{"meta":{"query_hash":"aac46070376e","filters":{"venue":"Database"},"cohort_total":105,"direct_labels_cover":0,"predictions_cover":105,"exported":105,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/aac46070376e","api":"https://metacan.xera.ac/api/v1/cohort?venue=Database"},"results":[{"id":"W1829370794","doi":"10.1093/database/bav059","title":"G4RNA: an RNA G-quadruplex database","year":2015,"lang":"it","type":"article","venue":"Database","topic":"DNA and Nucleic Acid Chemistry","field":"Biochemistry, Genetics and Molecular Biology","cited_by":52,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Computer science; G-quadruplex; Information retrieval; Sequence (biology); Computational biology; Theoretical computer science; Data mining; Biology; DNA; Genetics","score_opus":0.03413014463313407,"score_gpt":0.2888167434363996,"score_spread":0.25468659880326555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1829370794","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9666015,0.004326929,0.0014315149,0.00048207035,0.0011579907,0.0003159889,0.012465464,0.0000765479,0.01314199],"genre_scores_gemma":[0.9279459,0.001103879,0.003914476,0.0014631992,0.0028547803,0.000028147844,0.057121944,0.00014330186,0.005424334],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99683297,0.00014840541,0.0005070031,0.0012263675,0.00048658357,0.0007987029],"domain_scores_gemma":[0.9954295,0.00001678754,0.00021719503,0.0028171334,0.00023141936,0.0012879586],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006305733,0.00056150876,0.00038189557,0.000059442602,0.00015494204,0.00012330285,0.000995697,0.00038259698,0.0004992753],"category_scores_gemma":[0.0003996548,0.00058822375,0.00014737944,0.0001916284,0.00028996638,0.00006043258,0.0010024327,0.00040154054,0.00059348694],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003707084,0.0005986401,0.00041107336,0.000109181514,0.000113986396,0.00022952791,0.000098114324,0.000009491318,0.7809949,0.00012459673,0.21387774,0.0030620636],"study_design_scores_gemma":[0.0018381778,0.00032516127,0.000039277333,0.0000665264,0.00013089998,0.00009338839,0.00062076957,0.0004972792,0.490465,0.000019364488,0.505164,0.00074012624],"about_ca_topic_score_codex":0.0002186063,"about_ca_topic_score_gemma":0.000045316032,"teacher_disagreement_score":0.2912863,"about_ca_system_score_codex":0.000058340887,"about_ca_system_score_gemma":0.0005222927,"threshold_uncertainty_score":0.9996569},"labels":[],"label_agreement":null},{"id":"W1967204795","doi":"10.1093/database/bar044","title":"Tripal: a construction toolkit for online genome databases","year":2011,"lang":"en","type":"article","venue":"Database","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":75,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Agriculture and Agri-Food Canada; Saskatchewan Pulse Growers; Agricultural Research Service; Clemson University; U.S. Department of Agriculture; National Science Foundation","keywords":"Computer science; World Wide Web; Python (programming language); Database; Biological database; User interface; Application programming interface; Bioinformatics; Biology","score_opus":0.0671172462474224,"score_gpt":0.2781780268173692,"score_spread":0.21106078056994682,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1967204795","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97539794,0.0013764115,0.009635872,0.00003362748,0.00029638264,0.00033448957,0.012461644,0.000007851872,0.00045580228],"genre_scores_gemma":[0.7749609,0.0015011181,0.20336029,0.000673816,0.00089626916,0.00013471191,0.01803891,0.000054578464,0.00037945443],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99926037,0.000016193206,0.00016272423,0.00031594207,0.000048865244,0.00019592824],"domain_scores_gemma":[0.9993684,0.000010327691,0.00005997503,0.0004322654,0.00006592324,0.00006308889],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000096758406,0.00012670505,0.00011605341,0.000030265133,0.000081771526,0.000006495801,0.0001385998,0.000035767272,0.000040348878],"category_scores_gemma":[0.00007656275,0.00012127363,0.00006210607,0.000040964536,0.000080541446,0.0000015501676,0.00015192555,0.000034367502,0.0000069169673],