{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":1581,"total_is_capped":false,"direct_labels_cover":8,"predictions_cover":1581,"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":"0ee2f2a50fc7","filters":{"topic":"Biomedical Text Mining and Ontologies"}},"results":[{"id":"W2002463857","doi":"10.1016/s0140-6736(13)62228-x","title":"Reducing waste from incomplete or unusable reports of biomedical research","year":2014,"lang":"en","type":"article","venue":"The Lancet","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1359,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Ottawa Hospital","funders":"Medical Research Council; National Health and Medical Research Council; Cancer Research UK","keywords":"Waste management; MEDLINE; Medicine; Business; Engineering; Political science; Law","retraction":null,"screen_n_in":null,"score":{"opus":0.0983632052959929,"gpt":0.3670015905797646,"spread":0.2686383852837717,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001551455,0.00007010973,0.0002248497,0.00002669014,0.0000842533,0.00001245377,0.0003427759,0.0001233488,0.00004936905],"category_scores_gemma":[0.001396676,0.00003864158,0.00003587119,0.0001360284,0.0005081962,9.443414e-7,0.000234797,0.0001680335,0.000007675522],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005305778,"about_ca_system_score_gemma":0.00005674397,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002354052,"about_ca_topic_score_gemma":0.00002606801,"domain_scores_codex":[0.9988133,0.0002172352,0.0002180729,0.0002332008,0.0002445792,0.0002736602],"domain_scores_gemma":[0.9989386,0.0001623188,0.00007790491,0.0007073628,0.0000573162,0.00005655354],"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":[0.0003593378,0.00006466818,0.001743152,0.00004739652,0.00007928243,0.00001876427,0.0002098131,0.000009850271,0.6424597,0.0001141892,0.312009,0.0428848],"study_design_scores_gemma":[0.0006656495,0.000625972,0.002482581,0.0001127413,0.00001383657,0.00003889788,0.0003125506,0.0003315831,0.1389491,0.002143641,0.8541838,0.0001397013],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9929971,0.0004809954,0.0009724299,0.002915177,0.0002307056,0.00006854611,0.000019136,0.00001766292,0.002298258],"genre_scores_gemma":[0.9940512,0.0001199957,0.003379749,0.0002048809,0.001620402,0.000007907873,0.00005426397,0.000009182076,0.0005524809],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5421748,"threshold_uncertainty_score":0.187247,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2131660156","doi":"10.1093/nar/gkp440","title":"BioPortal: ontologies and integrated data resources at the click of a mouse","year":2009,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":884,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Victoria","funders":"National Human Genome Research Institute","keywords":"Biology; Computational biology; Genetics; Bioinformatics","retraction":null,"screen_n_in":null,"score":{"opus":0.09505631666808116,"gpt":0.3857343446169439,"spread":0.2906780279488627,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001098776,0.0001040014,0.000153396,0.00005878153,0.0001764022,0.00003146815,0.000840254,0.0002088412,0.00003650914],"category_scores_gemma":[0.001187028,0.00006159171,0.00003007515,0.0001942711,0.001341285,0.000003646288,0.0008523888,0.0002487969,0.000008849119],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000010729,"about_ca_system_score_gemma":0.00005383199,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000129883,"about_ca_topic_score_gemma":0.0001859795,"domain_scores_codex":[0.9985846,0.0001957286,0.0001917111,0.0003917406,0.000312876,0.0003233607],"domain_scores_gemma":[0.9987082,0.00009278725,0.00004869817,0.0009639152,0.0001133646,0.00007299567],"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":[0.000466209,0.0001334937,0.01057961,0.00002800655,0.00008040843,0.00001326832,0.0004428147,7.407512e-7,0.6531171,0.0001265957,0.1012451,0.2337666],"study_design_scores_gemma":[0.0007527941,0.00192707,0.03982169,0.00004086503,0.00001715285,0.00004764484,0.003646742,0.000203514,0.1319728,0.0003078716,0.8210177,0.0002441099],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9926123,0.00318867,0.0000306672,0.002374221,0.00002157072,0.0001185585,0.00006391613,0.00002175758,0.001568311],"genre_scores_gemma":[0.9943164,0.001012237,0.0008413998,0.0001384208,0.00006035526,0.000004505474,0.0001236847,0.000009446966,0.003493552],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7197726,"threshold_uncertainty_score":0.4942022,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2046381118","doi":"10.1046/j.1528-1157.2001.22001.x","title":"Glossary of Descriptive Terminology for Ictal Semiology: Report of the ILAE Task Force on Classification and Terminology","year":2001,"lang":"en","type":"article","venue":"Epilepsia","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":859,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"London Health Sciences Centre","funders":"","keywords":"Semiology; Psychology; Automatism (medicine); Ictal; Epilepsy; Tonic (physiology); Audiology; Neuroscience; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.03703950545523505,"gpt":0.2913068359067388,"spread":0.2542673304515038,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001943607,0.0001132655,0.0002294042,0.00003645727,0.00005333235,0.000001991349,0.0001848132,0.0003239322,0.000003731319],"category_scores_gemma":[0.0005623315,0.00007926175,0.00008713278,0.00005347513,0.000746336,0.000001864345,0.00009245206,0.00008760732,6.091048e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008692108,"about_ca_system_score_gemma":0.00005450964,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001015591,"about_ca_topic_score_gemma":0.000008858278,"domain_scores_codex":[0.9990584,0.00007902314,0.0003137263,0.0003009438,0.00005779205,0.0001900849],"domain_scores_gemma":[0.999186,0.00008591902,0.0002670214,0.0003670979,0.00006237263,0.00003153532],"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":[0.0005355202,0.0001433443,0.1365958,0.00004987174,0.0001176226,0.00001876873,0.0001994915,0.000002310476,0.803643,0.001706562,0.006209565,0.05077808],"study_design_scores_gemma":[0.001401342,0.002710648,0.7476749,0.00006268034,0.0000855031,0.001116359,0.0005667509,0.0002296138,0.1696323,0.003028666,0.07321548,0.000275709],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9958731,0.0002963264,0.001354923,0.001076043,0.0002332821,0.000205592,0.00003300976,0.000009359445,0.0009183793],"genre_scores_gemma":[0.9975438,0.000128918,0.001091701,0.0001835258,0.00008284888,0.00003493738,0.00005888834,0.000008990936,0.000866364],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6340107,"threshold_uncertainty_score":0.32322,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2170282111","doi":"10.1093/nar/gkt1026","title":"The Human Phenotype Ontology project: linking molecular biology and disease through phenotype data","year":2013,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":837,"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; University of Toronto","funders":"Basic Energy Sciences; National Institute of Mental Health; National Institutes of Health; National Human Genome Research Institute; Bundesministerium für Bildung und Forschung; Office of Science; University College London; British Heart Foundation; National Institute for Health and Care Research; Deutsche Forschungsgemeinschaft; U.S. Department of Energy","keywords":"Unified Medical Language System; Annotation; Ontology; DECIPHER; Controlled vocabulary; Documentation; Computer science; Biology; Phenotype; Set (abstract data type); Interoperability; UniProt; Computational biology; Function (biology); Information retrieval; Bioinformatics; World Wide Web; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.09187093386330562,"gpt":0.4176459453405298,"spread":0.3257750114772242,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008668386,0.0001754148,0.0001776348,0.00005429117,0.0006761714,0.0001277443,0.00125057,0.0002965984,0.00005477453],"category_scores_gemma":[0.001411016,0.0001201923,0.00003912202,0.0001985503,0.001698062,0.00001107261,0.001765061,0.0004580458,0.00006093585],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001575808,"about_ca_system_score_gemma":0.000227279,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004876916,"about_ca_topic_score_gemma":0.00009559209,"domain_scores_codex":[0.9975688,0.0004548088,0.0002374156,0.0007315223,0.0002738235,0.0007335616],"domain_scores_gemma":[0.998064,0.0001475815,0.00005290384,0.001336415,0.000209062,0.000190083],"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":[0.0002912288,0.0003060494,0.02580002,0.000145851,0.0003526431,0.0000477921,0.0005550509,0.000001071539,0.5264331,0.03028969,0.08851869,0.3272588],"study_design_scores_gemma":[0.001252081,0.001424091,0.01250467,0.00005967985,0.00004450161,0.00001439713,0.0008876807,0.0006691181,0.003301591,0.08985853,0.8893753,0.0006083354],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.960087,0.01476766,0.003699498,0.01105463,0.0002824945,0.001001318,0.00006236928,0.00008884018,0.008956204],"genre_scores_gemma":[0.9946983,0.0006463717,0.002802992,0.0004191082,0.0003253478,0.00008701981,0.0002987936,0.00003495775,0.0006870341],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8008566,"threshold_uncertainty_score":0.6256579,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2557385283","doi":"10.1093/nar/gkw1039","title":"The Human Phenotype Ontology in 2017","year":2016,"lang":"en","type":"review","venue":"Nucleic Acids Research","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":801,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"SickKids Foundation; University of Toronto; Children's Hospital of Eastern Ontario; Hospital for Sick Children; University of Ottawa","funders":"Basic Energy Sciences; U.S. National Library of Medicine; Office of Science; National Institute for Health and Care Research; Bundesministerium für Bildung und Forschung; U.S. Department of Energy; European Commission; National Institutes of Health; NIHR Biomedical Research Centre, Royal Marsden NHS Foundation Trust/Institute of Cancer Research; Deutsche Forschungsgemeinschaft; Moorfields Eye Hospital NHS Foundation Trust; European Science Foundation; Cold Spring Harbor Laboratory; British Heart Foundation; National Human Genome Research Institute; Wellcome Trust; E-Rare","keywords":"Phenotype; Biology; Computational biology; Ontology; Clinical phenotype; Terminology; Pipeline (software); Disease; Bioinformatics; Controlled vocabulary; Data science; Genetics; Computer science; Gene; Information retrieval; Pathology; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.1460962601911709,"gpt":0.4624024800580583,"spread":0.3163062198668875,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002192489,0.0002715722,0.0006641307,0.0001713512,0.000409123,0.00006063083,0.001494727,0.001014176,0.00007123164],"category_scores_gemma":[0.00112745,0.0001439199,0.0002257919,0.0002542263,0.001324475,0.000001548669,0.0007394883,0.0009193275,0.0004255885],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008408828,"about_ca_system_score_gemma":0.0004259975,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003941078,"about_ca_topic_score_gemma":0.0002117504,"domain_scores_codex":[0.9966519,0.0009614939,0.0004530075,0.0006369021,0.0004018558,0.0008948804],"domain_scores_gemma":[0.9982564,0.0003568596,0.0001083118,0.001034194,0.0001186826,0.0001255674],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0000114547,0.00002753678,0.00001770785,0.0004071484,0.00005518419,0.00002013968,0.00001241038,3.527427e-9,0.0001105542,0.0004248391,0.02772427,0.9711888],"study_design_scores_gemma":[0.0001891193,0.0002353257,0.00004839002,0.001156231,0.00001221158,0.00001908952,0.00002817056,2.70319e-7,0.000009710996,0.0003834789,0.9977339,0.0001841166],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0001143846,0.9886777,0.00001433523,0.0002981502,0.0002143089,0.0003588687,0.00001832699,0.00001639365,0.01028757],"genre_scores_gemma":[0.0002063518,0.9907259,0.000073583,0.00002170046,0.0005426283,0.0001461799,0.00005399193,0.0000457414,0.008183876],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9710047,"threshold_uncertainty_score":0.7822254,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2165428180","doi":"10.1016/j.jbi.2008.03.004","title":"Bio2RDF: Towards a mashup to build bioinformatics knowledge systems","year":2008,"lang":"en","type":"article","venue":"Journal of Biomedical Informatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":798,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Wilfrid Laurier University; Université Laval; Centre hospitalier de l'Université Laval","funders":"Canadian Institutes of Health Research; Génome Québec; Genome Canada","keywords":"Computer science; Mashup; Bioinformatics; World Wide Web; Data science; The Internet; Biology; Web 2.0","retraction":null,"screen_n_in":null,"score":{"opus":0.02595393934073312,"gpt":0.2929058343851578,"spread":0.2669518950444246,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008351219,0.0002280342,0.0004593907,0.0003317632,0.0001210661,0.00004242694,0.0006027596,0.0003904185,0.00001723265],"category_scores_gemma":[0.0008368099,0.000160285,0.0001987606,0.0004223474,0.000418369,0.00001845521,0.0002378428,0.0003073598,0.00008883773],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004711434,"about_ca_system_score_gemma":0.0005278818,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005497984,"about_ca_topic_score_gemma":9.120704e-7,"domain_scores_codex":[0.9972861,0.00004583845,0.001555556,0.00008529738,0.0006142081,0.000413],"domain_scores_gemma":[0.9981016,0.0000470903,0.0005437535,0.0003056269,0.0003645972,0.0006373337],"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":[0.0003871623,0.0008246349,0.0009313143,0.0008117743,0.0006682497,0.000125437,0.009397323,0.000148446,0.009677699,0.00017026,0.7616975,0.2151602],"study_design_scores_gemma":[0.001176371,0.002323019,0.0005095676,0.0002007173,0.00003925208,0.002184225,0.002208917,0.002107964,0.002454053,0.00001554144,0.9864646,0.0003158113],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7570918,0.003046595,0.2283532,0.001505531,0.003789784,0.0004016889,0.00007907818,0.00006509091,0.005667169],"genre_scores_gemma":[0.8406299,0.001777263,0.1515394,0.00217163,0.002302647,0.0000152372,0.00008026027,0.00005033482,0.001433328],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2247671,"threshold_uncertainty_score":0.6536232,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2901332105","doi":"10.1093/nar/gky1105","title":"Expansion of the Human Phenotype Ontology (HPO) knowledge base and