma":[0.0004478576,0.00007335242,0.00002422243,0.0008391227,0.0006370526,0.0003408633,0.0002321501,0.0001637004,0.0007131002],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":3.287324e-7,"about_ca_system_score_gemma":0.0001603611,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001111485,"about_ca_topic_score_gemma":0.001970656,"domain_scores_codex":[0.9984072,0.000135239,0.0001894121,0.0006613941,0.0002897885,0.0003169554],"domain_scores_gemma":[0.9984896,0.0000763773,0.00005657614,0.001107865,0.00006123266,0.0002084197],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00004636377,0.0000103648,0.9168624,0.00003652572,0.00001072129,0.00003619702,0.00004433123,0.0000216431,0.00001303701,0.00004002658,0.08189814,0.0009803061],"study_design_scores_gemma":[0.0004727971,0.0001307695,0.9506286,0.00002747324,0.0000286673,0.00006713653,0.0001991301,0.013788,0.0001415025,0.0003799875,0.03391569,0.000220206],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9515259,0.001753751,0.0000755804,0.003299765,0.001185799,0.0001704889,0.03174489,0.0000378755,0.01020598],"genre_scores_gemma":[0.9739671,0.00003054247,0.001343436,0.0002544782,0.00005814564,2.241818e-7,0.02417461,9.890761e-7,0.0001705073],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04798245,"threshold_uncertainty_score":0.995527,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01223721011083671,"gpt":0.2024199108008323,"spread":0.1901827006899956,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001567617,0.00004878968,0.00006517907,0.00008530446,0.00002688962,0.00003135518,0.0002454605,0.00001824804,0.00005534332],"category_scores_gemma":[0.00001546419,0.00003446959,0.000003910913,0.0000886362,0.00002157248,0.0002745495,0.0001379663,0.0000328455,0.000005472602],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005542135,"about_ca_system_score_gemma":0.00004589256,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.1664421,"about_ca_topic_score_gemma":0.7960443,"domain_scores_codex":[0.9994302,0.00001166669,0.0001129946,0.0001886401,0.0001212019,0.0001353134],"domain_scores_gemma":[0.9995367,0.00002028608,0.00001140044,0.0003825541,0.00001386148,0.0000351808],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00006241004,0.00002647624,0.01678396,0.0000527771,0.00004475539,0.000009750075,0.0001875976,0.0524685,0.4444806,0.00012687,0.4546972,0.0310591],"study_design_scores_gemma":[0.002146977,0.00002830268,0.05538793,0.0003745814,0.00005736355,0.000009441352,0.00003360592,0.3069733,0.5891148,0.0009096406,0.04406764,0.0008963305],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9957343,0.000255268,0.002563376,0.00006912276,0.0009477604,0.00004639293,0.0003456456,0.00003094357,0.00000719857],"genre_scores_gemma":[0.9990676,0.00004584838,0.0004146077,0.000007083755,0.00001664183,0.000001487411,0.0002932993,0.000007619953,0.0001457834],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6296023,"threshold_uncertainty_score":0.8391087,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1204121820045291,"gpt":0.4146772621389453,"spread":0.2942650801344162,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006636253,0.00009958267,0.0002146672,0.0002128906,0.0002097818,0.00006958163,0.0004592478,0.00002203882,0.0001375575],"category_scores_gemma":[0.0003181419,0.00006394649,0.00006332147,0.002014133,0.001206504,0.000180958,0.0005833392,0.00005225869,0.0000211217],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003384739,"about_ca_system_score_gemma":0.0002794897,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003035326,"about_ca_topic_score_gemma":0.001951527,"domain_scores_codex":[0.9983066,0.0001177275,0.0001989961,0.0005972374,0.0005280924,0.0002513429],"domain_scores_gemma":[0.9979023,0.00003726055,0.00007627226,0.001594807,0.000118452,0.0002709482],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002713927,0.0006989576,0.9674344,0.00003176713,0.01227683,0.00004985933,0.0002390919,0.000001153343,0.0002660778,0.0007929854,0.01694044,0.0009970496],"study_design_scores_gemma":[0.0006732364,0.00006244804,0.9911563,0.00005306654,0.003183305,8.038033e-7,0.00009306971,0.002071262,0.00006548896,0.0005036728,0.002072177,0.00006517221],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9861192,0.003094153,0.00001243649,0.001252416,0.00009395048,0.000744843,0.008287767,0.0000123255,0.0003828799],"genre_scores_gemma":[0.9980018,0.000004351312,0.0001912428,0.00005074128,0.00001719951,0.00001600288,0.00163036,0.000004874076,0.00008342235],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0237219,"threshold_uncertainty_score":0.4445413,"prediction_status":"machine_predicted_unvalidated"},"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":"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.06242883869439955,"gpt":0.2966238125018321,"spread":0.2341949738074325,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002526032,0.00008131743,0.00007368578,0.000005523828,0.0002894424,0.0001135549,0.0006727632,0.00002597335,0.0006241382],"category_scores_gemma":[0.0001627548,0.00005288933,0.00001406243,0.0001933227,0.0008750084,0.0002217309,0.000622015,0.00003006962,0.0004876209],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001900023,"about_ca_system_score_gemma":0.0000114898,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006542848,"about_ca_topic_score_gemma":0.0001650738,"domain_scores_codex":[0.9989036,0.00002028177,0.0001072157,0.0005813136,0.0001915113,0.0001961135],"domain_scores_gemma":[0.9992255,0.00004844909,0.00003546867,0.000600187,0.000003511421,0.00008687399],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001301936,0.0002010225,0.000439007,0.000003912695,0.00000755075,9.86166e-7,0.00005030301,0.000003888221,0.8586819,0.0002531623,0.1024117,0.03781638],"study_design_scores_gemma":[0.00481917,0.001647345,0.0747972,0.000138247,0.0001536927,0.00001326549,0.0003260453,0.09078153,0.1519088,0.06214247,0.6115918,0.001680483],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9927025,0.00001146403,0.0005828579,0.0005084319,0.0005467128,0.0002377375,0.003640476,0.00002866224,0.001741114],"genre_scores_gemma":[0.9953632,7.249446e-7,0.002807363,0.0002601747,0.0001664197,0.000006781784,0.001061228,0.000002690053,0.0003313964],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7067731,"threshold_uncertainty_score":0.6833875,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