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035802368,0.00021660759,0.0032030388,0.000048216116,0.0001558087,0.000003904194,0.00007764492,0.0000032259534,0.98328626,0.0013438544,0.0039735287,0.007329875],"study_design_scores_gemma":[0.0016231935,0.0004208513,0.016747225,0.000011451185,0.000104533734,0.00004281349,0.0003273308,0.000038250026,0.122750334,0.00015069603,0.85732967,0.00045367944],"about_ca_topic_score_codex":0.000067119414,"about_ca_topic_score_gemma":0.00012101165,"teacher_disagreement_score":0.8605359,"about_ca_system_score_codex":0.0000048099164,"about_ca_system_score_gemma":0.00004005696,"threshold_uncertainty_score":0.49453953},"labels":[],"label_agreement":null},{"id":"W1974274010","doi":"10.1093/database/bas025","title":"HAltORF: a database of predicted out-of-frame alternative open reading frames in human","year":2012,"lang":"en","type":"article","venue":"Database","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":59,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Université de Sherbrooke","funders":"Canadian Institutes of Health Research","keywords":"Open reading frame; Human proteome project; Human genome; Ribosome profiling; Biology; Frame (networking); Computational biology; Transcriptome; Computer science; Genome; Translation (biology); Genetics; Gene; Gene expression; Messenger RNA; Proteomics; Peptide sequence","score_opus":0.04269381016478672,"score_gpt":0.32927023066012606,"score_spread":0.2865764204953393,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1974274010","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98797303,0.00050599116,0.006486098,0.000028867938,0.0002464145,0.0005220056,0.0029717854,0.000006909787,0.0012589064],"genre_scores_gemma":[0.9894112,0.000101125515,0.00764019,0.00006795314,0.00015601769,0.000051151128,0.0024167714,0.000021714008,0.00013389865],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988655,0.00014262377,0.00032245906,0.00026728841,0.00014844662,0.00025370886],"domain_scores_gemma":[0.99889416,0.000032606295,0.00020227062,0.0007206526,0.000051771112,0.00009857157],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00062300265,0.00014090644,0.00023356162,0.00007286449,0.000033870434,0.0000119628985,0.0005469742,0.00009156632,0.000108492466],"category_scores_gemma":[0.0003128558,0.00013396196,0.0000433461,0.00008251787,0.00006913106,0.00003541064,0.00063402526,0.00009133796,0.0000047941426],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010292025,0.00020910584,0.0049115885,0.00006212565,0.00004085665,0.0000030970853,0.00023184587,0.0000018140307,0.99166423,0.0015290059,0.00074265694,0.0005007688],"study_design_scores_gemma":[0.00054065906,0.00012587642,0.0005613024,0.00018532225,0.00001915671,0.0000019198571,0.00013704362,0.000020601334,0.99174315,0.00010657773,0.006406749,0.00015164856],"about_ca_topic_score_codex":0.000558025,"about_ca_topic_score_gemma":0.00006453781,"teacher_disagreement_score":0.005664092,"about_ca_system_score_codex":0.000009488508,"about_ca_system_score_gemma":0.00003993554,"threshold_uncertainty_score":0.546281},"labels":[],"label_agreement":null},{"id":"W1993679825","doi":"10.1093/database/bau061","title":"Finding needles in haystacks: linking scientific names, reference specimens and molecular data for Fungi","year":2014,"lang":"en","type":"article","venue":"Database","topic":"Plant Pathogens and Fungal Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":481,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Biodiversity Monitoring Institute","funders":"National Human Genome Research Institute; Agricultural Research Service; College of Pharmacy, University of Michigan; National Institutes of Health; National Brain Research Centre; University of Michigan; Ministry of Agriculture, Forestry and Fisheries; U.S. National Library of Medicine; University of Alberta; Beef Cattle Research Council; Université Catholique de Louvain","keywords":"RefSeq; Biology; Phylogenetic tree; Identification (biology); DNA sequencing; Cistron; Computational biology; Ribosomal DNA; Internal transcribed spacer; Information retrieval; Genome; Computer