resources","year":2018,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":737,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Ottawa Hospital; Children's Hospital of Eastern Ontario; University of Toronto; SickKids Foundation; University of Ottawa; Hospital for Sick Children","funders":"NHLBI Division of Intramural Research; National Center for Advancing Translational Sciences; National Human Genome Research Institute; British Heart Foundation; National Cancer Institute; National Institutes of Health; Horizon 2020; National Institute of Allergy and Infectious Diseases; Division of Intramural Research, National Institute of Allergy and Infectious Diseases; European Commission; National Institute for Health and Care Research; E-Rare","keywords":"Biology; Phenotype; Knowledge base; Ontology; Computational biology; Base (topology); Genetics; Gene; World Wide Web; Computer science; Epistemology","retraction":null,"screen_n_in":null,"score":{"opus":0.05771103562546586,"gpt":0.3712816491888905,"spread":0.3135706135634246,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008154872,0.00008553639,0.0001253677,0.00006005958,0.0003081987,0.00001358442,0.0003940196,0.0002265391,0.00007710725],"category_scores_gemma":[0.0005609712,0.00005575241,0.00004099818,0.0001822957,0.002202622,0.000001644988,0.0005800861,0.0002099721,0.00001805109],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001013768,"about_ca_system_score_gemma":0.00007477729,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000714869,"about_ca_topic_score_gemma":0.0001659359,"domain_scores_codex":[0.9987067,0.0003105988,0.0001494316,0.0002912711,0.0002141415,0.0003278515],"domain_scores_gemma":[0.9991501,0.00005773216,0.00003597951,0.0004544613,0.0002185906,0.00008313981],"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":[0.00009373759,0.00007257082,0.01096587,0.00003857505,0.00002662421,0.000001413552,0.001039025,4.948866e-8,0.9144443,0.0004016357,0.01280014,0.06011607],"study_design_scores_gemma":[0.001152777,0.002742946,0.1477737,0.0001035143,0.00001730169,0.00001993446,0.001694491,0.0001094578,0.4254525,0.001420615,0.4192579,0.0002548414],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9895969,0.001161664,0.00004086863,0.000454809,0.00008824204,0.00009698996,0.000004461678,0.00001028162,0.008545777],"genre_scores_gemma":[0.9974517,0.00005201823,0.0004061405,0.00006039156,0.0002777966,0.000006945616,0.000003709517,0.00001214094,0.001729207],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4889918,"threshold_uncertainty_score":0.8115653,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2148866736","doi":"10.1126/science.1105776","title":"High-Throughput Mapping of a Dynamic Signaling Network in Mammalian Cells","year":2005,"lang":"en","type":"article","venue":"Science","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":723,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; University of Toronto; Mount Sinai Hospital","funders":"National Institute of General Medical Sciences","keywords":"Interactome; Occludin; Cell biology; Transforming growth factor; Signal transduction; Transforming growth factor beta; Tight junction; Biology; Chemistry; Gene; Biochemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.01112985846536018,"gpt":0.2601856382676177,"spread":0.2490557798022575,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005095736,0.0000640698,0.00009428485,0.00004650616,0.00005241358,0.00001048542,0.0002901203,0.00006606284,0.00001044736],"category_scores_gemma":[0.00006309719,0.00005678783,0.00002477186,0.0003568417,0.0004808398,0.000003553088,0.0001111702,0.00005809756,0.000005819435],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001698716,"about_ca_system_score_gemma":0.00008783238,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002351898,"about_ca_topic_score_gemma":0.000059886,"domain_scores_codex":[0.9991474,0.00001845351,0.0001607945,0.0002546855,0.000139293,0.0002793612],"domain_scores_gemma":[0.9996855,0.00001098704,0.0000542997,0.0001763421,0.00002786961,0.00004499329],"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":[0.000005998974,0.0000166695,0.0006683966,0.000006704713,0.00000173208,0.000001367984,0.00007783095,0.001479387,0.9543483,0.00003701204,0.0001114053,0.04324526],"study_design_scores_gemma":[0.0005832322,0.0002580539,0.02332688,0.0001151455,0.000004890652,0.000008639999,0.0003929528,0.003534635,0.9388775,0.0005829646,0.03199438,0.0003206961],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9948618,0.0006879763,0.00381143,0.000249034,0.0001638742,0.00004332229,0.000001942309,0.000007589684,0.0001729785],"genre_scores_gemma":[0.9548045,0.00003413174,0.04479865,0.000136205,0.00008841037,0.000002314208,0.000002249604,0.000003368858,0.0001301277],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04292456,"threshold_uncertainty_score":0.2315741,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2050554833","doi":"10.1038/nbt.1411","title":"Promoting coherent minimum reporting guidelines for biological and biomedical investigations: the MIBBI project","year":2008,"lang":"en","type":"article","venue":"Nature Biotechnology","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":562,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"BC Cancer Agency","funders":"Natural Environment Research Council; National Institute of Biomedical Imaging and Bioengineering; National Human Genome Research Institute; Biotechnology and Biological Sciences Research Council","keywords":"Extant taxon; Resource (disambiguation); Knowledge management; Business; Management science; Data science; Computer science; Biology; Engineering; Evolutionary biology","retraction":null,"screen_n_in":null,"score":{"opus":0.1045177839257098,"gpt":0.370750662613217,"spread":0.2662328786875072,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0006856665,0.0001814587,0.0002411295,0.0000786027,0.0003005213,0.00001109751,0.0002874822,0.001826042,0.000002445619],"category_scores_gemma":[0.01807778,0.0001050888,0.00008401966,0.0002104477,0.001501063,0.000001850576,0.0002321059,0.000477176,0.000001051572],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009497301,"about_ca_system_score_gemma":0.0001525426,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005791583,"about_ca_topic_score_gemma":0.00000771797,"domain_scores_codex":[0.9983319,0.00005356749,0.0006433781,0.0005219471,0.0001216756,0.0003275239],"domain_scores_gemma":[0.998926,0.00009387754,0.0004181156,0.0003312824,0.0001742049,0.00005651319],"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":[0.00009393626,0.0001313281,0.009102669,0.00006157306,0.0001465487,0.00003482289,0.000258822,2.271324e-7,0.7962641,0.0006411793,0.07850836,0.1147564],"study_design_scores_gemma":[0.0006761014,0.001104085,0.002046553,0.00004885445,0.00002328657,0.001008986,0.0004124447,0.000318631,0.1219208,0.001036159,0.8711123,0.0002917368],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9472944,0.005988614,0.001484761,0.04424655,0.0002751932,0.0005550662,0.00001978204,0.000107427,0.00002823082],"genre_scores_gemma":[0.9460824,0.0009496475,0.04972424,0.002092754,0.0006210989,0.0001888168,0.00015168,0.00002097231,0.0001684556],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.792604,"threshold_uncertainty_score":0.9994698,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2899915536","doi":"10.1093/nar/gky1032","title":"Human Disease Ontology 2018 update: classification, content and workflow expansion","year":2018,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":557,"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 Cancer Institute; National Human Genome Research Institute","keywords":"Workflow; Disease; Ontology; Biology; Computer science; Data science; Information retrieval; Database; Pathology; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.1212601190760921,"gpt":0.3832616903960068,"spread":0.2620015713199147,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006478711,0.0001223762,0.0001363027,0.00008838633,0.0004125815,0.00004736448,0.0003112808,0.0002404007,0.0001461808],"category_scores_gemma":[0.0004628581,0.0001010413,0.00003899476,0.0001448458,0.001833441,0.000004225485,0.00030634,0.0002180802,0.0001197184],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002284509,"about_ca_system_score_gemma":0.00009131833,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003320679,"about_ca_topic_score_gemma":0.00005992433,"domain_scores_codex":[0.9983231,0.0002250984,0.0001919544,0.0005060862,0.0003034947,0.0004502749],"domain_scores_gemma":[0.9988376,0.00002571229,0.00003634644,0.0005225457,0.0002888523,0.0002889749],"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":[0.0004364583,0.0002188281,0.0363341,0.000040565,0.00006191305,0.00001923749,0.0001795821,9.05755e-8,0.6841965,0.001613838,0.1461586,0.1307404],"study_design_scores_gemma":[0.001242187,0.001581696,0.4679059,0.00005940486,0.00001742486,0.0000170307,0.0007155279,0.0002038209,0.0155856,0.002042167,0.5102794,0.0003498221],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.993247,0.001144532,0.0005092741,0.003284061,0.000141834,0.0001724483,0.00001144385,0.0000341801,0.00145519],"genre_scores_gemma":[0.9953825,0.0002436722,0.001228232,0.0003424599,0.0004735776,0.00003497296,0.00006147943,0.00001888804,0.002214141],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6686109,"threshold_uncertainty_score":0.675539,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2141297584","doi":"10.1038/ng.1054","title":"Toward interoperable bioscience data","year":2012,"lang":"en","type":"article","venue":"Nature Genetics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":468,"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 Cancer Institute; National Heart, Lung, and Blood Institute; National Human Genome Research Institute; National Center for Research Resources; National Institute of General Medical Sciences; National Institute of Mental Health; Biotechnology and Biological Sciences Research Council","keywords":"Interoperability; Biology; Data science; Knowledge management; Data curation; Research data; World Wide Web; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.05015497168541178,"gpt":0.3283915047080819,"spread":0.2782365330226702,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002565179,0.0001044109,0.00008367473,0.0000217784,0.00005142273,0.00001992268,0.0007456235,0.0003744409,0.00002186829],"category_scores_gemma":[0.000257313,0.00008128775,0.00002493127,0.00009482051,0.0001468022,0.000003281175,0.0005890288,0.0002233678,0.00002742144],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005473389,"about_ca_system_score_gemma":0.00003997074,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002194735,"about_ca_topic_score_gemma":0.000003627231,"domain_scores_codex":[0.9991109,0.00002738138,0.0001057122,0.0002881292,0.0001454431,0.0003224034],"domain_scores_gemma":[0.9990942,0.000008041307,0.00003083103,0.0007084714,0.00003733965,0.0001210516],"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":[0.00007073684,0.0003201612,0.07453915,0.00006020423,0.0001055135,0.000006390858,0.0003248283,0.00000759055,0.3895758,0.0001651327,0.2655183,0.2693062],"study_design_scores_gemma":[0.0001537865,0.0001105482,0.007524385,0.000007120955,0.00001166889,0.00002707383,0.000106376,0.00008556647,0.08172683,0.00001963208,0.9100668,0.0001602108],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9306867,0.05553326,0.005589659,0.0009612055,0.002581457,0.0001256353,0.00008981684,0.00005314374,0.00437911],"genre_scores_gemma":[0.9800697,0.0005747413,0.01712504,0.0008996089,0.0006741171,0.000002187903,0.0001294105,0.00001076301,0.0005144249],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6445485,"threshold_uncertainty_score":0.3314818,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2595381146","doi":"10.15171/ijhpm.2017.15","title":"Defining Integrated Knowledge Translation and Moving Forward: A Response to Recent Commentaries","year":2017,"lang":"en","type":"article","venue":"International Journal of Health Policy and Management","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":387,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa; Ottawa Hospital; Western University","funders":"","keywords":"Knowledge translation; Translation (biology); Computer science; Data science; Knowledge management; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.05534345557430839,"gpt":0.4141588096681419,"spread":0.3588153540938335,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008428373,0.00006624594,0.0001065269,0.0001335521,0.0001679194,0.00007714852,0.0001774938,0.00003459937,0.0000022589],"category_scores_gemma":[0.0004857555,0.00005507877,0.00002291718,0.00001982088,0.00006849352,0.000007648111,0.0001394784,0.00005870859,6.686e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004189801,"about_ca_system_score_gemma":0.00008769851,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001328228,"about_ca_topic_score_gemma":0.0001006522,"domain_scores_codex":[0.9993496,0.00008049625,0.0002502954,0.00009654197,0.0001087372,0.0001143285],"domain_scores_gemma":[0.9994886,0.00005058329,0.0002007717,0.00008449014,0.00008548154,0.00009006062],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0007916468,0.00003490931,0.000558882,0.00002684996,0.000126887,0.000008305403,0.0007323264,0.000003895321,0.0002749287,0.001268156,0.005012382,0.9911608],"study_design_scores_gemma":[0.00116631,0.0004583839,0.01740044,0.0001519673,0.000008516568,0.00004627193,0.0005274914,0.00003565423,0.0002275603,0.0003469858,0.9795656,0.00006486378],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.526935,0.01311876,0.0271772,0.4290804,0.001176424,0.0003558358,0.0000438013,0.00001379048,0.002098827],"genre_scores_gemma":[0.9797985,0.006340848,0.008230993,0.005241438,0.0001710554,0.000004770096,0.000008753457,0.000006442678,0.0001972232],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.991096,"threshold_uncertainty_score":0.2246047,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2021074129","doi":"10.1371/journal.pone.0154556","title":"The Ontology for Biomedical Investigations","year":2016,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":385,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"Biotechnology and Biological Sciences Research Council; National Institute of Diabetes and Digestive and Kidney Diseases; National Institute of Allergy and Infectious Diseases; Division of Biological Infrastructure; National Institute of General Medical Sciences; National Center for Advancing Translational Sciences; Agence Nationale de la Recherche; National Human Genome Research Institute; Engineering and Physical Sciences Research Council; National Institute on