03338112897152191,"gpt":0.3065188368589979,"spread":0.273137707887476,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001997818,0.0001222437,0.0002126605,0.00002113571,0.00007001992,0.0001315895,0.0007388113,0.00005199597,0.0001710975],"category_scores_gemma":[0.0002208004,0.0001062763,0.00001142759,0.0007758165,0.0002844546,0.0003724291,0.0009233555,0.00007470919,0.00004420814],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005547071,"about_ca_system_score_gemma":0.00005485425,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003069475,"about_ca_topic_score_gemma":0.08831569,"domain_scores_codex":[0.9982469,0.0002176193,0.0002984123,0.0006671983,0.0003526628,0.0002172213],"domain_scores_gemma":[0.9983954,0.00009584705,0.0001074359,0.001223947,0.00001383364,0.000163554],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00007202366,0.0002427058,0.3730419,0.00003888691,0.00002665593,0.00002033389,0.0008560197,0.0002528025,0.06767581,0.0001289405,0.5526031,0.005040893],"study_design_scores_gemma":[0.002447924,0.00009931337,0.1728117,0.0002172643,0.00007231079,0.00002365683,0.001033729,0.0864889,0.004161637,0.002798893,0.7289426,0.0009020561],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9511624,0.00118888,0.001175364,0.00006154124,0.0006480654,0.0002691453,0.042764,0.00001874289,0.002711866],"genre_scores_gemma":[0.9087145,0.00005220207,0.0691432,0.00005804433,0.00001896976,0.000003034739,0.01975354,0.00001264383,0.002243916],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2002301,"threshold_uncertainty_score":0.9283202,"prediction_status":"machine_predicted_unvalidated"},"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":"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.06778257964544786,"gpt":0.3175512912259267,"spread":0.2497687115804789,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007467471,0.0001486507,0.0001273189,0.0001151408,0.0002285949,0.0004921216,0.001411761,0.00005579028,0.0002502996],"category_scores_gemma":[0.00007038857,0.0001486993,0.00003489778,0.0003152768,0.0002205444,0.0008729998,0.0002516859,0.00007852277,0.0001953406],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003000596,"about_ca_system_score_gemma":0.00002539893,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004852724,"about_ca_topic_score_gemma":0.00001978679,"domain_scores_codex":[0.9985033,0.00001412394,0.0001867501,0.0006112996,0.0002481764,0.0004363428],"domain_scores_gemma":[0.9977849,0.00005138927,0.00001453289,0.001895924,0.0001063573,0.0001468929],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00000912877,0.00003447969,0.0002564851,0.00003352092,0.00002532058,0.000003121481,0.0001481171,0.0002925597,0.8676183,0.00001430448,0.1106203,0.0209444],"study_design_scores_gemma":[0.0001708988,0.0001056219,0.0001728572,0.00003364006,0.00002450547,0.00000407113,0.00009185167,0.04038387,0.7964695,0.0001657447,0.1620188,0.0003586356],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6197525,0.0002606938,0.3448642,0.00003525199,0.0171582,0.001392439,0.01115476,0.001245216,0.004136751],"genre_scores_gemma":[0.9647332,0.000001434177,0.03147609,0.00001668272,0.001062673,0.00004441003,0.002321595,0.00005108262,0.00029281],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3449808,"threshold_uncertainty_score":0.6063782,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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)","retraction":null,"screen_n_in":null,"score":{"opus":0.07491076497867988,"gpt":0.2493241337972274,"spread":0.1744133688185475,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0007875249,0.000211738,0.0001661098,0.00004433107,0.0007382975,0.0009684731,0.008762768,0.00007389743,0.0001123989],"category_scores_gemma":[0.000132759,0.000139429,0.00002414424,0.0006140445,0.000198404,0.001341875,0.005033433,0.0001672569,0.000009308725],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002764338,"about_ca_system_score_gemma":0.0000799046,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004836921,"about_ca_topic_score_gemma":0.0009921989,"domain_scores_codex":[0.9976748,0.00009723365,0.000332378,0.001082418,0.0004640989,0.0003491294],"domain_scores_gemma":[0.9923994,0.0001970723,0.00007999819,0.007195039,0.00004017973,0.0000883004],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004205512,0.00003315346,0.0000462316,0.00002174485,0.0003536862,0.000008131302,0.0002148672,0.0690918,0.005046068,0.008212982,0.9011027,0.0158266],"study_design_scores_gemma":[0.0001114313,0.000004080705,0.00002155906,0.00001274473,0.00003997248,0.000001248464,0.00002781214,0.5020385,0.0001640493,0.0001011078,0.4973699,0.000107563],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003593938,0.006104938,0.900853,0.002651208,0.007230737,0.0003909737,0.07619137,0.001201364,0.001782427],"genre_scores_gemma":[0.5166982,0.001341827,0.01251843,0.000958526,0.002513215,0.00004642334,0.4646092,0.0001542944,0.001159869],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8883346,"threshold_uncertainty_score":0.9966003,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.07065568232724688,"gpt":0.2633220157493701,"spread":0.1926663334221232,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0005487386,0.0001397656,0.0001506746,0.00001256056,0.0006986864,0.0005108349,0.001184259,0.00003671434,0.01717996],"category_scores_gemma":[0.0001538754,0.00009824557,0.00003588375,0.0003998861,0.0001970527,0.000482262,0.0005580274,0.00009787664,0.003723868],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006053468,"about_ca_system_score_gemma":0.0001110688,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001005555,"about_ca_topic_score_gemma":0.05046273,"domain_scores_codex":[0.9979297,0.00004210648,0.0002360844,0.0008684818,0.0004543279,0.0004693275],"domain_scores_gemma":[0.9974014,0.00006979117,0.00004121444,0.002236337,0.0001055792,0.0001457209],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000006152465,0.00004223862,0.07355642,0.00001989542,0.00003751405,0.00006195655,0.0001271664,0.0002551177,0.0001574003,0.00001349586,0.8822046,0.04351803],"study_design_scores_gemma":[0.000139862,0.000008923392,0.0369873,0.00001351084,0.00002505495,0.00001174435,0.000491194,0.002479079,0.0003906121,0.0001712052,0.9591076,0.0001738722],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.4335415,0.009027042,0.001182764,0.01059852,0.01562415,0.000626448,0.5168