science; Genetics; DNA; Gene; Ecology","score_opus":0.042030844701357574,"score_gpt":0.282761934017969,"score_spread":0.24073108931661144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1993679825","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9545464,0.0034084006,0.010202859,0.00003222854,0.00013815053,0.0002492114,0.031064687,0.00001232446,0.00034576064],"genre_scores_gemma":[0.9463183,0.0001529121,0.0045360257,0.00015032111,0.00009348719,0.000012777591,0.048642606,0.000014633754,0.00007893569],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989679,0.00003683414,0.00013824462,0.00054062996,0.00008740242,0.00022903242],"domain_scores_gemma":[0.9990433,0.000031300613,0.00004435194,0.00076777703,0.000028204171,0.00008510663],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039798577,0.000113761016,0.00010708518,0.00006386597,0.000097509306,0.00008497748,0.00029253916,0.0000547901,0.0000055511146],"category_scores_gemma":[0.0002270173,0.000111340225,0.000019017147,0.00007218309,0.000060360937,0.0000142325025,0.00039935237,0.000053499854,0.0000040254135],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038927832,0.00003240379,0.0028132857,0.000057864392,0.000009201136,0.000008951563,0.000009954709,0.000007082937,0.9926749,0.0005324586,0.0024441916,0.0013707846],"study_design_scores_gemma":[0.0026797454,0.00037390797,0.01295695,0.0005439476,0.00014624052,0.000051085874,0.00033589124,0.015364382,0.16499688,0.00042361478,0.80084944,0.0012779399],"about_ca_topic_score_codex":0.000010490204,"about_ca_topic_score_gemma":0.00008456661,"teacher_disagreement_score":0.827678,"about_ca_system_score_codex":0.0000044365015,"about_ca_system_score_gemma":0.000040185543,"threshold_uncertainty_score":0.45403227},"labels":[],"label_agreement":null},{"id":"W2005813445","doi":"10.1093/database/baq031","title":"LPS-annotate: complete annotation of compositionally biased regions in the protein knowledgebase","year":2011,"lang":"en","type":"article","venue":"Database","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University","funders":"McGill University","keywords":"UniProt; Annotation; Protein sequencing; Computational biology; Genome; Biology; Database; Computer science; Gene; Genetics; Peptide sequence","score_opus":0.062374608092546455,"score_gpt":0.260019375891962,"score_spread":0.19764476779941553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2005813445","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9960885,0.00041405793,0.00075972383,0.00012484805,0.000035948637,0.00031605852,0.00095871306,0.0000016693906,0.0013004525],"genre_scores_gemma":[0.99579227,0.000038764978,0.002703447,0.00016638162,0.000041892443,0.000056833458,0.0011640495,0.00000750295,0.000028884928],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993478,0.000095448886,0.00018245552,0.00018072827,0.000076115575,0.00011742352],"domain_scores_gemma":[0.99946254,0.000017254653,0.00007098014,0.00034502597,0.00008064123,0.000023542552],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002124524,0.00008880739,0.00008988878,0.000037394297,0.00005516374,0.000004523547,0.00018551746,0.000029172776,0.00001237085],"category_scores_gemma":[0.000040456584,0.00007029063,0.000040839554,0.00009492022,0.00009538664,0.0000011680124,0.00007204325,0.000046932,0.0000073887118],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001221659,0.00023038994,0.0016516063,0.000024774019,0.000028755137,0.0000068106106,0.0004928767,0.000008410742,0.99293816,0.0024787546,0.0017703123,0.00024700174],"study_design_scores_gemma":[0.0040821065,0.0013859938,0.24411887,0.00017091437,0.000104795174,0.000048827216,0.0016583255,0.0004166148,0.66527605,0.0025071648,0.07936938,0.0008609572],"about_ca_topic_score_codex":0.00011546805,"about_ca_topic_score_gemma":0.00023305348,"teacher_disagreement_score":0.32766208,"about_ca_system_score_codex":0.0000035185203,"about_ca_system_score_gemma":0.000036482692,"threshold_uncertainty_score":0.28663686},"labels":[],"label_agreement":null},{"id":"W2047689005","doi":"10.1093/database/baq018","title":"The systematic annotation of the three main GPCR families in Reactome","year":2010,"lang":"en","type":"article","venue":"Database","topic":"Receptor Mechanisms and Signaling","field":"Biochemistry, Genetics