Drug Abuse; California Institute for Regenerative Medicine; National Institutes of Health; National Science Foundation","keywords":"Open Biomedical Ontologies; Ontology; Computer science; Process ontology; Data science; Upper ontology; Interoperability; Biological database; Ontology-based data integration; World Wide Web; Information retrieval; Semantic Web; Suggested Upper Merged Ontology; Bioinformatics; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.06034610189973234,"gpt":0.2676917707597481,"spread":0.2073456688600158,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001584598,0.00006150189,0.00008250034,0.00001303515,0.0001343603,0.000007816837,0.0001765813,0.0001362198,0.00001031785],"category_scores_gemma":[0.001520392,0.00003075352,0.00003789287,0.00003461054,0.000549363,7.430325e-7,0.00005062208,0.00003200079,0.0000175539],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005981708,"about_ca_system_score_gemma":0.00005729014,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002093448,"about_ca_topic_score_gemma":0.00002616806,"domain_scores_codex":[0.9993924,0.00003042621,0.0001196629,0.0001631959,0.0000954065,0.0001988627],"domain_scores_gemma":[0.9994615,0.0001612182,0.00003468794,0.0002099019,0.00005322877,0.00007951315],"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":[0.00005417187,0.0002583739,0.002250522,0.00001436081,0.0001922692,5.095176e-7,0.00001910566,1.117914e-8,0.9263481,0.001961359,0.021731,0.04717024],"study_design_scores_gemma":[0.001166038,0.001037182,0.002016947,0.0000724402,0.00006978335,0.000004785873,0.00005236978,0.00002757321,0.3182577,0.006869718,0.6702284,0.0001971366],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9102965,0.00139114,0.0200724,0.06634705,0.0002400936,0.0003995899,0.00008042732,0.00007764712,0.00109513],"genre_scores_gemma":[0.9603374,0.0005025449,0.02847454,0.001221037,0.0008380461,0.0003163222,0.00006662416,0.00002311733,0.008220353],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6484973,"threshold_uncertainty_score":0.2024151,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2139259976","doi":"10.1186/1471-2105-4-11","title":"PreBIND and Textomy – mining the biomedical literature for protein-protein interactions using a support vector machine","year":2003,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":340,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; National Research Council Canada; Lunenfeld-Tanenbaum Research Institute","funders":"Canadian Institutes of Health Research; Directorate for Biological Sciences; Genome Canada","keywords":"Computer science; Support vector machine; Set (abstract data type); Task (project management); Interaction information; Precision and recall; Recall; Data curation; Interaction network; Artificial intelligence; Protein–protein interaction; Data mining; Machine learning; Database; Information retrieval; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.02721208388926301,"gpt":0.2967162964898785,"spread":0.2695042126006155,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003388593,0.0001737139,0.0001518127,0.0000546101,0.0002082324,0.00009160917,0.000149585,0.0002009731,0.00001706475],"category_scores_gemma":[0.0006519047,0.0001119113,0.00008044734,0.0001333257,0.0002301675,0.00001100237,0.00007879123,0.0001462144,0.000003065898],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001145068,"about_ca_system_score_gemma":0.0001309635,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003060014,"about_ca_topic_score_gemma":0.00001119694,"domain_scores_codex":[0.9990563,0.00004765359,0.0003208321,0.0001670287,0.0001312918,0.0002768908],"domain_scores_gemma":[0.999403,0.00004020818,0.0001291501,0.0002587303,0.00006314738,0.0001057663],"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":[0.001673043,0.001397953,0.007672831,0.00697523,0.001455485,0.00003092031,0.02226786,0.0000810666,0.6320181,0.008468716,0.04537751,0.2725813],"study_design_scores_gemma":[0.003091468,0.001521581,0.0005303692,0.0004715834,0.0001226679,0.0005854395,0.002677689,0.04978728,0.04521612,0.0004898623,0.8946756,0.0008303676],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.6141729,0.001295592,0.3804178,0.0005390355,0.0004198246,0.001799626,0.0003144123,0.00006521505,0.0009755974],"genre_scores_gemma":[0.4667232,0.00001367464,0.5308076,0.0003250174,0.0002158819,0.0001609164,0.0003576061,0.00002934719,0.001366794],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8492981,"threshold_uncertainty_score":0.4563612,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2145435867","doi":"10.1038/msb.2011.77","title":"Controlled vocabularies and semantics in systems biology","year":2011,"lang":"en","type":"article","venue":"Molecular Systems Biology","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":331,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University; Terry Fox Research Institute","funders":"National Institute of General Medical Sciences; Biotechnology and Biological Sciences Research Council; European Commission","keywords":"Ontology; Terminology; Semantics (computer science); Computer science; Systems biology; Reuse; Open Biomedical Ontologies; Biology; Data science; Semantic Web; Computational biology; Information retrieval; Ontology-based data integration; Programming language; Suggested Upper Merged Ontology","retraction":null,"screen_n_in":null,"score":{"opus":0.02141404991475278,"gpt":0.2575830418387564,"spread":0.2361689919240036,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006279367,0.0003010781,0.0007254366,0.0001593058,0.00006371584,0.0000277309,0.0002817797,0.0007684515,0.000005007801],"category_scores_gemma":[0.0003398298,0.0002400214,0.00009535865,0.0001248079,0.0005465252,0.000002519984,0.000193571,0.0001750107,0.00001091929],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001457947,"about_ca_system_score_gemma":0.00006385586,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000645103,"about_ca_topic_score_gemma":0.00005207084,"domain_scores_codex":[0.9976404,0.0005678409,0.0005696925,0.000625248,0.00006959948,0.0005272632],"domain_scores_gemma":[0.9991167,0.00004686645,0.0001842369,0.0004485026,0.00008175881,0.0001219518],"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":[0.001117224,0.0002887607,0.111469,0.000299564,0.0007711659,0.0002322887,0.00059961,0.00003121119,0.8208423,0.05864514,0.0006390129,0.00506482],"study_design_scores_gemma":[0.08996324,0.02485638,0.04639323,0.001366148,0.00108607,0.00446672,0.01063564,0.01617985,0.1610926,0.01099412,0.6225097,0.01045632],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9301698,0.03733313,0.02807503,0.0001379548,0.001351858,0.0007760061,0.00003307465,0.00006498548,0.002058177],"genre_scores_gemma":[0.9983892,0.0003245471,0.0005583452,0.0001418537,0.0001235294,0.0001473869,0.0000796095,0.00002742115,0.0002081128],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6597496,"threshold_uncertainty_score":0.978779,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2149378423","doi":"10.1186/2041-1480-1-s1-s7","title":"Modeling biomedical experimental processes with OBI","year":2010,"lang":"en","type":"article","venue":"Journal of Biomedical Semantics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":286,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"BC Cancer Agency","funders":"National Center for Research Resources; National Institute of Environmental Health Sciences; Engineering and Physical Sciences Research Council; Natural Environment Research Council; Biotechnology and Biological Sciences Research Council; Canadian Institutes of Health Research; National Institute of Mental Health; Public Health Agency; Public Health Agency of Canada; National Institutes of Health; National Institute of Biomedical Imaging and Bioengineering; Michael Smith Health Research BC; National Institute of Allergy and Infectious Diseases; NERC Environmental Bioinformatics Centre","keywords":"Computer science; Data science; Terminology; Ontology; Process (computing); Semantic Web; Interpretation (philosophy); Information retrieval; Epistemology; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.01200842841084153,"gpt":0.2767398138278822,"spread":0.2647313854170406,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004050232,0.0001859635,0.0002937911,0.000118993,0.00008291848,0.00003505604,0.0004106049,0.000374225,0.00005148655],"category_scores_gemma":[0.0007710873,0.0001172351,0.00009710031,0.000238979,0.0007168897,0.000007007518,0.0001057651,0.0004687079,0.000004961131],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009516388,"about_ca_system_score_gemma":0.0005058812,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004770482,"about_ca_topic_score_gemma":0.00001317453,"domain_scores_codex":[0.998281,0.0000305929,0.0004937965,0.0002181876,0.0006484411,0.0003279681],"domain_scores_gemma":[0.9989055,0.0000445164,0.0001900597,0.000202177,0.0002423647,0.0004153228],"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":[0.0003868916,0.001081383,0.0007307128,0.0001306111,0.0002051888,0.000213871,0.0002321575,0.00001793345,0.9819117,0.00004207378,0.005066661,0.009980812],"study_design_scores_gemma":[0.009073363,0.01737047,0.0004754543,0.0007477559,0.0003149003,0.008276627,0.003514358,0.007632858,0.4290271,0.0004003745,0.5216441,0.001522666],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9604527,0.000839834,0.03635125,0.00149959,0.0007042337,0.00005886155,0.000006450638,0.00001603595,0.00007098894],"genre_scores_gemma":[0.9757206,0.0001520328,0.02253835,0.0002274173,0.001255975,0.000002403055,0.00002023129,0.00002194543,0.00006104156],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5528846,"threshold_uncertainty_score":0.4780707,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2104990432","doi":"10.1136/amiajnl-2011-000523","title":"The National Center for Biomedical Ontology","year":2011,"lang":"en","type":"article","venue":"Journal of the American Medical Informatics Association","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":280,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Victoria","funders":"National Human Genome Research Institute; National Heart, Lung, and Blood Institute; Common Fund; National Institutes of Health","keywords":"Open Biomedical Ontologies; Ontology; Computer science; Biomedicine; Variety (cybernetics); World Wide Web; Data science; Semantic Web; Process ontology; Resource (disambiguation); Upper ontology; Ontology-based data integration; Analytics; Ontology alignment; Bioinformatics; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.02141549515800975,"gpt":0.3000184411159791,"spread":0.2786029459579693,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002093364,0.0000744031,0.0001666173,0.00003110589,0.0001474318,0.00001628059,0.0005297406,0.0001330799,0.0000087305],"category_scores_gemma":[0.007016874,0.00003705833,0.0001816431,0.0001090748,0.000386717,0.000005240379,0.00009126699,0.0002215782,0.000002790015],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007880968,"about_ca_system_score_gemma":0.0002876297,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005010699,"about_ca_topic_score_gemma":0.00001257841,"domain_scores_codex":[0.9982786,0.00009983119,0.000587112,0.00004339701,0.0007812936,0.0002097686],"domain_scores_gemma":[0.9978923,0.0002509085,0.001291301,0.00009132214,0.0003612628,0.0001128693],"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":[0.0006805031,0.0004657862,0.03255371,0.00003424638,0.001084416,0.000001877889,0.0017694,0.000003604596,0.001140355,0.0009751337,0.7291471,0.2321438],"study_design_scores_gemma":[0.001773909,0.001451989,0.02372262,0.00004702862,0.00006234917,0.0001489137,0.001349666,0.001068513,0.001255954,0.00211204,0.9668351,0.0001719594],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9173146,0.0003477504,0.04336715,0.03008135,0.003995583,0.0003960043,0.00007801563,0.00002202023,0.004397559],"genre_scores_gemma":[0.9718668,0.0005571692,0.01424521,0.01127512,0.001477236,0.00001766521,0.00002142682,0.00001686008,0.0005224645],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2376879,"threshold_uncertainty_score":0.840036,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1974896839","doi":"10.1093/bib/bbv011","title":"The role of ontologies in biological and biomedical research: a functional perspective","year":2015,"lang":"en","type":"article","venue":"Briefings in Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":279,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Canadian Association of Occupational Therapists; Saint Paul University","funders":"","keywords":"Computer science; Biomedicine; Open Biomedical Ontologies; Metadata; Ontology; Controlled vocabulary; Data science; Domain (mathematical analysis); Perspective (graphical); Meaning (existential); Identifier; Vocabulary; Biological data; IDEF5; Information retrieval; Knowledge management; Artificial intelligence; Domain knowledge; World Wide Web; Ontology-based data integration; Ontology alignment; Epistemology; Bioinformatics","retraction":null,"screen_n_in":null,"score":{"opus":0.09409572770032755,"gpt":0.3389545872947298,"spread":0.2448588595944022,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001369398,0.00008483508,0.0001397975,0.0001009679,0.00005699931,0.00001973815,0.0001784894,0.0002233918,0.00000183878],"category_scores_gemma":[0.003479413,0.00005358492,0.00002527725,0.0002251765,0.001357914,0.00000481951,0.000252067,0.0002149471,0.000002777053],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003570738,"about_ca_system_score_gemma":0.0001489349,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000189008,"about_ca_topic_score_gemma":0.0001462232,"domain_scores_codex":[0.9989482,0.00008867869,0.00031638,0.0001355267,0.0002348877,0.0002762895],"domain_scores_gemma":[0.9993863,0.0001980674,0.00006581414,0.0001473421,0.0001304729,0.00007200205],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00290298,0.001106748,0.1863077,0.0001289407,0.0002029347,0.00003672999,0.02691645,0.0000486175,0.0209232,0.05906045,0.03508746,0.6672778],"study_design_scores_gemma":[0.004484017,0.003594741,0.125603,0.0001859914,0.000009609428,0.0001925569,0.1802307,0.005040173,0.008035076,0.0787024,0.5932841,0.0006376473],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9859607,0.006120837,0.0003982462,0.002796585,0.00009545086,0.0001917242,0.00001005982,0.00001242067,0.004413952],"genre_scores_gemma":[0.9946087,0.0005977018,0.004557947,0.0001184644,0.00004330349,0.00001795617,0.00001361604,0.000004176182,0.00003814824],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6666401,"threshold_uncertainty_score":0.5003291,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2158439765","doi":"10.1186/1741-7007-5-44","title":"Broadening