164,0.0004315611,0.0121516],"genre_scores_gemma":[0.1419806,0.0002027588,0.003983026,0.00109772,0.0005063557,0.000002604179,0.8356646,0.00001768638,0.0165447],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.3188482,"threshold_uncertainty_score":0.9970518,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03944935008229553,"gpt":0.2532188669693745,"spread":0.213769516887079,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001115654,0.0001750211,0.0001886681,0.00001401566,0.0002582969,0.0002998528,0.002509543,0.00007842884,0.002679162],"category_scores_gemma":[0.0004295391,0.0001434838,0.00004821246,0.0008515135,0.0005065785,0.0005222948,0.001696794,0.0001310218,0.01109668],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001119768,"about_ca_system_score_gemma":0.00003232018,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001958235,"about_ca_topic_score_gemma":0.0001998911,"domain_scores_codex":[0.9970889,0.0001587556,0.0002342668,0.001337095,0.0007364902,0.0004445004],"domain_scores_gemma":[0.9976942,0.00005853544,0.00008052434,0.001824945,0.000005003798,0.0003368222],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002661294,0.00008551944,0.02391988,0.00001549033,0.000009207628,0.00005028541,0.00004894143,0.0001026932,0.005422365,0.00003398601,0.9498005,0.02048451],"study_design_scores_gemma":[0.0004180072,0.00009201654,0.01940157,0.00001046559,0.00002285694,0.000006706181,0.00001935522,0.1101354,0.000531168,0.000120838,0.8689462,0.0002954164],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9194199,0.0002940607,0.004150033,0.01963641,0.006078702,0.001710636,0.01627899,0.0009329962,0.03149822],"genre_scores_gemma":[0.9925739,3.961251e-7,0.002983108,0.001868522,0.0001037075,0.00001099304,0.002135642,0.00001235057,0.0003114054],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1100327,"threshold_uncertainty_score":0.9982325,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03882169248641047,"gpt":0.2928124533598392,"spread":0.2539907608734287,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000722917,0.0002243713,0.0002071775,0.0002301772,0.0001862412,0.0004482745,0.001783858,0.00008535301,0.00007277579],"category_scores_gemma":[0.0002026019,0.0002400365,0.00003168585,0.000691576,0.0001083641,0.0008575166,0.000618065,0.0001869392,0.00006186565],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002443987,"about_ca_system_score_gemma":0.0000611618,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002339481,"about_ca_topic_score_gemma":0.0003992779,"domain_scores_codex":[0.9979375,0.00001922875,0.0003039751,0.0008277175,0.0003110965,0.000600509],"domain_scores_gemma":[0.9973782,0.00006893624,0.00002923493,0.002300543,0.00004431911,0.0001787158],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003064818,0.0001170253,0.01600456,0.0002555088,0.0001955524,0.00002130932,0.0005060655,0.0003229222,0.5182766,0.00001879903,0.4221679,0.04208318],"study_design_scores_gemma":[0.001161498,0.0001015647,0.004918953,0.0002581094,0.0002253429,0.00001082233,0.0001111626,0.006730835,0.4758315,0.0004374632,0.5094115,0.0008012694],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6417698,0.00467227,0.05014115,0.0001290233,0.07245009,0.005282979,0.2218537,0.001706843,0.001994202],"genre_scores_gemma":[0.9455468,0.00001571841,0.03322173,0.000004734222,0.002340019,0.00008161691,0.01808181,0.00009536403,0.0006121938],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.303777,"threshold_uncertainty_score":0.9788403,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.05262219948600481,"gpt":0.3532226569827437,"spread":0.3006004574967389,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002964787,0.0002809815,0.0004998153,0.0006667773,0.0007570706,0.0005829641,0.0007464954,0.00007553247,0.000879719],"category_scores_gemma":[0.004979244,0.0002948231,0.000052214,0.002691974,0.0005575811,0.0003667702,0.002231657,0.0007769881,0.00009156294],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002384816,"about_ca_system_score_gemma":0.001129469,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001627985,"about_ca_topic_score_gemma":0.003229416,"domain_scores_codex":[0.9958919,0.0003430308,0.0004773385,0.001983162,0.0006819453,0.0006226687],"domain_scores_gemma":[0.9959301,0.0007690183,0.0001670667,0.002126795,0.00009861995,0.000908338],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001359589,0.0008058072,0.2259323,0.001396443,0.0001217777,0.002042016,0.0007568129,0.003468555,0.008265587,0.0001065272,0.7329492,0.02401906],"study_design_scores_gemma":[0.001933109,0.00004667562,0.001517817,0.0001169106,0.00009777024,0.0001981226,0.0003033114,0.04822017,0.0004129327,0.00005483657,0.9468126,0.0002857583],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"dataset","genre_scores_codex":[0.3245797,0.124897,0.07820524,0.2674153,0.01021564,0.0120296,0.1745121,0.005858352,0.002287145],"genre_scores_gemma":[0.4008922,0.0008687943,0.01085137,0.03487949,0.0002837188,0.00008073311,0.5497575,0.000154884,0.002231355],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.3752454,"threshold_uncertainty_score":0.9999504,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1633179462311934,"gpt":0.3183892448547478,"spread":0.1550712986235543,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0007703733,0.0001151758,0.00009302679,0.00001461067,0.0005841045,0.0004665077,0.001364071,0.00003814257,0.09820227],"category_scores_gemma":[0.0002049936,0.00008319599,0.00004086459,0.0005762659,0.0004504893,0.0004379178,0.0009690929,0.00009540295,0.001476564],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009792143,"about_ca_system_score_gemma":0.00004378825,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001167964,"about_ca_topic_score_gemma":0.002244806,"domain_scores_codex":[0.998287,0.00003156424,0.0001838085,0.0007316733,0.000381373,0.0003845975],"domain_scores_gemma":[0.9979277,0.00007162326,0.00005412386,0.001795743,0.00002347758,0.0001273305],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000007748596,0.00006885041,0.0001105423,0.000007999206,0.000009306857,0.00001111891,0.00006598049,0.000005521892,0.01333066,0.0006996522,0.9837472,0.00193537],"study_design_scores_gemma":[0.0002627981,0.000007047262,0.0069037,0.000007689567,0.00003000101,0.00002063388,0.001839855,0.0009898209,0.003583532,0.00004726565,0.9861785,0.0001292253],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