and Molecular Biology","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Institute for Cancer Research","funders":"National Human Genome Research Institute; Sixth Framework Programme; National Institutes of Health; European Commission","keywords":"G protein-coupled receptor; UniProt; Computational biology; Computer science; Annotation; Database; Biology; Bioinformatics; Receptor; Gene; Genetics","score_opus":0.00734967211467777,"score_gpt":0.22838758613593957,"score_spread":0.2210379140212618,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2047689005","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9983777,0.00019124665,0.00070320826,0.000059286565,0.00024205954,0.00023216894,0.00008273004,0.0000022381112,0.00010936396],"genre_scores_gemma":[0.99942344,0.000046076184,0.00027742633,0.000035752364,0.000044233566,0.00002222631,0.000088444314,0.0000064380692,0.000055962817],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994768,0.000053822318,0.0001709313,0.0001056718,0.00009837267,0.00009441397],"domain_scores_gemma":[0.99938565,0.000036174024,0.00008267142,0.00045282676,0.000027326267,0.000015346133],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004999685,0.00005839996,0.00007513304,0.000014569296,0.000058609578,0.000012917725,0.00021345586,0.000043541142,0.000008333883],"category_scores_gemma":[0.00025511184,0.000031142517,0.000036214125,0.00006679855,0.00004321517,0.0000033133615,0.00007847276,0.000085708474,0.0000025749373],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009405615,0.00001033969,0.00046229266,0.00016970719,0.000006147697,4.1547057e-7,0.000035045934,0.0000044814883,0.9976363,0.001398795,0.0001291093,0.00013793347],"study_design_scores_gemma":[0.00025225434,0.000033162767,0.0019280846,0.00023547644,0.000014122989,0.0000069699217,0.0004614482,0.00040585786,0.99466324,0.00038433186,0.0015203113,0.00009472418],"about_ca_topic_score_codex":0.00006971824,"about_ca_topic_score_gemma":0.0014880089,"teacher_disagreement_score":0.0029730708,"about_ca_system_score_codex":0.0000028304696,"about_ca_system_score_gemma":0.000027189897,"threshold_uncertainty_score":0.1269955},"labels":[],"label_agreement":null},{"id":"W2051020903","doi":"10.1093/database/bat087","title":"DBM-DB: the diamondback moth genome database","year":2014,"lang":"en","type":"article","venue":"Database","topic":"Insect Resistance and Genetics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":69,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ministry of Agriculture; University of British Columbia","funders":"National Natural Science Foundation of China; Yuhan","keywords":"Diamondback moth; dBm; Genome; Annotation; Gene Annotation; Plutella; Genomics; Biology; Computer science; Database; Computational biology; Gene; Bioinformatics; Genetics; Larva; Ecology","score_opus":0.007791138652176461,"score_gpt":0.229161108559944,"score_spread":0.22136996990776756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2051020903","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9726033,0.0025883303,0.015710197,0.0005177639,0.00034606332,0.00035413873,0.0021724731,0.000032302483,0.0056753918],"genre_scores_gemma":[0.98446065,0.0008116484,0.0021306039,0.0028208273,0.0009988627,0.00003516836,0.0069992663,0.000042481992,0.0017004918],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988854,0.000090289155,0.00016760576,0.00037436467,0.0001617493,0.0003205685],"domain_scores_gemma":[0.99842644,0.000021997825,0.000060054124,0.0013405595,0.0000527022,0.000098267585],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032341506,0.00017088006,0.00011108828,0.000023575385,0.0001628946,0.000037036796,0.0004399076,0.00006830609,0.00007955054],"category_scores_gemma":[0.00010801683,0.0001252428,0.00006715198,0.00008840384,0.00011575104,0.0000057899883,0.00027159473,0.000117009105,0.00017107598],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007028512,0.00006563541,0.0005767482,0.000031883206,0.000036405596,0.0000064585843,0.000034791214,0.00003767074,0.9652584,0.0006375934,0.032066055,0.0011780739],"study_design_scores_gemma":[0.00050559145,0.0001176434,0.0015555111,0.000010978521,0.000033985052,0.000012901981,0.000045666526,0.00014788898,0.2725094,0.00004876947,0.72472286,0.00028878317],"about_ca_topic_score_codex":0.000040170216,"about_ca_topic_score_gemma":0.00021067233,"teacher_disagreement_score":0.69274896,"about_ca_system_score_codex":0.0000068347886,"about_ca_system_score_gemma":0.000046149406,"threshold_uncertainty_score":0.5107253},"labels":[],"label_agreement":null},{"id":"W2099131261","doi":"10.1093/database/baq037","title":"The