the horizon – level 2.5 of the HUPO-PSI format for molecular interactions","year":2007,"lang":"en","type":"article","venue":"BMC Biology","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":276,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Mount Sinai Hospital; University of Toronto; Lunenfeld-Tanenbaum Research Institute","funders":"National Institutes of Health; European Commission; Genome Canada; Ontario Genomics; National Institute of General Medical Sciences; Ontario Genomics Institute; U.S. Department of Energy","keywords":"Collaboratory; Human proteome project; Computer science; Schema (genetic algorithms); XML; Data science; World Wide Web; Computational biology; Biology; Information retrieval; Proteomics","retraction":null,"screen_n_in":null,"score":{"opus":0.08892370149535112,"gpt":0.3564340266507199,"spread":0.2675103251553688,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003759078,0.0001001356,0.0001180197,0.0000244624,0.0001193742,0.000005415368,0.0003465422,0.0001883818,0.000005664335],"category_scores_gemma":[0.0004325088,0.00005416353,0.000157711,0.00007930327,0.0003256286,0.000001389947,0.000150835,0.000107364,0.000001923714],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007754925,"about_ca_system_score_gemma":0.00004825768,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002364856,"about_ca_topic_score_gemma":0.0002063403,"domain_scores_codex":[0.999242,0.00006182319,0.0002218094,0.0001767789,0.00004906349,0.0002485318],"domain_scores_gemma":[0.9993324,0.0001377936,0.0001189838,0.0003183811,0.00006261108,0.00002987288],"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":[0.0001567393,0.00004025863,0.004607288,0.00002355934,0.00007151168,3.040622e-7,0.00008889283,0.000007927082,0.9378853,0.002752227,0.003863886,0.05050211],"study_design_scores_gemma":[0.0006013522,0.000592933,0.008814692,0.00001853456,0.00003802037,0.00004410693,0.0005734846,0.00007305652,0.5898515,0.001044458,0.3981862,0.0001616531],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6255509,0.001034535,0.3705842,0.0007336983,0.0007996779,0.0002700274,0.00005509693,0.00001479339,0.0009570011],"genre_scores_gemma":[0.992583,0.00001861568,0.006454674,0.0002905529,0.0001733446,0.000023328,0.00003499098,0.000009427805,0.000412024],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3943223,"threshold_uncertainty_score":0.2208725,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2144427809","doi":"10.1186/2041-1480-5-14","title":"The Semanticscience Integrated Ontology (SIO) for biomedical research and knowledge discovery","year":2014,"lang":"en","type":"article","venue":"Journal of Biomedical Semantics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":272,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of New Brunswick; Ontario Institute for Cancer Research; Carleton University","funders":"Instituto de Salud Carlos III; Natural Sciences and Engineering Research Council of Canada; National Science Foundation; University of Texas at El Paso; Canarie; European Federation of Pharmaceutical Industries and Associations; National Aeronautics and Space Administration","keywords":"Computer science; Ontology; License; Simple (philosophy); Semantic Web; Data science; World Wide Web; Open Biomedical Ontologies; Information retrieval; Ontology-based data integration; Suggested Upper Merged Ontology","retraction":null,"screen_n_in":null,"score":{"opus":0.04075967433146419,"gpt":0.3676510272121369,"spread":0.3268913528806727,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.004527206,0.0001585203,0.0003262192,0.0001643203,0.0003969827,0.0001121945,0.0006579189,0.0003828621,0.000002485334],"category_scores_gemma":[0.005814143,0.00008701062,0.0001175297,0.0003466739,0.003814129,0.000008487216,0.0002850649,0.0004614871,0.000002659898],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002282042,"about_ca_system_score_gemma":0.0003501885,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006451905,"about_ca_topic_score_gemma":0.00002759815,"domain_scores_codex":[0.9977367,0.0002729817,0.0006107159,0.0002823842,0.0005397779,0.0005574358],"domain_scores_gemma":[0.9975569,0.00109781,0.0002233382,0.0002685467,0.0005124485,0.0003409794],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001197994,0.00148724,0.002223511,0.0003139598,0.0004148163,0.00004519577,0.0005722695,8.58322e-7,0.2992345,0.009531084,0.1798998,0.5050787],"study_design_scores_gemma":[0.001247655,0.005001485,0.001135266,0.0001261881,0.00003479774,0.0002803145,0.0006616013,0.001209602,0.003529568,0.004136376,0.9824725,0.0001645822],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7629958,0.005399447,0.2070087,0.02148373,0.002592138,0.0002929328,0.00002364268,0.00001792653,0.0001856076],"genre_scores_gemma":[0.9900795,0.001326104,0.006450227,0.0001834098,0.001214763,0.000006679826,0.00001793182,0.00001827395,0.0007030827],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8025727,"threshold_uncertainty_score":0.9988969,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2061327015","doi":"10.1089/106652703322756104","title":"Mining the Biomedical Literature in the Genomic Era: An Overview","year":2003,"lang":"en","type":"review","venue":"Journal of Computational Biology","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":264,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"","keywords":"Data science; Computer science; Biomedical text mining; sort; Genomics; Genome; Data mining; Text mining; Information retrieval; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.06706577458925418,"gpt":0.389611694130938,"spread":0.3225459195416839,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001426002,0.0002442596,0.0007120127,0.0001470224,0.00007691691,0.00004626896,0.0007986201,0.0005671188,0.00001175183],"category_scores_gemma":[0.0002687662,0.0001097053,0.0003623672,0.0002834283,0.0003237441,0.000003334784,0.00006942468,0.0006703572,0.000003721412],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002371557,"about_ca_system_score_gemma":0.0005418135,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":9.840843e-7,"about_ca_topic_score_gemma":0.000002483229,"domain_scores_codex":[0.9973201,0.001258346,0.0007910141,0.000227912,0.0001825097,0.0002201259],"domain_scores_gemma":[0.9985688,0.0004294976,0.0006029246,0.0002134189,0.000120492,0.00006480545],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001974639,0.0001150543,0.00001981734,0.0004106508,0.0002012468,0.00004912326,0.0001814558,0.00002490669,0.00001233383,0.000647363,0.005660611,0.9926577],"study_design_scores_gemma":[0.0002334719,0.0005605377,0.0001059204,0.000744984,0.00009163529,0.001932436,0.00005954106,0.000008368917,2.514211e-7,0.001188426,0.9949473,0.0001271049],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0007392652,0.9976203,0.000450597,0.0005019075,0.0004780787,0.0001285936,0.00003632154,0.000002143508,0.0000427331],"genre_scores_gemma":[0.0003697702,0.9937277,0.003411955,0.001023726,0.0008699475,0.000009702161,0.0005516114,0.00001525993,0.00002035639],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9925306,"threshold_uncertainty_score":0.4473653,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3171450272","doi":"10.1136/rapm-2020-102451","title":"Standardizing nomenclature in regional anesthesia: an ASRA-ESRA Delphi consensus study of abdominal wall, paraspinal, and chest wall blocks","year":2021,"lang":"en","type":"article","venue":"Regional Anesthesia & Pain Medicine","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":264,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"St. Thomas Hospital; Toronto Western Hospital; Dalhousie University; University of Ottawa; University of Toronto","funders":"","keywords":"CLARITY; Nomenclature; Delphi method; Harmonization; Standardization; Consensus conference; Medicine; Delphi; Medical physics; Computer science; Political science; Artificial intelligence; Taxonomy (biology); Law; Library science","retraction":null,"screen_n_in":null,"score":{"opus":0.03398223843376127,"gpt":0.2978920485314313,"spread":0.26390981009767,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001695271,0.0003434613,0.0006515699,0.0001273107,0.0001156567,0.00001451533,0.0002612636,0.0003734411,0.00002191391],"category_scores_gemma":[0.0002099335,0.0002781169,0.00007840359,0.0002886282,0.0008021295,0.000005937782,0.00002648381,0.0003073305,6.141915e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003147608,"about_ca_system_score_gemma":0.0003031251,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001817208,"about_ca_topic_score_gemma":0.0002910321,"domain_scores_codex":[0.9970627,0.0006331828,0.0005952292,0.000726592,0.0005761107,0.0004061434],"domain_scores_gemma":[0.9985797,0.0002620227,0.0002241679,0.0004502152,0.0002370481,0.000246848],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.01406631,0.01152166,0.4506668,0.002175352,0.00160439,0.032264,0.02472716,0.0002838802,0.2681507,0.001412657,0.1316828,0.06144426],"study_design_scores_gemma":[0.01646761,0.02155505,0.3232415,0.003705119,0.0004113561,0.01818381,0.04578412,0.001061067,0.002757295,0.00111859,0.563764,0.001950548],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9242957,0.007608382,0.00009564879,0.06770761,0.00000589723,0.0002571084,2.452322e-7,0.00002082093,0.000008591538],"genre_scores_gemma":[0.9813602,0.00100848,0.001786459,0.01524823,0.0002822225,0.00003924315,0.0001064052,0.00003368855,0.0001350864],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4320811,"threshold_uncertainty_score":0.9999671,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2031950862","doi":"10.1093/nar/gkn296","title":"PolySearch: a web-based text mining system for extracting relationships between human diseases, genes, mutations, drugs and metabolites","year":2008,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":256,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"National Institute for Nanotechnology; University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Genome Prairie; Genome Canada","keywords":"Identification (biology); Variety (cybernetics); Biology; Gene nomenclature; Rank (graph theory); Information retrieval; Computational biology; Computer science; Gene; Genomics; Genome; Bioinformatics; Genetics; Artificial intelligence; Nomenclature","retraction":null,"screen_n_in":null,"score":{"opus":0.1261345981632541,"gpt":0.3758657254152483,"spread":0.2497311272519942,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.001550177,0.0001626488,0.0002402853,0.0002414999,0.001428657,0.00006615302,0.0002726047,0.0002759027,0.000009892235],"category_scores_gemma":[0.001453719,0.0001500603,0.0000946065,0.0003044739,0.000685229,0.00001103129,0.0001478796,0.000345683,0.000007990703],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004409568,"about_ca_system_score_gemma":0.000298417,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003123699,"about_ca_topic_score_gemma":0.000005624073,"domain_scores_codex":[0.9976075,0.0005192448,0.0003162033,0.0005156287,0.0004759563,0.0005654179],"domain_scores_gemma":[0.9982455,0.0007698775,0.00007520065,0.00036553,0.0002616867,0.0002822526],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002668106,0.0001999816,0.4966787,0.0005993773,0.0002860008,0.00003494077,0.00122038,0.00001125524,0.3887726,0.0006311139,0.004851999,0.1064468],"study_design_scores_gemma":[0.01028844,0.002427855,0.535636,0.0005469486,0.000350745,0.0001398494,0.02499657,0.00500959,0.1447613,0.0005183372,0.27345,0.001874328],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9920387,0.0053213,0.001254742,0.0004116298,0.00003820278,0.0003690367,0.0001378121,0.00007332797,0.0003552329],"genre_scores_gemma":[0.9896669,0.00009278431,0.008822585,0.0000169782,0.000390037,0.0001445201,0.0004217785,0.00003971661,0.0004046342],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.268598,"threshold_uncertainty_score":0.9998714,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2104381725","doi":"10.1136/amiajnl-2011-000150","title":"Machine-learned solutions for three stages of clinical information extraction: the state of the art at i2b2 2010","year":2011,"lang":"en","type":"article","venue":"Journal of the American Medical Informatics Association","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":240,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"U.S. National Library of Medicine","keywords":"Narrative; Benchmark (surveying); Process (computing); Computer science; State (computer science); Data science; Health care; Artificial intelligence; Natural language processing; Political science; Art; Cartography; Literature; Geography; Law","retraction":null,"screen_n_in":null,"score":{"opus":0.04653909334875948,"gpt":0.340871690572667,"spread":0.2943325972239075,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003558089,0.00008340988,0.0002759108,0.000031335,0.0001453896,0.000009938619,0.0005321678,0.0001240806,0.00001662486],"category_scores_gemma":[0.005891096,0.00003923466,0.0003344423,0.0001522037,0.0004779773,0.00002444393,0.0002003546,0.0003473044,0.000002288961],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004521082,"about_ca_system_score_gemma":0.0002705289,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003119299,"about_ca_topic_score_gemma":0.00008497143,"domain_scores_codex":[0.9976616,0.0001742248,0.001279964,0.00003693867,0.000674483,0.0001728244],"domain_scores_gemma":[0.9945642,0.0003434077,0.004389491,0.0002459562,0.0003876244,0.0000692795],"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":[0.001329793,0.0005185343,0.1906929,0.0001757639,0.001624735,4.440452e-7,0.004694991,0.0004302751,0.001880987,0.0002973498,0.1816364,0.6167179],"study_design_scores_gemma":[0.003483944,0.002663083,0.7625557,0.0002324712,0.0005000082,0.00007681899,0.002834769,0.01307383,0.009153448,0.002681174,0.2023977,0.0003471271],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9592066,0.0001517301,0.0313124,0.006696429,0.001548084,0.0003153675,0.00008776933,0.000006338635,0.0006752214],"genre_scores_gemma":[0.9943545,0.000618034,0.003090716,0.001274925,0.0001981634,0.000006786244,0.00001325542,0.000007410983,0.0004361946],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6163707,"threshold_uncertainty_score":0.7052618,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2016928406","doi":"10.1093/bioinformatics/bth451","title":"Discovering patterns to extract protein–protein interactions from full texts","year":2004,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":238,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Recall rate; Scientific literature; Matching (statistics); Information retrieval; Natural language processing; Artificial