.09880063,0.0002966201,0.002545455,0.02424484,0.007641576,0.001560773,0.8506601,0.0002563779,0.01399366],"genre_scores_gemma":[0.3347498,0.0000952956,0.002370357,0.001573691,0.0003594341,0.0001681043,0.5424934,0.00005891623,0.118131],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.3081667,"threshold_uncertainty_score":0.9993009,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03046131893085998,"gpt":0.2288782553762343,"spread":0.1984169364453743,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002920837,0.0001280365,0.0001765366,0.000004130512,0.0003370886,0.0001660634,0.0008230217,0.00006408383,0.002210029],"category_scores_gemma":[0.0001461458,0.0001101858,0.00002690121,0.0007059271,0.0003786304,0.0003501768,0.0002482316,0.00008322485,0.0001121575],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004661628,"about_ca_system_score_gemma":0.0001757529,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006656151,"about_ca_topic_score_gemma":0.0008482185,"domain_scores_codex":[0.9984907,0.0000353047,0.0002493711,0.0006371785,0.0003257917,0.0002616744],"domain_scores_gemma":[0.9988076,0.00004681241,0.0001111242,0.0007009308,0.00004143335,0.0002920862],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001148818,0.00009938488,0.5265353,0.0002165662,0.00007975799,0.0000184997,0.0003057123,0.0008433023,0.0822648,0.00005396484,0.3820438,0.007424003],"study_design_scores_gemma":[0.002626131,0.0003831475,0.4331753,0.0002101521,0.0002927352,0.00009672045,0.001097843,0.4168523,0.02683046,0.001439293,0.11539,0.001605903],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9812317,0.0007218271,0.0006525763,0.0007428744,0.000521371,0.0001125092,0.01495778,0.00005927741,0.001000082],"genre_scores_gemma":[0.9895688,0.00001817696,0.001515913,0.0000803412,0.00009535436,1.916053e-7,0.008426797,0.000002625167,0.0002917486],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.416009,"threshold_uncertainty_score":0.9987021,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.04358805088912733,"gpt":0.2293282728724539,"spread":0.1857402219833266,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001004211,0.0001689245,0.000279869,0.00004419457,0.0004471231,0.0004495018,0.001624796,0.0002276417,0.006716935],"category_scores_gemma":[0.0002282773,0.00008944605,0.00005245064,0.0002419721,0.0003307373,0.0007111586,0.0004747285,0.0004491379,0.004310185],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006363982,"about_ca_system_score_gemma":0.00009440271,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004570453,"about_ca_topic_score_gemma":0.009213779,"domain_scores_codex":[0.9980806,0.00008701625,0.0004240631,0.0004718339,0.0006333026,0.0003032035],"domain_scores_gemma":[0.9980979,0.0001499991,0.0002174085,0.001336108,0.0001399417,0.00005862316],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001786431,0.000006571717,0.002269139,0.00001699861,0.00002247649,3.669273e-7,0.0003493133,0.00003783475,0.00000408407,0.0000018986,0.991529,0.005744423],"study_design_scores_gemma":[0.00008792367,0.00003573372,0.01219513,0.00003771299,0.0000370954,0.000001564034,0.0005092022,0.0144491,0.00002720083,0.0002004264,0.9722807,0.000138219],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"editorial","genre_gemma":"dataset","genre_scores_codex":[0.01711057,0.003303378,0.0009859402,0.01473358,0.7545435,0.002463131,0.1317504,0.0002058008,0.07490363],"genre_scores_gemma":[0.04439354,0.0000879546,0.0002057782,0.0004135946,0.001307722,0.000003475802,0.8594835,0.000004690236,0.09409977],"genre_candidate":"dataset","genre_consensus":null,"teacher_disagreement_score":0.7532358,"threshold_uncertainty_score":0.9964651,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1245422815350868,"gpt":0.3377334745517816,"spread":0.2131911930166948,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004766634,0.00009154329,0.0001834062,0.00017905,0.0002094927,0.0001410929,0.001141824,0.00004148887,0.00001351613],"category_scores_gemma":[0.0008260574,0.00005917823,0.00002532005,0.004012215,0.0007641519,0.0003659681,0.001742207,0.000206013,0.0002168055],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001047769,"about_ca_system_score_gemma":0.00004255375,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003046883,"about_ca_topic_score_gemma":0.01062735,"domain_scores_codex":[0.9970888,0.0002879249,0.0003229746,0.0006524299,0.001234089,0.0004138002],"domain_scores_gemma":[0.9975327,0.0002473318,0.0001073028,0.001991744,0.00004786566,0.0000730648],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001868032,0.00006313789,0.002044372,0.0002496306,0.00003181273,0.0001841287,0.0109112,0.02195668,0.5287579,0.0001142444,0.2978081,0.137692],"study_design_scores_gemma":[0.001065938,0.0001574171,0.1452,0.001955454,0.00003400358,0.0000910727,0.009645891,0.2172985,0.1181647,0.0005356264,0.5051656,0.0006857265],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9960486,0.00001565117,0.0004576962,0.0003519766,0.0005033081,0.0005144236,0.001589056,0.00003752389,0.0004818022],"genre_scores_gemma":[0.9560963,0.000008480184,0.04128141,0.00001472415,0.00003607362,1.75755e-7,0.0007493601,0.00001576643,0.001797709],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4105933,"threshold_uncertainty_score":0.5930309,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.07157132679559527,"gpt":0.3255467582382028,"spread":0.2539754314426075,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001298944,0.0001749217,0.0001674072,0.0001544265,0.001141848,0.0005606381,0.00485297,0.00003067204,0.0003755217],"category_scores_gemma":[0.006708503,0.0001316695,0.00002183676,0.0008612495,0.0003929953,0.001014495,0.003750935,0.0002853571,0.0007068347],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000607375,"about_ca_system_score_gemma":0.00007491979,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003055413,"about_ca_topic_score_gemma":0.0001365285,"domain_scores_codex":[0.9963106,0.0002281683,0.0002363969,0.002226536,0.0005383971,0.0004598901],"domain_scores_gemma":[0.9923549,0.001530322,0.0001160724,0.005874605,0.00005960587,0.00006443864],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001433101,0.00001757725,0.0001438488,0.000005022405,0.000003903485,0.000002574616,0.00007366703,0.00001607723,0.7453235,0.002622827,0.2469592,0.00481747],"study_design_scores_gemma":[0.0004708203,0.000082311,0