Biomolecular Interaction Network Database in PSI-MI 2.5","year":2011,"lang":"en","type":"article","venue":"Database","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":97,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Human Genome Research Institute; National Institutes of Health; Ontario Genomics; Ontario Genomics Institute; Genome Canada","keywords":"Identifier; Computer science; Database; Download; World Wide Web","score_opus":0.019740439397880078,"score_gpt":0.24994526918287382,"score_spread":0.23020482978499374,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2099131261","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7529288,0.010413686,0.18554543,0.0007768613,0.0053096367,0.0018126527,0.0013477461,0.00010421504,0.041760966],"genre_scores_gemma":[0.9895911,0.0010829823,0.004851771,0.000860808,0.00044737774,0.000042899494,0.002890844,0.00002897269,0.00020323781],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990901,0.00005349186,0.00025073878,0.00021475182,0.000078844234,0.00031211736],"domain_scores_gemma":[0.9991025,0.000014993668,0.000085174965,0.00069950713,0.000025504398,0.00007237566],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043529554,0.0001267134,0.00008030609,0.000025408452,0.00012033634,0.000029888828,0.0002847775,0.00007150271,0.00004427614],"category_scores_gemma":[0.00003947037,0.00009946756,0.00004768746,0.00011690388,0.00006869715,0.000012091229,0.0002813137,0.00014481082,0.000054051314],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022911485,0.0007035779,0.010535882,0.00014724325,0.0003864869,0.00022933946,0.00088034774,0.0005147123,0.3040234,0.017145686,0.56144404,0.101698086],"study_design_scores_gemma":[0.0014698232,0.0002743512,0.001955673,0.00010893671,0.000044862478,0.00008261391,0.00048682248,0.0043487954,0.052205414,0.0008796711,0.9374338,0.000709261],"about_ca_topic_score_codex":0.00012188915,"about_ca_topic_score_gemma":0.0005492129,"teacher_disagreement_score":0.3759897,"about_ca_system_score_codex":0.000009765919,"about_ca_system_score_gemma":0.00003495621,"threshold_uncertainty_score":0.40561694},"labels":[],"label_agreement":null},{"id":"W2100190412","doi":"10.1093/database/bat070","title":"Phenol-Explorer 3.0: a major update of the Phenol-Explorer database to incorporate data on the effects of food processing on polyphenol content","year":2013,"lang":"en","type":"article","venue":"Database","topic":"Phytochemicals and Antioxidant Activities","field":"Medicine","cited_by":868,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Institut National Du Cancer; Danone","keywords":"Polyphenol; Database; Phenol; Food science; Computer science; Chemistry; Biochemistry; Organic chemistry","score_opus":0.06410583990095763,"score_gpt":0.2677329195989637,"score_spread":0.20362707969800609,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2100190412","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9903519,0.00030200343,0.0002046178,0.0032952323,0.00018963931,0.0019644382,0.0033878135,0.000059954655,0.000244378],"genre_scores_gemma":[0.9943049,0.000049403257,0.0006938269,0.0033596805,0.00019129862,0.00021909624,0.0010574792,0.000060329632,0.00006398006],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99759734,0.00012765898,0.0005209012,0.00062437064,0.00069960556,0.00043013302],"domain_scores_gemma":[0.99592966,0.00036133593,0.0004039798,0.002924325,0.00018507562,0.00019563329],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034889675,0.00036562717,0.00055512425,0.00012230396,0.00014103307,0.000041663414,0.0009776376,0.000060115162,0.00012454254],"category_scores_gemma":[0.0009165209,0.0001938559,0.00010258814,0.0004299387,0.0002888057,0.000564674,0.0009962575,0.00039905906,0.000101982914],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