intelligence; Data mining; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.01549990955994195,"gpt":0.267165727324153,"spread":0.251665817764211,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007094621,0.0001589312,0.0001308512,0.00004709995,0.00008189269,0.00006033304,0.0002226249,0.0001238328,0.00003659057],"category_scores_gemma":[0.0001451208,0.0001344148,0.00007403483,0.00007302662,0.00004551808,0.0000122223,0.0001621443,0.0001238535,0.0001448134],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003216602,"about_ca_system_score_gemma":0.00006085688,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001096491,"about_ca_topic_score_gemma":0.0001727354,"domain_scores_codex":[0.9991258,0.0000110132,0.0002947361,0.0001666714,0.0001468952,0.0002549278],"domain_scores_gemma":[0.9993973,0.000007672244,0.00008920826,0.000335226,0.00003156554,0.0001390287],"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":[0.0001634541,0.0002125425,0.0006073937,0.0001091584,0.0001262254,0.00001225956,0.001478982,0.0002355377,0.7448636,0.000142983,0.001077578,0.2509703],"study_design_scores_gemma":[0.001987702,0.001488048,0.005996979,0.0007928376,0.00004076964,0.00004732921,0.002574007,0.0004906342,0.7400716,0.001090251,0.2442705,0.001149302],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.826021,0.00005597092,0.1723548,0.0004221142,0.0001488692,0.0002545578,0.00009902176,0.00004210442,0.0006015825],"genre_scores_gemma":[0.9398645,0.000008328059,0.0591281,0.0002917481,0.0002132219,0.00005623933,0.0001456001,0.00001500649,0.0002772959],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.249821,"threshold_uncertainty_score":0.5481275,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2951560185","doi":"10.1038/s41592-019-0422-y","title":"CancerMine: a literature-mined resource for drivers, oncogenes and tumor suppressors in cancer","year":2019,"lang":"en","type":"article","venue":"Nature Methods","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":223,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University; Canada's Michael Smith Genome Sciences Centre; University of British Columbia","funders":"","keywords":"Suppressor; License; Resource (disambiguation); Cancer; Disease; Database; Computer science; Bioinformatics; Biology; Medicine; Genetics; Internal medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.01149039921388123,"gpt":0.3900107605720499,"spread":0.3785203613581687,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004367479,0.0001481006,0.0002235247,0.00006124602,0.00003013524,0.00001929931,0.0001588176,0.0004796403,0.00001218007],"category_scores_gemma":[0.0004139405,0.0001176801,0.00006122004,0.0001418069,0.0000756189,0.00000241709,0.00008244342,0.0002690803,3.296268e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001775225,"about_ca_system_score_gemma":0.00006053002,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002539722,"about_ca_topic_score_gemma":0.0000899433,"domain_scores_codex":[0.9990054,0.0001382503,0.0001357272,0.0004040074,0.00007793647,0.0002386389],"domain_scores_gemma":[0.9994815,0.0001289362,0.0000567013,0.0002192198,0.00005066961,0.00006300161],"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":[0.0006727545,0.00005431513,0.01568879,0.0003009991,0.00009041508,0.00001228015,0.000506771,0.00002462157,0.6932029,0.000129022,0.01390716,0.2754101],"study_design_scores_gemma":[0.001171067,0.0002431145,0.0051479,0.0001062543,0.0000182161,0.00001352553,0.0001102798,0.0001757503,0.1635667,0.000124431,0.8291096,0.0002131721],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9359854,0.06012216,0.001200963,0.0009844869,0.0006324741,0.0004206361,0.0001140343,0.0000234261,0.0005163726],"genre_scores_gemma":[0.580371,0.001422156,0.4057487,0.003301606,0.000928343,0.0002659947,0.0002372177,0.00006647971,0.007658509],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8152025,"threshold_uncertainty_score":0.4798855,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1964255443","doi":"10.1371/journal.pbio.1002033","title":"Finding Our Way through Phenotypes","year":2015,"lang":"en","type":"article","venue":"PLoS Biology","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":222,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary; Simon Fraser University","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Cancer Institute; National Human Genome Research Institute; Biotechnology and Biological Sciences Research Council; National Science Foundation","keywords":"Phenomics; Biology; Bottleneck; Data science; Genomics; Systematics; Phenotype; Systems biology; Computational biology; Ecology; Computer science; Genome; Genetics; Taxonomy (biology)","retraction":null,"screen_n_in":null,"score":{"opus":0.09074615135526791,"gpt":0.3319444958987222,"spread":0.2411983445434543,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001383259,0.0001235264,0.0001618008,0.00002156465,0.00004630972,0.000008361016,0.0002196395,0.0002942167,0.00001198167],"category_scores_gemma":[0.0004777483,0.00009528291,0.00004877794,0.00006113372,0.0001055756,0.000001591277,0.0001443956,0.00009594583,0.0001067367],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001024948,"about_ca_system_score_gemma":0.00005319464,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002145811,"about_ca_topic_score_gemma":0.00001248531,"domain_scores_codex":[0.9991294,0.00007574959,0.0001407748,0.0003075578,0.00006108861,0.0002854364],"domain_scores_gemma":[0.9995541,0.00001359636,0.00005057352,0.0002396365,0.00005380858,0.00008828392],"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":[0.0003057138,0.0003541019,0.03352012,0.00003702796,0.0003830537,0.00001938115,0.0008032014,0.000009528931,0.8089513,0.003346874,0.09907591,0.05319377],"study_design_scores_gemma":[0.001346867,0.00159143,0.00115725,0.0000207839,0.00004147428,0.00003858886,0.001302251,0.00005474611,0.2133289,0.005977644,0.77464,0.0005001145],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9787977,0.003025367,0.00364463,0.002355387,0.000772146,0.0001167374,0.0000251152,0.00009545209,0.01116749],"genre_scores_gemma":[0.9916388,0.00007425081,0.006161585,0.0006709659,0.000541234,0.00001423407,0.0001035941,0.00001295686,0.0007823586],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6755641,"threshold_uncertainty_score":0.3885524,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2062558911","doi":"10.1186/1756-0500-3-175","title":"OntoFox: web-based support for ontology reuse","year":2010,"lang":"en","type":"article","venue":"BMC Research Notes","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":209,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia; BC Cancer Agency","funders":"National Institute of Biomedical Imaging and Bioengineering; National Institute of Allergy and Infectious Diseases; Canadian Institutes of Health Research; Public Health Agency of Canada; National Institutes of Health; Michael Smith Health Research BC; Public Health Agency; University of Michigan","keywords":"Computer science; Ontology; SPARQL; Information retrieval; Open Biomedical Ontologies; RDF; Process ontology; Ontology-based data integration; Interoperability; Suggested Upper Merged Ontology; World Wide Web; Semantic Web","retraction":null,"screen_n_in":null,"score":{"opus":0.1424209078921109,"gpt":0.4383030431723238,"spread":0.2958821352802129,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001575306,0.0001300941,0.0001699022,0.0001076383,0.0001830963,0.00003752135,0.0006895899,0.0004222499,0.0001254985],"category_scores_gemma":[0.0124718,0.0001077479,0.0001172732,0.00011708,0.0006462831,0.000002089332,0.0002255877,0.0003613175,0.00004790691],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009869271,"about_ca_system_score_gemma":0.0006736983,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007741337,"about_ca_topic_score_gemma":0.002349039,"domain_scores_codex":[0.9982888,0.0001445751,0.00019217,0.0004549754,0.0002754201,0.0006441011],"domain_scores_gemma":[0.9979635,0.0006615268,0.00003860704,0.0008582321,0.0002913112,0.0001868237],"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":[0.0006128111,0.0001657338,0.01652146,0.00007257051,0.00002596517,0.000006382351,0.00003003787,0.000002377938,0.8960345,0.0003720828,0.06701755,0.01913849],"study_design_scores_gemma":[0.001429185,0.001308545,0.009059314,0.000008652812,0.000007026271,0.00001041124,0.00004195066,0.0003592154,0.2137884,0.0007959692,0.7729927,0.0001987097],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9848946,0.0002956954,0.007109302,0.004135645,0.0005962641,0.0005494093,0.00007948535,0.00007679158,0.002262861],"genre_scores_gemma":[0.9475489,0.0000215098,0.04961501,0.0002503579,0.0005780251,0.0002004381,0.0001571318,0.0000262045,0.001602463],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7059751,"threshold_uncertainty_score":0.9958466,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3170771812","doi":"10.1093/database/baab069","title":"OBO Foundry in 2021: operationalizing open data principles to evaluate ontologies","year":2021,"lang":"en","type":"article","venue":"Database","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":206,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"National Human Genome Research Institute; National Institutes of Health","keywords":"Computer science; Operationalization; World Wide Web; Data science","retraction":null,"screen_n_in":null,"score":{"opus":0.2031218362382894,"gpt":0.4157198848331276,"spread":0.2125980485948382,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006690712,0.0001161333,0.0001604376,0.00003171723,0.00007169529,0.0001066637,0.001071629,0.00008485681,0.0001700377],"category_scores_gemma":[0.002310896,0.0001055491,0.0000186242,0.0001487099,0.0000634168,0.00001678359,0.004450098,0.00009035323,0.00005500557],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001550529,"about_ca_system_score_gemma":0.0003482744,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002244967,"about_ca_topic_score_gemma":0.003848924,"domain_scores_codex":[0.9986271,0.0001331722,0.0002223211,0.00063499,0.0001505609,0.0002318976],"domain_scores_gemma":[0.998533,0.00004521611,0.00003358912,0.001235192,0.00006869196,0.00008438672],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003990593,0.0006435062,0.02600783,0.0001051295,0.0002052516,0.0006415655,0.0002883013,0.0003044052,0.6102062,0.002595247,0.1837941,0.1748095],"study_design_scores_gemma":[0.0007493924,0.00008473951,0.007018701,0.00007741098,0.00001425417,0.00003025051,0.0004721,0.0004641301,0.02760129,0.00005329312,0.9631705,0.0002639691],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.952533,0.009935922,0.01109766,0.01108793,0.001004742,0.0008698606,0.004395448,0.00005333234,0.009022096],"genre_scores_gemma":[0.5188601,0.002619842,0.3774148,0.008894127,0.001036079,0.0002951922,0.08226245,0.00007805302,0.008539435],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7793764,"threshold_uncertainty_score":0.5546728,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2024038403","doi":"10.1093/nar/gku1068","title":"BRENDA in 2015: exciting developments in its 25th year of existence","year":2014,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":195,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"Bundesministerium für Bildung und Forschung","keywords":"Annotation; Information retrieval; Relevance (law); Computer science; KEGG; Computational biology; Function (biology); Ontology; Biology; Data mining; Artificial intelligence; Gene ontology; Biochemistry; Genetics; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.06924922146140024,"gpt":0.3853085447481472,"spread":0.316059323286747,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001444847,0.00007578718,0.0001412699,0.0001553332,0.00003383825,0.00001016197,0.0003289154,0.000176765,0.00002890826],"category_scores_gemma":[0.001146906,0.00006958804,0.00002302319,0.0003030684,0.0002089659,0.000002869875,0.0002619815,0.0002445514,0.00003178116],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002528729,"about_ca_system_score_gemma":0.00009928043,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006241202,"about_ca_topic_score_gemma":0.00009028364,"domain_scores_codex":[0.998611,0.000198291,0.0002242023,0.0002727764,0.0003102626,0.0003834374],"domain_scores_gemma":[0.999558,0.00004999159,0.000032327,0.0002040625,0.00009150401,0.00006408189],"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":[0.000278809,0.0002781193,0.3164943,0.0002204342,0.00002786573,0.00002500905,0.001178064,0.000008794807,0.4934978,0.0008845124,0.004088063,0.1830182],"study_design_scores_gemma":[0.003082321,0.001035499,0.7323131,0.000462435,0.000002575348,0.00001598723,0.002428278,0.0008143007,0.1733699,0.0005628358,0.08542038,0.0004923853],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9913368,0.0002746672,0.00005623653,0.0001381297,0.00003930956,0.00007891715,0.000003013995,0.00000588057,0.008067098],"genre_scores_gemma":[0.9961373,0.0001189037,0.003067149,0.00002745531,0.0000489669,0.00001161566,0.00001004513,0.00001051711,0.0005680675],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4158187,"threshold_uncertainty_score":0.2837718,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2949176808","doi":"10.1093/bioinformatics/bty449","title":"Transfer learning for biomedical named entity recognition with neural networks","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":195,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"National Human Genome Research Institute; National Institutes of Health; Nvidia","keywords":"Computer science; Named-entity recognition; Transfer of learning; Artificial intelligence; Annotation; Deep learning; Conditional random field; Task (project management); Artificial neural network; Field (mathematics); Machine learning; Natural language processing; Word (group theory); Noise (video); State (computer science); Domain (mathematical