.02166698,0.00002937226,0.00002549151,0.00007621145,0.0003175306,0.01258813,0.04640349,0.00835125,0.9094416,0.0005468467],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9299638,0.0001082415,0.001572249,0.04615687,0.009952971,0.001307134,0.009639444,0.0002224416,0.001076879],"genre_scores_gemma":[0.9922671,0.000002791435,0.000372867,0.003050584,0.000535458,0.000005755731,0.001899574,0.00002306644,0.001842805],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.69892,"threshold_uncertainty_score":0.9085166,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.08310562985708746,"gpt":0.3268033104726912,"spread":0.2436976806156038,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.001910407,0.0002050428,0.0001500146,0.0002230397,0.001785238,0.0009234925,0.007659231,0.00002651435,0.0004072767],"category_scores_gemma":[0.01979549,0.0001428786,0.0000289797,0.002028197,0.002028255,0.001313598,0.008167167,0.000200563,0.0004268714],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002063134,"about_ca_system_score_gemma":0.0001100759,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005164012,"about_ca_topic_score_gemma":0.0007352685,"domain_scores_codex":[0.9955911,0.0002190338,0.000220674,0.002554372,0.0008789125,0.0005358778],"domain_scores_gemma":[0.9892965,0.001924976,0.00008616526,0.008440272,0.0001261223,0.0001259821],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001445477,0.00002403289,0.0002243707,0.000004057092,0.000005806804,0.000005815126,0.0002254168,0.000001381845,0.09719143,0.0008418206,0.8866815,0.01477989],"study_design_scores_gemma":[0.000161429,0.00003755917,0.005031057,0.00001400006,0.00001647126,0.00003652808,0.0002483779,0.003497532,0.008258999,0.003967979,0.9784939,0.0002361335],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.1873999,0.001236552,0.01269346,0.5400767,0.06472842,0.004507989,0.1690103,0.001538747,0.01880792],"genre_scores_gemma":[0.9689246,0.000004075144,0.002086278,0.02305997,0.0009544282,0.00001261871,0.001399886,0.00003510117,0.003522977],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7815248,"threshold_uncertainty_score":0.9998546,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1024925104869529,"gpt":0.3681364229874934,"spread":0.2656439125005406,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004499582,0.0001002298,0.0003116939,0.0001654897,0.00005519288,0.00002949841,0.0008714815,0.00007561027,0.00001784116],"category_scores_gemma":[0.001658432,0.0000874779,0.00002441885,0.000666482,0.0003243266,0.00001523898,0.001715575,0.00004701297,0.000003033261],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003191431,"about_ca_system_score_gemma":0.00006682237,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001444729,"about_ca_topic_score_gemma":0.0004009561,"domain_scores_codex":[0.9981838,0.000130586,0.0004599488,0.000737028,0.0002318826,0.0002567644],"domain_scores_gemma":[0.9973109,0.00005343437,0.0001822046,0.002333178,0.00007082042,0.00004940393],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00008082444,0.00006964961,0.006355702,0.00002972166,0.00007713801,0.000002024451,0.0000196852,0.000001441951,0.9850888,0.0009625435,0.005243624,0.002068878],"study_design_scores_gemma":[0.001642703,0.0000657178,0.8915656,0.00002217186,0.0001252902,0.000007285072,0.0001093184,0.002417956,0.02555885,0.0008202599,0.07741288,0.0002520136],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9816045,0.002656174,0.0006418456,0.000225941,0.0004040858,0.0002431436,0.01392712,0.00001052014,0.0002866973],"genre_scores_gemma":[0.9938854,0.0004694638,0.001177392,0.00001432188,0.00002728546,0.000004703944,0.004261666,0.000006863604,0.0001528842],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9595299,"threshold_uncertainty_score":0.3567245,"prediction_status":"machine_predicted_unvalidated"},"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":"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.08278359054886814,"gpt":0.3268148658449304,"spread":0.2440312752960623,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.007046425,0.0002122588,0.0004325382,0.000173397,0.001171226,0.002743698,0.005080384,0.0000730695,0.001316463],"category_scores_gemma":[0.005893897,0.0001760664,0.0000264463,0.0001306807,0.002276454,0.001188346,0.003334892,0.00008187009,0.0003261143],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001454268,"about_ca_system_score_gemma":0.0000900756,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008478404,"about_ca_topic_score_gemma":0.00004708383,"domain_scores_codex":[0.9968393,0.0002883668,0.0005175853,0.00126154,0.0006340147,0.000459137],"domain_scores_gemma":[0.9933129,0.000259565,0.00073392,0.005453164,0.00008859202,0.0001518389],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003957024,0.00002881023,0.0007509161,0.00007976012,0.000005062488,0.000005742706,0.00007747504,0.00001537471,0.9948184,0.0007272279,0.001825458,0.001626166],"study_design_scores_gemma":[0.0002514534,0.00002497015,0.01218139,0.0001119491,0.00004337912,0.00001803394,0.00005225513,0.002255737,0.9796073,0.001075042,0.004071803,0.0003066681],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9905173,0.00005663545,0.000326412,0.0005414702,0.002515672,0.0002290415,0.004778587,0.00007816018,0.0009566776],"genre_scores_gemma":[0.9699031,0.0000148819,0.02877776,0.00002903081,0.00003262085,0.00001170636,0.0001499411,0.00002008623,0.001060864],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02845135,"threshold_uncertainty_score":0.9995965,"prediction_status":"machine_predicted_unvalidated"},"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":"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.09751765212507633,"gpt":0.3243820928474974,"spread":0.226864440722421,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.01018687,0.000576744,0.000656724,0.0006403179,0.0008582388,0.004184117,0.437055,0.0007024728,0.0002074641],"category_scores_gemma":[0.2991443,0.0004153072,0.00008887408,0.002897731,0.003549698,0.004466407,0.6984959,0.001407882,0.001069407],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001183643,"about_ca_system_score_gemma":0.0015739,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001619092,"about_ca_topic_score_gemma":0.0001139992,"domain_scores_codex":[0.9884858,0.000353491,0.001004966,0.005339721,0.003846048,0.0009699343],"domain_scores_gemma":[0.6423253,0.006759586,0.001570303