000615549,0.0011882447,0.0006057305,0.0011032156,0.00019904213,0.000014396244,0.00063493865,0.0000010629767,0.96535045,0.0014992893,0.024752254,0.0040358435],"study_design_scores_gemma":[0.002073611,0.0006745822,0.0023087831,0.0035651107,0.00025240783,0.000009569616,0.0009931119,0.00039871124,0.9878734,0.00027414883,0.001269435,0.00030715094],"about_ca_topic_score_codex":0.0001668389,"about_ca_topic_score_gemma":0.000014999088,"teacher_disagreement_score":0.02348282,"about_ca_system_score_codex":0.000039233004,"about_ca_system_score_gemma":0.00014547422,"threshold_uncertainty_score":0.79052144},"labels":[],"label_agreement":null},{"id":"W2105772474","doi":"10.1093/database/bas031","title":"Phenol-Explorer 2.0: a major update of the Phenol-Explorer database integrating data on polyphenol metabolism and pharmacokinetics in humans and experimental animals","year":2012,"lang":"en","type":"article","venue":"Database","topic":"Phytochemicals and Antioxidant Activities","field":"Medicine","cited_by":188,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"European Social Fund; Instituto de Salud Carlos III; Institut National Du Cancer; Ministerio de Ciencia e Innovación; Centro de Investigación Biomédica en Red-Fisiopatología de la Obesidad y Nutrición; University of Alberta; Danone","keywords":"Polyphenol; Database; Phenol; Chemistry; Computer science; Biochemistry; Organic chemistry","score_opus":0.051556922381446754,"score_gpt":0.32397729840762185,"score_spread":0.2724203760261751,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2105772474","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98851174,0.00674882,0.000036374306,0.00035266936,0.00014547173,0.00047555886,0.003439858,0.000036744317,0.00025273385],"genre_scores_gemma":[0.99525154,0.00045505908,0.0022618957,0.000640584,0.00032478903,0.000039357168,0.0009670921,0.000045005523,0.000014695482],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9982108,0.00009449489,0.00041795324,0.00048914616,0.00034608415,0.00044152065],"domain_scores_gemma":[0.99842566,0.000104205756,0.00016574186,0.0010776055,0.000029652741,0.00019714244],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040810416,0.00031277727,0.00047043845,0.00012672524,0.000098240496,0.000030946856,0.00031883933,0.00005279934,0.00014602533],"category_scores_gemma":[0.00015915385,0.0002160496,0.00004275628,0.00019762048,0.0003067986,0.00076933653,0.0009978936,0.00038188242,0.0000063241027],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036503022,0.00075007323,0.008662005,0.00016394361,0.000082174636,0.000012949851,0.0019605139,1.2832209e-7,0.9836436,0.0014751107,0.0021344095,0.0007500756],"study_design_scores_gemma":[0.0041285693,0.0000884757,0.011164145,0.0006691394,0.00031656225,0.000042632248,0.004978073,0.0005406815,0.9713572,0.000041085455,0.006263112,0.00041030045],"about_ca_topic_score_codex":0.00012904702,"about_ca_topic_score_gemma":0.000011853431,"teacher_disagreement_score":0.012286362,"about_ca_system_score_codex":0.000024596324,"about_ca_system_score_gemma":0.000036558853,"threshold_uncertainty_score":0.88102466},"labels":[],"label_agreement":null},{"id":"W2105939477","doi":"10.1093/database/bar053","title":"The Comprehensive Phytopathogen Genomics Resource: a web-based resource for data-mining plant pathogen genomes","year":2011,"lang":"en","type":"article","venue":"Database","topic":"Plant Pathogens and Fungal Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; Agriculture and Agri-Food Canada","funders":"","keywords":"Oomycete; GenBank; Genome; Biology; Genomics; UniProt; Genome browser; Computational biology; DNA sequencing; Reference genome; Genome