analysis); Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01989986393970058,"gpt":0.2556185910061561,"spread":0.2357187270664556,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001888,0.0001183135,0.0001194463,0.0000344309,0.0001421619,0.0000290077,0.0001147732,0.0002133854,0.00002067956],"category_scores_gemma":[0.000129622,0.00008703393,0.00005733778,0.00009030176,0.0003583857,0.000007409122,0.00002878983,0.0001044764,0.00001019999],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006782525,"about_ca_system_score_gemma":0.00003298074,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003000968,"about_ca_topic_score_gemma":0.00001207586,"domain_scores_codex":[0.9992521,0.00002047677,0.0002118491,0.0001290638,0.0001188375,0.0002676552],"domain_scores_gemma":[0.9996086,0.0000245179,0.00004362079,0.0001238768,0.0001035403,0.00009587263],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000854324,0.0001355821,0.001137183,0.0001755411,0.0001787619,0.000002345744,0.0005947266,0.0001185694,0.005960059,0.00004195139,0.01033137,0.9804696],"study_design_scores_gemma":[0.004446417,0.01036505,0.0008362375,0.0001146986,0.0001377851,0.0001055128,0.001398442,0.4602784,0.0206426,0.00008546953,0.5007209,0.0008684802],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4322612,0.00007835414,0.5663976,0.0002045117,0.0002876129,0.0002208108,0.0000175299,0.00006139461,0.0004709908],"genre_scores_gemma":[0.9712829,0.00003940825,0.02678259,0.000514942,0.0006010988,0.00003147093,0.0005723304,0.00001555719,0.000159701],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9796011,"threshold_uncertainty_score":0.3549141,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2146538435","doi":"10.1186/1758-2946-3-19","title":"Linked open drug data for pharmaceutical research and development","year":2011,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":187,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"Pfizer","keywords":"Data science; Computer science; Task (project management); Open data; Data sharing; External Data Representation; Web application; World Wide Web; Data mining; Medicine; Engineering; Alternative medicine; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.4477610663788747,"gpt":0.4690782952067872,"spread":0.02131722882791248,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001777505,0.00006693842,0.0001406274,0.00003823934,0.00007179774,0.00004013087,0.0008641396,0.00008881729,0.0000112302],"category_scores_gemma":[0.0004975687,0.00004899784,0.00001624488,0.00003865247,0.0001562989,0.00001923443,0.0008014014,0.000163157,0.000001795891],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008497494,"about_ca_system_score_gemma":0.0002193108,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":7.814792e-7,"about_ca_topic_score_gemma":0.000001237946,"domain_scores_codex":[0.9991701,0.000008947189,0.0003907795,0.00007797948,0.0001725563,0.0001796959],"domain_scores_gemma":[0.9992051,0.00005947576,0.0001464036,0.0002314334,0.0002313992,0.0001261963],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001490536,0.0005223246,0.001141418,0.0005934747,0.0005050643,0.00001372363,0.008481905,3.241893e-7,0.02189137,0.0002035907,0.3590345,0.6061218],"study_design_scores_gemma":[0.001148015,0.0002950776,0.0001586787,0.00005146884,0.0000146074,0.00008879074,0.001422071,0.0001066527,0.156973,0.0002345836,0.8394071,0.00009987457],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.9540431,0.003451564,0.01917966,0.001290888,0.00062419,0.0008901816,0.00007217746,0.00001513941,0.0204331],"genre_scores_gemma":[0.494962,0.0006026084,0.5020807,0.0004651792,0.0003996233,0.00001286971,0.0001148485,0.00002052614,0.001341689],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6060219,"threshold_uncertainty_score":0.1998074,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1997148915","doi":"10.1038/nmeth.2698","title":"Significance, P values and t-tests","year":2013,"lang":"en","type":"article","venue":"Nature Methods","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":185,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Canada's Michael Smith Genome Sciences Centre","funders":"","keywords":"Biology; Computational biology","retraction":null,"screen_n_in":null,"score":{"opus":0.01318092258949543,"gpt":0.3727160138569054,"spread":0.35953509126741,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003305127,0.00009460252,0.0001097205,0.00002256099,0.00004466949,0.00002155229,0.0001107592,0.0004344538,0.00003600788],"category_scores_gemma":[0.0006548786,0.00007006853,0.00003271119,0.00006358945,0.0001518975,0.000001505545,0.00007307735,0.0002202773,0.000007202961],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000002723623,"about_ca_system_score_gemma":0.00001808631,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009077888,"about_ca_topic_score_gemma":0.000001274867,"domain_scores_codex":[0.9992991,0.0001506591,0.00008704585,0.0002416576,0.00006575607,0.0001557952],"domain_scores_gemma":[0.9995825,0.0000764722,0.00002975935,0.0001887715,0.00004890656,0.0000736499],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000007330728,0.00001429443,0.001358567,0.00001204158,0.00002284273,8.828965e-7,0.00002786961,2.129399e-7,0.4596962,0.00008733555,0.02380252,0.5149699],"study_design_scores_gemma":[0.000477468,0.0003762763,0.07476157,0.00001925466,0.00002503123,0.00003387441,0.0001731399,0.0001007562,0.353983,0.009605699,0.5600665,0.0003773734],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.8904241,0.03532464,0.05738586,0.002425283,0.001071618,0.0003972718,0.000008955185,0.0001181928,0.01284405],"genre_scores_gemma":[0.413954,0.0002090103,0.5817787,0.001083246,0.0002836922,0.00002931306,0.00001283308,0.00001261541,0.002636614],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.536264,"threshold_uncertainty_score":0.3350905,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1481389199","doi":"10.1136/amiajnl-2013-001636","title":"Literature review of SNOMED CT use","year":2013,"lang":"en","type":"review","venue":"Journal of the American Medical Informatics Association","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":177,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Victoria","funders":"","keywords":"SNOMED CT; Systematized Nomenclature of Medicine; Implementation; Computer science; Medicine; MEDLINE; Domain (mathematical analysis); Information retrieval; Medical physics; Terminology; Software engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.0225821128250893,"gpt":0.3324139615146779,"spread":0.3098318486895886,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001769274,0.0002138002,0.001478409,0.00008699102,0.0000336932,0.00003607761,0.0007817524,0.0002403871,0.0000206777],"category_scores_gemma":[0.01126096,0.0001103759,0.0008520322,0.0004558538,0.000192166,0.00001198957,0.000194748,0.0007609051,0.0000059117],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001125519,"about_ca_system_score_gemma":0.0006328308,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003976686,"about_ca_topic_score_gemma":6.19155e-7,"domain_scores_codex":[0.9965628,0.0003819057,0.001748913,0.00006750811,0.001040697,0.0001981954],"domain_scores_gemma":[0.9909512,0.0002909815,0.007844698,0.0003183897,0.0004404891,0.0001542545],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000002578404,0.00003038129,0.00003764023,0.01538772,0.0003899324,0.000002449234,0.00002828493,9.340463e-8,0.000001381081,0.000002529204,0.0928572,0.8912598],"study_design_scores_gemma":[0.0001053148,0.0001598373,0.00002246364,0.07117467,0.0003726574,0.000169814,0.00002448177,0.000004584484,0.000005931765,0.000004860688,0.9278459,0.0001095147],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0002323182,0.9984963,0.000116095,0.0004423957,0.0004047775,0.0001960069,0.00003193041,0.000003063462,0.00007713537],"genre_scores_gemma":[0.00000609617,0.9961373,0.001544042,0.001643523,0.000307685,0.000006292337,0.00005208487,0.00001361326,0.0002893308],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.8911503,"threshold_uncertainty_score":0.9970676,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2025891673","doi":"10.1038/461171a","title":"Post-publication sharing of data and tools","year":2009,"lang":"en","type":"article","venue":"Nature","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":171,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"National Heart, Lung, and Blood Institute; U.S. National Library of Medicine; Wellcome Trust","keywords":"Data sharing; Data science; Computer science; World Wide Web; Medicine; Alternative medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.02565004229168766,"gpt":0.3222853500815559,"spread":0.2966353077898682,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009429574,0.00003758345,0.0000489535,0.00001368752,0.00001521141,0.00001464438,0.000223776,0.000473059,0.000004063537],"category_scores_gemma":[0.0005320497,0.00003025172,0.000009224304,0.00003473917,0.00003086052,0.000004634269,0.0001071522,0.000192023,5.359731e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000001030125,"about_ca_system_score_gemma":0.00001240048,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001179018,"about_ca_topic_score_gemma":0.000001872639,"domain_scores_codex":[0.9996555,0.00000538605,0.00006121065,0.0001680395,0.0000502416,0.00005957032],"domain_scores_gemma":[0.9995579,0.000005775996,0.00002808313,0.0003053335,0.00008068795,0.00002225175],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003499683,0.00003171539,0.001030528,0.00001257962,0.00001565485,7.150058e-7,0.00002992175,1.031423e-7,0.350421,0.0004838622,0.0225849,0.625354],"study_design_scores_gemma":[0.0008574264,0.0007579647,0.1725927,0.00004181819,0.00003077607,0.00003892075,0.0002256048,0.0002562615,0.129896,0.0008286075,0.6941734,0.0003005733],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9783193,0.007254082,0.0003914218,0.01079879,0.00007816717,0.00007913693,0.0001723096,0.00002276622,0.002884034],"genre_scores_gemma":[0.993847,0.00006392931,0.003054384,0.002045994,0.00007100714,4.13427e-7,0.0007309883,0.00000198666,0.0001843112],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6715885,"threshold_uncertainty_score":0.3648664,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1480287196","doi":"10.1186/1471-2105-7-356","title":"New directions in biomedical text annotation: definitions, guidelines and corpus construction","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":169,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"U.S. National Library of Medicine; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; National Science Foundation","keywords":"Annotation; Computer science; Task (project management); Information retrieval; Natural language processing; Categorization; Set (abstract data type); Biomedical text mining; Executable; Focus (optics); Artificial intelligence; Unified Medical Language System; Text corpus; Text mining","retraction":null,"screen_n_in":null,"score":{"opus":0.03638827609910656,"gpt":0.2788558833373014,"spread":0.2424676072381949,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001253207,0.0001048881,0.0001126463,0.0001004408,0.00007273565,0.00003059929,0.00006404593,0.0001870185,0.00001333659],"category_scores_gemma":[0.0002373942,0.00009265472,0.00003305998,0.0001851076,0.0001994557,0.000007173261,0.00004409807,0.00007030617,0.00001227307],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001047973,"about_ca_system_score_gemma":0.0001247868,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001180169,"about_ca_topic_score_gemma":0.000263921,"domain_scores_codex":[0.9991825,0.00001821956,0.0004092055,0.0001196076,0.0001131846,0.0001572942],"domain_scores_gemma":[0.9996256,0.00002950721,0.0000881013,0.000127362,0.00005932805,0.0000701621],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00009850562,0.0001528681,0.0546947,0.0002000894,0.00004063789,0.000004897346,0.0002322914,0.0001241631,0.003986531,0.006740004,0.152099,0.7816263],"study_design_scores_gemma":[0.003625215,0.0005532669,0.06640336,0.0001755859,0.00005594333,0.0006293616,0.002148588,0.01968591,0.003054662,0.006025677,0.8968548,0.0007876422],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2429122,0.007520903,0.7344451,0.00269443,0.001332532,0.0004804686,0.0001386629,0.0002165928,0.01025908],"genre_scores_gemma":[0.0188722,0.00097537,0.9784367,0.0002871386,0.0004337459,0.00001600552,0.0004533347,0.00001175452,0.0005137247],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7808387,"threshold_uncertainty_score":0.377835,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2122174694","doi":"","title":"The National Center for Biomedical Ontology: Advancing Biomedicine through Structured \\nOrganization of Scientific Knowledge","year":2006,"lang":"en","type":"review","venue":"eScholarship (California Digital Library)","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":167,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Victoria","funders":"","keywords":"Ontology; Dissemination; Biomedicine; Context (archaeology); Computer science; Knowledge management; Data science; Resource (disambiguation); Open Biomedical Ontologies; World Wide Web; Upper ontology; Bioinformatics; Domain knowledge; Suggested Upper Merged Ontology","retraction":null,"screen_n_in":null,"score":{"opus":0.02821121261448315,"gpt":0.3067289090249404,"spread":0.2785176964104573,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000430125,0.0004585396,0.0008139266,0.0001789385,0.0003341004,0.0003446088,0.0008550941,0.0007653003,0.0000226685],"category_scores_gemma":[0.001629709,0.0002915837,0.0004414279,0.00069694,0.001179384,0.00004647022,0.0003665619,0.0003286973,0.00003791284],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004420904,"about_ca_system_score_gemma":0.0007694634,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":5.852944e-7,"about_ca_topic_score_gemma":0.000004559336,"domain_scores_codex":[0.9971989,0.0001355473,0.0009847841,0.000725931,0.0004145404,0.0005403258],"domain_scores_gemma":[0.9984202,0.0003226413,0.0005121037,0.000385653,0.0002080304,0.0001513889],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00007862983,0.0003244566,0.0002712663,0.003908112,0.0003276297,0.000002629425,0.00001213263,2.18088e-7,0.0001781987,0.000579149,0.1400914,0.8542262],"study_design_scores_gemma":[0.0004891315,0.0001822145,0.00001128944,0.0009251988,0.00008830403,0.0000292628,0.000008780524,0.000004359169,0.0002403662,0.001432877,0.996289,0.0002992247],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000195033,0.9827761,0.001529226,0.0002529904,0.0009729631,0.0007586579,0.01212118,0.000083096,0.001310755],"genre_scores_gemma":[0.003444779,0.8506684,0.007512903,0.0003197319,0.003353304,0.0002887999,0.1285502,0.0003997502,0.005462086],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.8561975,"threshold_uncertainty_score":0.9999536,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2356882517","doi":"10.1093/jamia/ocw028","title":"Learning statistical models of phenotypes using noisy labeled training data","year":2016,"lang":"en","type":"article","venue":"Journal of the American Medical Informatics Association","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":165,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"U.S. National Library of Medicine; National Institute of General Medical Sciences; National Human Genome Research Institute","keywords":"Computer science; Scalability; Machine learning; Artificial intelligence; Logistic