,0.3480873,0.001050536,0.0002069665],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000007611581,0.000163686,0.000001398265,0.00004864667,0.00005978165,0.0000107119,0.00003544877,8.339894e-7,0.0001107059,0.0003044914,0.9950036,0.004253059],"study_design_scores_gemma":[0.0001902651,0.00006799359,0.000001945183,0.0002533008,0.0000404007,0.000002761262,0.00001002791,0.03390707,0.0005182875,0.02078941,0.9437985,0.0004200451],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"editorial","genre_gemma":"methods","genre_scores_codex":[0.0001322098,0.0002558079,0.02089111,0.002243468,0.8603731,0.0008424941,0.1144169,0.0006534595,0.0001914503],"genre_scores_gemma":[0.0004000169,0.0004313019,0.4365906,0.0002452565,0.3263379,0.0001800781,0.2254982,0.0002388824,0.01007775],"genre_candidate":"editorial","genre_consensus":null,"teacher_disagreement_score":0.5340352,"threshold_uncertainty_score":0.9998299,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1006169606146817,"gpt":0.3922536860077259,"spread":0.2916367253930442,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.008393578,0.0006815785,0.0008828353,0.001169772,0.00196795,0.004105445,0.02308062,0.0005194693,0.0003604417],"category_scores_gemma":[0.001627732,0.0006899359,0.0001182696,0.004922405,0.00027874,0.002091074,0.01192761,0.004208623,0.003690867],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006983611,"about_ca_system_score_gemma":0.01001349,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.007049417,"about_ca_topic_score_gemma":0.02300481,"domain_scores_codex":[0.9884793,0.0009141797,0.00121419,0.005179976,0.001972671,0.002239664],"domain_scores_gemma":[0.9806623,0.0003029919,0.001210253,0.01692548,0.0002702893,0.0006287275],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000003683687,0.00004420385,0.00005363272,0.0003555808,0.0000307128,0.00002459141,0.0001349244,0.00001186949,6.380936e-7,0.0003374119,0.9290498,0.06995292],"study_design_scores_gemma":[0.0001170307,0.0001203689,0.0002195949,0.0004011539,0.00001504568,0.00003141311,0.00002488118,0.1603359,7.383119e-7,0.0006766887,0.8375406,0.0005165652],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"editorial","genre_gemma":"other","genre_scores_codex":[0.000005374162,0.004532326,0.04484897,0.04453927,0.7945916,0.001771039,0.1033055,0.002969892,0.003435991],"genre_scores_gemma":[0.00001727655,0.000230634,0.00602559,0.0009453981,0.00180988,0.0000638714,0.3704989,0.000112218,0.6202963],"genre_candidate":"editorial","genre_consensus":null,"teacher_disagreement_score":0.7927818,"threshold_uncertainty_score":0.9995627,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03377166860876531,"gpt":0.2755316290299293,"spread":0.241759960421164,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002757974,0.0001228641,0.0001108087,0.00008660104,0.0005880222,0.000933942,0.002176123,0.00004133602,0.0007129273],"category_scores_gemma":[0.0005385072,0.00007862087,0.00002757203,0.000350574,0.0003289074,0.0007580615,0.0001098683,0.0001326846,0.0003575521],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003069448,"about_ca_system_score_gemma":0.00007347699,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003219734,"about_ca_topic_score_gemma":0.002666263,"domain_scores_codex":[0.9981424,0.0001377717,0.0001768205,0.0007655025,0.0003848667,0.0003926949],"domain_scores_gemma":[0.9963494,0.0005045302,0.00006754408,0.002884576,0.00004858998,0.0001453842],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0005348952,0.0002604222,0.1724535,0.0003122155,0.00008777731,0.00002837417,0.0006964987,0.0009336401,0.00772232,0.0005627634,0.3762271,0.4401805],"study_design_scores_gemma":[0.0003098641,0.00009220311,0.5139965,0.00003616868,0.00004352862,0.00001823512,0.000194746,0.05202636,0.0001420164,0.0002376128,0.432682,0.0002207588],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9124986,0.0009028456,0.0007912801,0.001884659,0.006421709,0.001524866,0.07508899,0.0002891881,0.0005978813],"genre_scores_gemma":[0.9781736,0.000009615117,0.002691326,0.0001394471,0.0003144815,0.000004318157,0.01741828,0.000007526681,0.001241363],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4399598,"threshold_uncertainty_score":0.9006024,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.2473092512972187,"gpt":0.4295171565604403,"spread":0.1822079052632216,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001267522,0.0001005132,0.0001400109,0.00003589362,0.0006749462,0.0001844863,0.00137491,0.00003520173,0.00004030271],"category_scores_gemma":[0.002973639,0.00006570567,0.00003528221,0.0003007924,0.0005612801,0.000302567,0.0009650465,0.0001220863,0.00001295217],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006397534,"about_ca_system_score_gemma":0.0001312925,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007881589,"about_ca_topic_score_gemma":0.00006231725,"domain_scores_codex":[0.9980662,0.0002922432,0.0002642288,0.0008168192,0.0003044851,0.0002559728],"domain_scores_gemma":[0.9964652,0.001121804,0.0001448116,0.002106592,0.000120506,0.00004110069],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001999636,0.00003322263,6.181043e-7,0.00002166403,0.000003546843,0.00004817158,0.0008626437,0.00003294813,0.9360586,0.0006580873,0.05995823,0.002302214],"study_design_scores_gemma":[0.0008802984,0.00009664438,0.00001071572,0.00008031198,0.00005319115,0.0002501753,0.004513923,0.06786964,0.8238451,0.009164152,0.0929156,0.0003201784],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8620178,0.001909843,0.001298702,0.002064248,0.004318538,0.0007912776,0.1271446,0.00006103427,0.0003939027],"genre_scores_gemma":[0.9469437,0.00002041283,0.004825233,0.0009447853,0.0001141926,0.00001342403,0.04441571,0.00002013192,0.002702406],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1122135,"threshold_uncertainty_score":0.5191209,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1407024053130846,"gpt":0.3903484463825193,"spread":0.2496460410694347,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001334309,0.0001633872,0.0001922747,0.0002063009,0.0003778652,0.0006920759,0.003150927,0.00003074118,0.00001895533],"category_scores_gemma":[0.001282824,0.0001729697,0.00007717561,0.0009495871,0.000206053,0.001986033,0.002701846,0.0001445482,0.00006359562],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001142685,"about_ca_system_score_gemma":0.001153222,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005472239,"about_ca_topic_score_gemma":0.0000054479,"domain_scores_codex":[0.9967549,0.0003181556,0.000481793,0.001285505,0.0009301557,0.0002295321],"domain_scores_gemma":[0.9971941,0.0004603929,0.0003020517,0.001480494,0.0001729821,0.0003900498],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002083813,0.0004549302,0.00008449609,0.0004976614,0.0001162522,0.0001834849,0.00278114,0.2382716,0.3363026,0.2355289,0.1799581,0.005612566],"study_design_scores_gemma":[0.0002396529,0.00002459161,0.0002102571,0.00002940729,0.00001654449,0.00001085759,0.00003723004,0.9242787,0.01674871,0.0300474,0.02816678,0.0001898164],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007119818,0.00006379661,0.9834698,0.005192591,0.002489222,0.0002247095,0.001202025,0.0001582066,0.00007986965],"genre_scores_gemma":[0.4629525,9.138656e-7,0.5326709,0.002817312,0.0001335712,0.00001065043,0.001329331,0.00001839733,0.00006650958],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6860072,"threshold_uncertainty_score":0.7053498,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.06612173964472086,"gpt":0.3552075638803168,"spread":0.2890858242355959,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001986715,0.0001699973,0.0002064057,0.0002688881,0.0007407909,0.0005445679,0.00234407,0.00001662714,0.0009140257],"category_scores_gemma":[0.0001650056,0.0001701369,0.00002516692,0.000814677,0.00006227687,0.0006860632,0.01677846,0.0002709288,0.000289814],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001608023,"about_ca_system_score_gemma":0.0001317039,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001371185,"about_ca_topic_score_gemma":0.00001358129,"domain_scores_codex":[0.9967853,0.00008566306,0.0003270994,0.001406676,0.000941292,0.0004539597],"domain_scores_gemma":[0.996333,0.00002922162,0.0001338777,0.003238953,0.00005859559,0.0002063541],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005269705,0.0001919558,0.0001941771,0.00002299952,0.00003101597,0.00005929264,0.0001792082,0.00002812342,0.067858,0.000007394835,0.9059753,0.0253998],"study_design_scores_gemma":[0.00148405,0.0001068033,0.000158371,0.00001629821,0.0001007485,0.00003645288,0.003105585,0.01720556,0.003822917,0.000002379175,0.9737935,0.0001673213],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.1046675,0.0002834095,0.09574472,0.01752212,0.0114383,0.009417011,0.7517484,0.0005270113,0.008651554],"genre_scores_gemma":[0.0663624,0.00001262857,0.0368044,0.009346709,0.0003611394,0.0003702934,0.7949009,0.0001288231,0.0917127],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.08306114,"threshold_uncertainty_score":0.9999993,"prediction_status":"machine_predicted_unvalidated"},"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":"W4293463901","doi":"10.1038/s41597-022-01645-3","title":"Probabilistic atlas for the language network based on precision fMRI data from >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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1205485106440618,"gpt":0.3402758178060862,"spread":0.2197273071620243,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003812303,0.0001922011,0.0001935484,0.00008518193,0.001889285,0.0004258874,0.008466874,0.00004591345,0.001042277],"category_scores_gemma":[0.004645573,0.0001300051,0.00004976859,0.0006678541,0.0004442385,0.0002681763,0.005414604,0.0003387108,0.0001263958],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002576551,"about_ca_system_score_gemma":0.0001786279,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004242078,"about_ca_topic_score_gemma":0.00009051144,"domain_scores_codex":[0.99581,0.0005447887,0.0003229268,0.002095629,0.0007260007,0.0005006321],"domain_scores_gemma":[0.987832,0.004535615,0.0001895036,0.007341943,0.0000250839,0.00007585898],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001457453,0.0003065275,0.00008470214,0.00001404157,0.00001253573,0.0001273673,0.000624458,0.002871561,0.03028375,0.00013733,0.9543848,0.0110072],"study_design_scores_gemma":[0.0008489689,0.0001883495,0.0001607483,0.00003112701,0.00009575768,0.0000278196,0.0003216905,0.128249,0.004507177,0.001502931,0.86371,0.0003564466],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5920334,0.001285954,0.001790199,0.007423733,0.02106487,0.005578937,0.3691697,0.0004982649,0.001154934],"genre_scores_gemma":[0.9304355,0.000006731306,0.001777603,0.006265074,0.001032377,0.0001829122,0.05547073,0.0000625001,0.004766524],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3384021,"threshold_uncertainty_score":0.9998709,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03990451522155245,"gpt":0.2636712479106239,"spread":0.2237667326890714,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003091224,0.00007534506,0.0001489669,0.00006205836,0.00009337125,0.00001877818,0.0006126147,0.00002728126,0.00006285129],"category_scores_gemma":[0.0002279749,0.00005434449,0.00002927051,0.0005569985,0.0004952882,0.0001248541,0.0006446289,0.0001404214,0.00002734236],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001838705,"about_ca_system_score_gemma":0.00004935764,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007807775,"about_ca_topic_score_gemma":0.00005302723,"domain_scores_codex":[0.9988065,0.00005374464,0.0002211518,0.0005059895,0.0002325619,0.0001801035],"domain_scores_gemma":[0.9987599,0.00002211642,0.00006799498,0.001068514,0.00003261158,0.00004890479],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0001057222,0.0001515726,0.02263334,0.0001824883,0.000003484645,0.0002461165,0.0008506103,0.000004445626,0.827541,0.002103756,0.1080106,0.03816689],"study_design_scores_gemma":[0.004275138,0.0002541478,0.6422662,0.0007067336,0.00009982953,0.0003871542,0.0004503782,0.01124045,0.04284004,0.003756954,0.2933272,0.0003958133],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9853173,0.002838248,0.00007274238,0.008823432,0.0007077779,0.0004295919,0.0005905844,0.00003617962,0.00118415],"genre_scores_gemma":[0.9967188,0.000006088002,0.000286228,0.0003689904,0.00005924284,0.000003026322,0.0001969352,0.000007916002,0.002352808],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7847009,"threshold_uncertainty_score":0.2216104,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1006169606146817,"gpt":0.3922536860077259,"spread":0.2916367253930442,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.008393578,0.0006815