regression; Feature (linguistics); Phenotype; Feature engineering; Implementation; Predictive modelling; Data mining; Deep learning; Database","retraction":null,"screen_n_in":null,"score":{"opus":0.04244371233329072,"gpt":0.3199957147633697,"spread":0.277552002430079,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001791887,0.0000777216,0.0002780033,0.00003675938,0.0000539902,0.00001093087,0.0005470338,0.00008675327,0.000009511594],"category_scores_gemma":[0.00766157,0.00004106326,0.00006488386,0.0001169885,0.000241196,0.00001789235,0.0002250221,0.0002111413,8.364459e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005598985,"about_ca_system_score_gemma":0.0003458037,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001296953,"about_ca_topic_score_gemma":0.000004430011,"domain_scores_codex":[0.998229,0.0001636287,0.000650657,0.0000579965,0.000720888,0.0001778686],"domain_scores_gemma":[0.997503,0.0003027714,0.001712582,0.0001960784,0.0001847432,0.0001008203],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003531915,0.000193542,0.02530753,0.00008374677,0.00106176,0.000006216517,0.002687851,0.001223687,0.06015851,0.0003479517,0.01089926,0.8976768],"study_design_scores_gemma":[0.01863375,0.01026807,0.03738775,0.003835388,0.001970065,0.0008504952,0.03515674,0.7517862,0.03580338,0.01015232,0.09165436,0.002501466],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8523424,0.00005520518,0.1464066,0.0008694736,0.0001672856,0.00003065959,0.00002674875,0.000003961166,0.00009762765],"genre_scores_gemma":[0.9790401,0.0001896,0.02022426,0.0003003438,0.0001839167,2.817653e-7,0.000007593072,0.000007058508,0.00004679202],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8951753,"threshold_uncertainty_score":0.9172169,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2805893819","doi":"10.1016/j.jbi.2018.06.001","title":"Patient similarity for precision medicine: A systematic review","year":2018,"lang":"en","type":"review","venue":"Journal of Biomedical Informatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":163,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Precision medicine; Computer science; Profiling (computer programming); Psychosocial; Data mining; Data science; Similarity (geometry); Identification (biology); Medicine; Cluster analysis; Data integration; Systematic review; Guideline; MEDLINE; Artificial intelligence; Machine learning; Pathology","retraction":null,"screen_n_in":null,"score":{"opus":0.04857467617237364,"gpt":0.3780683290191312,"spread":0.3294936528467576,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002794517,0.0004260281,0.003213514,0.0002363077,0.00007629142,0.00002334861,0.0007808895,0.0008508099,0.00002544786],"category_scores_gemma":[0.009724162,0.0002266318,0.0009879495,0.000290699,0.0005410403,0.000007551979,0.0002105752,0.0004280771,0.00001494429],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000604496,"about_ca_system_score_gemma":0.0005405135,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":3.858405e-7,"about_ca_topic_score_gemma":2.61886e-7,"domain_scores_codex":[0.994267,0.0002230088,0.004199093,0.0001534544,0.0008213147,0.0003361215],"domain_scores_gemma":[0.9942262,0.0004254379,0.003882478,0.0005307673,0.0005723002,0.0003628498],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001062551,0.00004976619,2.040158e-8,0.6087275,0.0003108614,0.000003284031,0.00005914452,1.191848e-8,5.278625e-7,0.000002490048,0.1737638,0.217072],"study_design_scores_gemma":[0.0002027077,0.001862731,1.435869e-8,0.3791087,0.00156203,0.0003897344,0.00005996736,0.000007507868,0.000001553405,0.00002157877,0.6166329,0.0001505373],"study_design_candidate":"systematic_review","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000001384984,0.9865053,0.01092923,0.0001734697,0.0009781912,0.001249677,0.00007289145,0.000008939168,0.00008097849],"genre_scores_gemma":[5.638692e-7,0.9892005,0.008625577,0.0009432707,0.0008615184,0.0000592712,0.0002106519,0.00002785016,0.00007080512],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.4428692,"threshold_uncertainty_score":0.9986174,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2547991767","doi":"10.1111/1365-2745.12698","title":"Towards a thesaurus of plant characteristics: an ecological contribution","year":2016,"lang":"en","type":"article","venue":"Journal of Ecology","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":154,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Sherbrooke","funders":"Deutsches Zentrum für integrative Biodiversitätsforschung Halle-Jena-Leipzig; Centre National de la Recherche Scientifique; Consejo Nacional de Investigaciones Científicas y Técnicas; Deutsche Forschungsgemeinschaft; Fondo para la Investigación Científica y Tecnológica; Inter-American Institute for Global Change Research; National Science Foundation","keywords":"Terminology; Ontology; Computer science; Thesaurus; Context (archaeology); Information retrieval; Semantics (computer science); Quality (philosophy); Resource (disambiguation); Semantic Web; World Wide Web; Data science; Ecology; Geography; Artificial intelligence; Linguistics; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.01480413597490569,"gpt":0.2692910647887432,"spread":0.2544869288138375,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004902972,0.00007901595,0.0002820234,0.00004679661,0.00002546558,0.000003442957,0.0001934834,0.0002663488,0.0001033154],"category_scores_gemma":[0.001097894,0.00004315625,0.00009114431,0.00002621333,0.0002105225,0.000003294806,0.00004994454,0.00007755838,0.000002750109],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001888296,"about_ca_system_score_gemma":0.0001295343,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001327533,"about_ca_topic_score_gemma":0.00001387773,"domain_scores_codex":[0.999117,0.0001284828,0.0003909252,0.0001068336,0.00008351784,0.000173275],"domain_scores_gemma":[0.9991466,0.00007435478,0.0003830868,0.0001124092,0.0001946943,0.00008888701],"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":[0.001161048,0.0007504987,0.03714434,0.00001317577,0.0002038361,0.0001022082,0.00010116,6.929524e-7,0.8495375,0.000684529,0.00243217,0.1078688],"study_design_scores_gemma":[0.00324955,0.01238473,0.8091234,0.00005166368,0.00008139958,0.0009069775,0.0001944106,0.00001364499,0.0926745,0.001645363,0.07944062,0.000233732],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9973417,0.0001163708,0.001120008,0.0008832955,0.0003950833,0.0000393686,0.00004790672,0.000003462433,0.00005278868],"genre_scores_gemma":[0.9984642,0.0002497878,0.0007697715,0.0001489947,0.0003155016,0.000001952897,0.00001131947,0.000004397987,0.00003409444],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7719791,"threshold_uncertainty_score":0.2054326,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1967653863","doi":"10.1016/j.jbi.2012.09.006","title":"A survey of SNOMED CT implementations","year":2012,"lang":"en","type":"article","venue":"Journal of Biomedical Informatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":152,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Victoria","funders":"University of Victoria","keywords":"SNOMED CT; Terminology; Systematized Nomenclature of Medicine; Implementation; Computer science; Medicine; Medical physics; Software engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.04487624873121079,"gpt":0.3473409887546474,"spread":0.3024647400234366,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001405473,0.00008217165,0.0002159913,0.0001070479,0.00002888036,0.000007397603,0.0002128169,0.00007948319,0.00005486257],"category_scores_gemma":[0.0009206426,0.00005806986,0.00009094762,0.0001844241,0.0002480634,0.00001070917,0.00007614077,0.0001218544,0.000004885525],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001109109,"about_ca_system_score_gemma":0.0001435628,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001472326,"about_ca_topic_score_gemma":0.000004551002,"domain_scores_codex":[0.9984977,0.00006145396,0.0008739738,0.00002825691,0.0003182811,0.0002203363],"domain_scores_gemma":[0.998828,0.00008476159,0.0005507388,0.0001248305,0.0001825856,0.0002291144],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003694649,0.0017277,0.2221555,0.0004694646,0.001246103,0.00001099988,0.00411708,0.00001002541,0.04334769,0.0001828887,0.2644972,0.4618659],"study_design_scores_gemma":[0.00374502,0.00308735,0.3645955,0.0001371007,0.0001508224,0.000668244,0.004677391,0.0002474244,0.03257179,0.00007577714,0.5895909,0.0004526679],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9802805,0.0008248393,0.01778334,0.0001755224,0.0005186845,0.0000525263,0.00006561772,0.000003811524,0.000295137],"genre_scores_gemma":[0.9880968,0.0001552846,0.01124709,0.0001999393,0.0001834605,9.684628e-7,0.00007964671,0.000005212481,0.00003163762],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4614133,"threshold_uncertainty_score":0.236802,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2136291980","doi":"10.1371/journal.pone.0089606","title":"Semantics in Support of Biodiversity Knowledge Discovery: An Introduction to the Biological Collections Ontology and Related Ontologies","year":2014,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":151,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Guelph","funders":"National Human Genome Research Institute; European Commission; National Institutes of Health; National Science Foundation","keywords":"Ontology; Open Biomedical Ontologies; Biodiversity; Computer science; Data science; Metadata; Upper ontology; Terminology; Information retrieval; Semantic Web; Ecology; World Wide Web; Biology; Ontology alignment","retraction":null,"screen_n_in":null,"score":{"opus":0.03628357306770225,"gpt":0.2482332829296641,"spread":0.2119497098619619,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003122335,0.00008810972,0.0002020121,0.00006775027,0.00009448692,0.00001216361,0.0001463719,0.0002039068,0.00001068751],"category_scores_gemma":[0.0007209503,0.00006163715,0.0000256626,0.0001944231,0.0003221719,0.000004275203,0.0001417858,0.0001059662,0.000004406962],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001045749,"about_ca_system_score_gemma":0.0000254549,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004885587,"about_ca_topic_score_gemma":0.0008889293,"domain_scores_codex":[0.9991671,0.0001662415,0.0001661415,0.0002806351,0.00005983713,0.0001600339],"domain_scores_gemma":[0.9995702,0.00004529163,0.00005140941,0.0002341747,0.00005403582,0.00004492725],"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":[0.0008767472,0.005102032,0.2543745,0.0001369039,0.0005964221,0.000006147705,0.002355584,0.00003100655,0.6789718,0.002109476,0.04434257,0.01109677],"study_design_scores_gemma":[0.003593906,0.01842469,0.4410876,0.00007118542,0.0003924459,0.00009303953,0.003197761,0.0004375089,0.3587133,0.001990083,0.1708711,0.001127447],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9919156,0.000133404,0.00023083,0.007140124,0.00009351224,0.0001307637,0.00001842091,0.00001888702,0.0003184],"genre_scores_gemma":[0.9979453,0.0001417282,0.001091332,0.0001346892,0.000101047,0.000009744449,0.00005418855,0.000003011602,0.0005189682],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3202585,"threshold_uncertainty_score":0.251349,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1986657538","doi":"10.1093/nar/gkv383","title":"PolySearch2: a significantly improved text-mining system for discovering associations between human diseases, genes, drugs, metabolites, toxins and more","year":2015,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":148,"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":"Genome Alberta; Canadian Institutes of Health Research; Alberta Innovates; Genome Canada","keywords":"DrugBank; UniProt; Information retrieval; Unified Medical Language System; Computer science; Computational biology; Ontology; Bioinformatics; Biology; Gene; Genetics; Drug","retraction":null,"screen_n_in":null,"score":{"opus":0.07102885753606152,"gpt":0.373355959485395,"spread":0.3023271019493335,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001566269,0.0001993929,0.0003474193,0.0001563777,0.000499268,0.0001627168,0.0004236114,0.0002817498,0.000002960091],"category_scores_gemma":[0.001019473,0.0001752713,0.0001039782,0.0002697645,0.0004527912,0.00001453151,0.0004709951,0.0002525029,0.000003571368],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001203441,"about_ca_system_score_gemma":0.0003196507,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002230911,"about_ca_topic_score_gemma":0.00002633003,"domain_scores_codex":[0.9974843,0.0002632448,0.0003255928,0.000602197,0.0005560994,0.0007685197],"domain_scores_gemma":[0.9984604,0.0001961832,0.00008410494,0.0004335946,0.0003208015,0.0005048939],"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":[0.0002822745,0.0002350453,0.1065665,0.0003740614,0.0006751122,0.00001372549,0.002423612,0.000004350291,0.7591395,0.001229966,0.008454219,0.1206017],"study_design_scores_gemma":[0.01474165,0.006377008,0.3241162,0.0004736076,0.0006976235,0.00003345038,0.07938778,0.003217072,0.189736,0.001020489,0.3770527,0.003146429],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9919701,0.004371451,0.001086971,0.000505829,0.00008355418,0.0005503126,0.0008784741,0.00007637964,0.0004768929],"genre_scores_gemma":[0.995286,0.00007405983,0.002423526,0.00002787994,0.000659387,0.0001345192,0.0006510888,0.00004986202,0.0006936619],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5694035,"threshold_uncertainty_score":0.7147358,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2061231608","doi":"10.1093/nar/gkq907","title":"The Protein Ontology: a structured representation of protein forms and complexes","year":2010,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":147,"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; National Human Genome Research Institute; National Institutes of Health","keywords":"Biology; Ontology; Representation (politics); Computational biology; Open Biomedical Ontologies; Process ontology; Bioinformatics; Computer science; Information retrieval; Suggested Upper Merged Ontology; Semantic