785,0.0008828353,0.001169772,0.00196795,0.004105445,0.02308062,0.0005194693,0.0003604417],"category_scores_gemma":[0.001627732,0.0006899359,0.0001182696,0.004922405,0.00027874,0.002091074,0.01192761,0.004208623,0.003690867],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006983611,"about_ca_system_score_gemma":0.01001349,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.007049417,"about_ca_topic_score_gemma":0.02300481,"domain_scores_codex":[0.9884793,0.0009141797,0.00121419,0.005179976,0.001972671,0.002239664],"domain_scores_gemma":[0.9806623,0.0003029919,0.001210253,0.01692548,0.0002702893,0.0006287275],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000003683687,0.00004420385,0.00005363272,0.0003555808,0.0000307128,0.00002459141,0.0001349244,0.00001186949,6.380936e-7,0.0003374119,0.9290498,0.06995292],"study_design_scores_gemma":[0.0001170307,0.0001203689,0.0002195949,0.0004011539,0.00001504568,0.00003141311,0.00002488118,0.1603359,7.383119e-7,0.0006766887,0.8375406,0.0005165652],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"editorial","genre_gemma":"other","genre_scores_codex":[0.000005374162,0.004532326,0.04484897,0.04453927,0.7945916,0.001771039,0.1033055,0.002969892,0.003435991],"genre_scores_gemma":[0.00001727655,0.000230634,0.00602559,0.0009453981,0.00180988,0.0000638714,0.3704989,0.000112218,0.6202963],"genre_candidate":"editorial","genre_consensus":null,"teacher_disagreement_score":0.7927818,"threshold_uncertainty_score":0.9995627,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.06972847364218235,"gpt":0.2849240239335831,"spread":0.2151955502914007,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001013711,0.00006251279,0.0001159372,0.00000886754,0.0004907324,0.0002163552,0.002488719,0.00002074838,0.001744224],"category_scores_gemma":[0.0001948407,0.00003278267,0.00003135703,0.00009047083,0.003616667,0.0003025383,0.002741113,0.00005792583,0.00005998782],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002081352,"about_ca_system_score_gemma":0.00001283752,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008264385,"about_ca_topic_score_gemma":0.002030286,"domain_scores_codex":[0.9990891,0.00004575606,0.0001743685,0.0002725719,0.0002926631,0.0001255509],"domain_scores_gemma":[0.9974816,0.00002979805,0.000246392,0.00220402,0.000007108336,0.00003112561],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001037112,0.000132267,0.1068549,0.00002022792,0.00001732964,5.508024e-7,0.0005066562,0.00000335877,0.004724506,0.001828035,0.8813491,0.004459328],"study_design_scores_gemma":[0.002239644,0.00001886574,0.3393481,0.00007042746,0.00003961175,0.000005599405,0.00161196,0.0006676861,0.003654141,0.00103324,0.6511614,0.0001492351],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9572704,0.00004946272,0.00003576295,0.001922383,0.002044171,0.0003491254,0.004354565,0.000009072449,0.03396505],"genre_scores_gemma":[0.9981838,0.000005385322,0.00001431511,0.00002275078,0.0000153948,0.000002292069,0.0002132767,0.000002678829,0.001540049],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2324933,"threshold_uncertainty_score":0.9991683,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.09523647153939807,"gpt":0.3341223015070041,"spread":0.238885829967606,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002834002,0.00008104776,0.0001775,0.000101926,0.000101165,0.0001704257,0.0007082059,0.0000306117,0.0002033721],"category_scores_gemma":[0.000251311,0.00005892694,0.0000267207,0.0004612972,0.0001491752,0.0004026904,0.0002911589,0.00005740402,0.000253917],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003643947,"about_ca_system_score_gemma":0.00005787815,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004891823,"about_ca_topic_score_gemma":0.04166069,"domain_scores_codex":[0.998318,0.00006969779,0.0003192771,0.0005974269,0.0003405783,0.0003550325],"domain_scores_gemma":[0.9986945,0.0001545201,0.00004684099,0.0009875798,0.00003960551,0.00007695326],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000629151,0.0001246338,0.04846421,0.0004437956,0.00009829893,0.0001580947,0.001885108,0.0006975196,0.0359404,0.001233026,0.8519728,0.05835292],"study_design_scores_gemma":[0.004244547,0.000516678,0.2718967,0.0001978829,0.0001225002,0.00006765944,0.0155307,0.2247567,0.03406146,0.01702939,0.4299593,0.001616484],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8608541,0.0000218609,0.000157898,0.0005946961,0.001558409,0.0004099317,0.1315653,0.00003463353,0.004803183],"genre_scores_gemma":[0.817582,0.000002008542,0.001464534,0.00002386677,0.00006875583,4.926835e-7,0.1803226,0.000002166666,0.0005335528],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4220135,"threshold_uncertainty_score":0.9758265,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.04716827421050954,"gpt":0.3218757350716982,"spread":0.2747074608611887,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004735809,0.0002165125,0.0003701446,0.0001148987,0.0004764404,0.0003582623,0.001755885,0.00009159158,0.00001730157],"category_scores_gemma":[0.002119041,0.0001868118,0.00003221005,0.000262766,0.0003105944,0.00005135479,0.002164882,0.00008373908,0.000003981661],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000733908,"about_ca_system_score_gemma":0.00008637316,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000292496,"about_ca_topic_score_gemma":0.0001376411,"domain_scores_codex":[0.9972419,0.0001208464,0.0003656631,0.001618125,0.0002464552,0.0004070198],"domain_scores_gemma":[0.9957342,0.00009114166,0.000214279,0.003742238,0.00009902522,0.0001191027],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001271614,0.00007894249,0.001059971,0.0001161396,0.0001322457,3.009733e-7,0.00001398597,0.000001452824,0.8632033,0.00055218,0.1203284,0.01438591],"study_design_scores_gemma":[0.001200178,0.00008888663,0.001499025,0.00001186126,0.0001523499,0.000002768218,0.00004861394,0.005363956,0.01710105,0.0003346227,0.9738571,0.0003396077],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1830396,0.02339781,0.4085434,0.001422792,0.003816801,0.002227542,0.3745099,0.00009044031,0.002951638],"genre_scores_gemma":[0.6896641,0.0006714921,0.06826103,0.000439602,0.0006711188,0.00003177219,0.2393865,0.00004568031,0.0008286843],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8535287,"threshold_uncertainty_score":0.7617964,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}