Web","retraction":null,"screen_n_in":null,"score":{"opus":0.03836785129297262,"gpt":0.3623107203154941,"spread":0.3239428690225215,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007064475,0.00008031414,0.0001177073,0.00004410409,0.0002590252,0.00003599545,0.0003067613,0.0002188223,0.00001917517],"category_scores_gemma":[0.00117475,0.00004929461,0.00003486818,0.0001406088,0.001365498,0.000003128943,0.0002388438,0.0003698286,0.000002671723],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004473863,"about_ca_system_score_gemma":0.00006934933,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007822806,"about_ca_topic_score_gemma":0.0004142893,"domain_scores_codex":[0.9988492,0.0001439914,0.0001712989,0.0002532364,0.0002865664,0.000295694],"domain_scores_gemma":[0.9992549,0.00005774645,0.000052743,0.0003932573,0.0001703647,0.00007096404],"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":[0.0001422061,0.00001701679,0.001921495,0.00001844493,0.00001929237,0.000001119009,0.00007795833,5.063138e-8,0.9249241,0.001942232,0.0004310718,0.07050502],"study_design_scores_gemma":[0.0007058735,0.0008018469,0.03405709,0.00002141838,0.000003934434,0.0000212822,0.0007995041,0.00007477068,0.8898224,0.01000754,0.06355523,0.000129056],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9970364,0.000278822,0.00008421064,0.001171292,0.00003594681,0.0004494286,0.000007528199,0.00001118233,0.0009251717],"genre_scores_gemma":[0.9962776,0.00002858752,0.002735639,0.00001296918,0.00007790674,0.00007715118,0.00001299235,0.00001010332,0.0007670884],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07037596,"threshold_uncertainty_score":0.5031233,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2793303269","doi":"10.1109/tcbb.2018.2817488","title":"Automated ICD-9 Coding via A Deep Learning Approach","year":2018,"lang":"en","type":"article","venue":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":145,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Saskatchewan","funders":"Central South University; National Natural Science Foundation of China","keywords":"Deep learning; Artificial intelligence; Computer science; Convolutional neural network; ENCODE; Support vector machine; Machine learning; Coding (social sciences); Artificial neural network; Pattern recognition (psychology); Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.01649582494325603,"gpt":0.2844612318899851,"spread":0.267965406946729,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001881324,0.000165965,0.0001574898,0.0001032981,0.0004006635,0.00002508912,0.0001575538,0.000293846,0.00002639213],"category_scores_gemma":[0.00005633452,0.0001388893,0.00005971027,0.000139033,0.000519125,0.000007160248,0.00001390274,0.0001941844,0.00003355188],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001085343,"about_ca_system_score_gemma":0.00003728016,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000433583,"about_ca_topic_score_gemma":0.000003871045,"domain_scores_codex":[0.9991169,0.00006467442,0.000281016,0.0002147108,0.0000905856,0.0002321383],"domain_scores_gemma":[0.9994771,0.00009296749,0.00009215715,0.0001483562,0.0001050122,0.00008434179],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005365059,0.0004702247,0.001271717,0.0001895567,0.000657192,0.000003074858,0.001640072,0.02765001,0.01506005,0.0003879571,0.001702059,0.9504316],"study_design_scores_gemma":[0.001240406,0.00202085,0.001457697,0.0000296214,0.00005010798,0.0001935195,0.0004721422,0.9791113,0.005185131,0.001193717,0.008584737,0.0004607479],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05437627,0.00007886368,0.9441501,0.0001418032,0.000248248,0.0001064915,0.00002061079,0.0001644213,0.0007131727],"genre_scores_gemma":[0.845493,0.00006029359,0.1536308,0.0004203144,0.0001103669,0.00001266508,0.0001793971,0.000008811892,0.00008431428],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9514613,"threshold_uncertainty_score":0.5663739,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1974493848","doi":"10.1191/0962280202sm278ra","title":"Analysis of repeated events","year":2002,"lang":"en","type":"review","venue":"Statistical Methods in Medical Research","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":143,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Computer science; Event (particle physics); Marginal model; Medicine; Machine learning; Regression analysis","retraction":null,"screen_n_in":null,"score":{"opus":0.3234065665027732,"gpt":0.6439255386965067,"spread":0.3205189721937335,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01286105,0.0002872532,0.002206649,0.001006256,0.00004858003,0.000009986809,0.0009815005,0.001457415,0.002330281],"category_scores_gemma":[0.07452188,0.0002093389,0.0004303181,0.00292439,0.001272304,8.086699e-7,0.0006206868,0.001607958,0.00002109715],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000598489,"about_ca_system_score_gemma":0.0005540831,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006195995,"about_ca_topic_score_gemma":0.00002791995,"domain_scores_codex":[0.9874562,0.008023242,0.001255886,0.0008672555,0.001654641,0.0007427596],"domain_scores_gemma":[0.9918714,0.006529956,0.0001639846,0.0007627661,0.0001906527,0.0004812125],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001650432,0.0001543409,0.00002986535,0.001964403,0.0008012707,0.00007671796,0.00001047189,1.326239e-7,0.000004127715,0.0002359074,0.001408151,0.9952981],"study_design_scores_gemma":[0.0001911263,0.0003086672,0.0001017983,0.001996619,0.0006878852,0.000009033392,0.00001905717,0.0003839436,0.000007001878,0.0004429144,0.9956366,0.0002153335],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000004381192,0.9110173,0.08696418,0.00004615625,0.0001194295,0.0002677686,0.0001837096,0.000008887146,0.001388179],"genre_scores_gemma":[0.000007906288,0.8810972,0.1177279,0.00001886566,0.00009305478,0.00009269732,0.0003901587,0.00002877292,0.0005434736],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9950828,"threshold_uncertainty_score":0.9998389,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2067284187","doi":"10.1186/1472-6947-10-29","title":"Combining classifiers for robust PICO element detection","year":2010,"lang":"en","type":"article","venue":"BMC Medical Informatics and Decision Making","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":140,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University; Université de Montréal","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Computer science; Data mining; Identification (biology); Task (project management); Health informatics; Information retrieval; Element (criminal law); Process (computing); Population; Artificial intelligence; Machine learning; Pattern recognition (psychology); Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.03433126563978311,"gpt":0.3221974987188929,"spread":0.2878662330791098,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001024058,0.0001148666,0.0001506518,0.00005745314,0.0001695587,0.00005948184,0.0001634862,0.000328535,0.00003344143],"category_scores_gemma":[0.001659854,0.00008831479,0.00006397109,0.0000585675,0.0001437497,0.000005374944,0.0001532322,0.0001960588,0.000003288791],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005047802,"about_ca_system_score_gemma":0.00008724205,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":8.368696e-7,"about_ca_topic_score_gemma":0.00007920872,"domain_scores_codex":[0.9988834,0.00001605719,0.0004184445,0.0001384516,0.0003184398,0.0002251933],"domain_scores_gemma":[0.9990445,0.0004167891,0.0001210307,0.0001879021,0.00006061407,0.0001691231],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001277656,0.00002008294,0.0004329835,0.00005087006,0.00001476844,5.328915e-7,0.00006730851,0.00003211075,0.001462243,0.0003558838,0.001162391,0.996273],"study_design_scores_gemma":[0.004313088,0.001058814,0.001481908,0.000327336,0.00005440591,0.0001412997,0.00293375,0.8409411,0.004356825,0.005810096,0.1379552,0.0006262022],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3248566,0.00005959092,0.6743225,0.00001235352,0.0004053949,0.00008969365,0.000002898924,0.00001563539,0.0002353054],"genre_scores_gemma":[0.54506,0.00004744167,0.4541243,0.0005166451,0.0001805838,0.00002294217,0.00001532166,0.000008727965,0.00002403413],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9956468,"threshold_uncertainty_score":0.3601373,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2165034468","doi":"10.1093/nar/gku956","title":"Xenbase, the Xenopus model organism database; new virtualized system, data types and genomes","year":2014,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":138,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Institute of Child Health and Human Development; National Institutes of Health","keywords":"Xenopus; Biology; Genome; Computational biology; Model organism; Organism; Database; Gene; Genetics; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.09007029162540417,"gpt":0.361542129770755,"spread":0.2714718381453508,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001809416,0.0001394087,0.000174535,0.0000552349,0.0003170773,0.00009409461,0.001154572,0.0001919619,0.00004051125],"category_scores_gemma":[0.0009365203,0.00009060384,0.00002408267,0.0001609737,0.000523519,0.00000725077,0.001624955,0.0002946396,0.0000654095],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001516613,"about_ca_system_score_gemma":0.0001970157,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001463461,"about_ca_topic_score_gemma":0.00004559823,"domain_scores_codex":[0.998104,0.0003029453,0.000180871,0.0005655035,0.0004211645,0.0004255368],"domain_scores_gemma":[0.9980547,0.0001323726,0.00003826098,0.001487129,0.00009440599,0.000193165],"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":[0.0003124353,0.00009451947,0.0009183902,0.0002083568,0.0002087542,0.00001253685,0.0004501373,0.0000249752,0.4975049,0.008025656,0.2511563,0.241083],"study_design_scores_gemma":[0.001771929,0.0006749696,0.0006640906,0.00008442196,0.00005407785,0.00007206263,0.001358424,0.06310082,0.02007547,0.0008856697,0.9107867,0.0004713411],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8766134,0.02337364,0.06544418,0.01070616,0.0005557608,0.00118247,0.0006645914,0.000290899,0.02116889],"genre_scores_gemma":[0.9868442,0.0007682319,0.007388149,0.0002888662,0.0004929025,0.00001077914,0.0003260988,0.00003722143,0.003843497],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6596304,"threshold_uncertainty_score":0.3694717,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2002507929","doi":"10.1016/j.tree.2007.03.013","title":"Phenotype ontologies: the bridge between genomics and evolution","year":2007,"lang":"en","type":"article","venue":"Trends in Ecology & Evolution","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":137,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary; University of British Columbia","funders":"National Human Genome Research Institute; Johns Hopkins University; National Institutes of Health; National Science Foundation","keywords":"Genomics; Evolutionary developmental biology; Parallels; Biology; Evolutionary biology; Phenotype; Comparative genomics; Ontology; Gene; Genome; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.02300121471507478,"gpt":0.2948531741314533,"spread":0.2718519594163785,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007364598,0.0001344805,0.0001679617,0.0001289085,0.0001298541,0.000007795512,0.0001853053,0.0004036249,0.000009082213],"category_scores_gemma":[0.0002084489,0.0001061961,0.0000449193,0.0001920302,0.000475905,0.000003752228,0.0001312184,0.0001930575,0.000008036883],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001442696,"about_ca_system_score_gemma":0.00004904817,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001276473,"about_ca_topic_score_gemma":0.003177116,"domain_scores_codex":[0.9988651,0.00009393074,0.0002576624,0.0003216881,0.00007237277,0.0003892456],"domain_scores_gemma":[0.9994946,0.00009452688,0.00008893303,0.0002401768,0.00003024017,0.00005154226],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001199744,0.00005382333,0.8876677,0.000005829346,0.00004562625,0.00000426353,0.0001348173,0.00002412657,0.005456722,0.0006314135,0.002474246,0.1033814],"study_design_scores_gemma":[0.0004521931,0.0003058002,0.9904274,0.000003257779,0.00002171335,0.00001456443,0.0001580783,0.00006726022,0.0003044392,0.0009407089,0.007183144,0.0001214175],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9885532,0.00148238,0.007999401,0.0007593442,0.0002698522,0.00007256981,0.00000903441,0.0000318828,0.0008223808],"genre_scores_gemma":[0.998431,0.00006495907,0.000780447,0.00009242582,0.000271057,0.000009429955,0.00006211453,0.000009425371,0.0002791825],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.10326,"threshold_uncertainty_score":0.4330549,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2110279208","doi":"10.1371/journal.pone.0025513","title":"The Chemical Information Ontology: Provenance and Disambiguation for Chemical Data on the Biological Semantic Web","year":2011,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":136,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University","funders":"Biotechnology and Biological Sciences Research Council; Uppsala Universitet","keywords":"Computer science; Cheminformatics; Ontology; Context (archaeology); Semantic Web; Open Biomedical Ontologies; Data science; Domain (mathematical analysis); Ontology-based data integration; Web Ontology Language; Information retrieval; World Wide Web; Suggested Upper Merged Ontology; Bioinformatics","retraction":null,"screen_n_in":null,"score":{"opus":0.1332429346867007,"gpt":0.2638220714907671,"spread":0.1305791368040664,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003119492,0.00009072452,0.0001022843,0.000007429961,0.0001073799,0.00002062186,0.0003601746,0.0001695429,0.000003552778],"category_scores_gemma":[0.001582309,0.00004618609,0.00002196346,0.00003228991,0.0003534751,0.000005909484,0.0001916731,0.00009992165,0.000005977319],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005134456,"about_ca_system_score_gemma":0.00002507867,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003477487,"about_ca_topic_score_gemma":0.00000417544,"domain_scores_codex":[0.9993373,0.00003375905,0.0001601017,0.0001971784,0.00009587679,0.0001757861],"domain_scores_gemma":[0.9993129,0.0001309482,0.00007103022,0.000408098,0.00004252865,0.00003449675],"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":[0.0007774127,0.0006426868,0.001800811,0.00007228866,0.0002499128,4.662704e-7,0.0003001627,3.450352e-8,0.9320368,0.004221644,0.006190659,0.05370718],"study_design_scores_gemma":[0.001375727,0.001197327,0.003972459,0.0001156098,0.0001309636,0.00001103904,0.0004450612,0.003084122,0.9586662,0.003960522,0.02662675,0.0004141968],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9957668,0.0002684716,0.0004120228,0.002682049,0.00003457878,0.0003375823,0.00004685266,0.00002198091,0.0004297032],"genre_scores_gemma":[0.9965959,0.0002199535,0.002230028,0.0004959226,0.0001007865,0.00009489861,0.0002265842,0.000004726115,0.00003126523],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05329298,"threshold_uncertainty_score":0.1894286,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}