project; Annotation; Genetics; Gene","score_opus":0.05445920231675954,"score_gpt":0.25408823258207636,"score_spread":0.1996290302653168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2105939477","genre_codex":"empirical","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5341292,0.015740355,0.0036472392,0.00010233548,0.00026561203,0.0014046121,0.44292647,0.000092085385,0.0016921152],"genre_scores_gemma":[0.29937363,0.003034047,0.05818267,0.0070916535,0.0028416046,0.0007507598,0.62726533,0.00042103426,0.0010392817],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99822694,0.0001247353,0.0003058759,0.0007017583,0.00015756524,0.00048315254],"domain_scores_gemma":[0.9977127,0.00013197337,0.00016133043,0.0017295345,0.00007113313,0.00019335003],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039925045,0.00026988264,0.00021098768,0.000043800297,0.00042836057,0.00005116637,0.0009496639,0.00010155373,0.000012844713],"category_scores_gemma":[0.0001344622,0.00021117252,0.00011628512,0.00007341339,0.00013591052,0.000009192055,0.0005566797,0.000088157365,0.000012555134],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013541416,0.00013074647,0.0019544414,0.00006326861,0.000107984495,0.000070370574,0.000080261365,0.000016827953,0.9205663,0.00006175223,0.07026844,0.005325471],"study_design_scores_gemma":[0.00091925793,0.00017181167,0.0010041925,0.000023264925,0.000111047106,0.000032405896,0.00038706049,0.0028685199,0.011477833,0.000005735717,0.9826548,0.00034406342],"about_ca_topic_score_codex":0.000010475278,"about_ca_topic_score_gemma":0.00006327751,"teacher_disagreement_score":0.91238636,"about_ca_system_score_codex":0.0000130843955,"about_ca_system_score_gemma":0.00019391679,"threshold_uncertainty_score":0.86113656},"labels":[],"label_agreement":null},{"id":"W2106831214","doi":"10.1093/database/bar023","title":"The modENCODE Data Coordination Center: lessons in harvesting comprehensive experimental details","year":2011,"lang":"en","type":"article","venue":"Database","topic":"Evolution and Genetic Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Institute for Cancer Research","funders":"Basic Energy Sciences; Office of Science; National Institutes of Health; Wellcome Trust; National Human Genome Research Institute; U.S. Department of Energy","keywords":"Computer science; Metadata; Protocol (science); Research center; Encyclopedia; Caenorhabditis elegans; Set (abstract data type); World Wide Web; Information retrieval; Library science; Biology; Programming language","score_opus":0.10123420813286024,"score_gpt":0.33206898989045897,"score_spread":0.23083478175759872,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2106831214","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9728816,0.0019265718,0.02022756,0.00031732905,0.0002887258,0.00032914575,0.0016984125,0.000021553844,0.002309098],"genre_scores_gemma":[0.99153703,0.00013740195,0.0031555858,0.000136682,0.000040582265,0.00001232318,0.004708968,0.000010686284,0.00026073924],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992628,0.00006814169,0.0001456861,0.00027642562,0.0000774687,0.00016944323],"domain_scores_gemma":[0.99914104,0.000011347666,0.000049774644,0.00071731274,0.00003441277,0.000046114863],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014746086,0.0000861324,0.0000578763,0.00001954555,0.00010498921,0.000019057941,0.00039596952,0.000038141956,0.000009837336],"category_scores_gemma":[0.00006046323,0.00007334303,0.000016641978,0.000050285103,0.00007911039,0.000011837879,0.00048912753,0.000063480766,0.000011315302],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002479728,0.00079402287,0.016479723,0.000024908188,0.0000669173,0.000024753002,0.00040400206,0.00023198377,0.9491851,0.0042059454,0.020837452,0.0074972487],"study_design_scores_gemma":[0.006857238,0.000625741,0.051817548,0.00015060934,0.00006159369,0.00017534761,0.0067340727,0.32655704,0.28427264,0.00030037193,0.32085755,0.0015902274],"about_ca_topic_score_codex":0.00017629768,"about_ca_topic_score_gemma":0.0011960097,"teacher_disagreement_score":0.66491246,"about_ca_system_score_codex":0.000011208729,"about_ca_system_score_gemma":0.00003354271,"threshold_uncertainty_score":0.2990842},"labels":[],"label_agreement":null},{"id":"W2109144185","doi":"10.1093/database/bat068","title":"yApoptosis: yeast apoptosis database","year":2013,"lang":"en","type":"article","venue":"Database","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Fondation Chalmers","keywords":"Programmed cell death; Yeast; Computational biology; Apoptosis; Biology; Database; Resource (disambiguation); Computer science; World Wide Web; Genetics","score_opus":0.009843973817082024,"score_gpt":0.22529482374096857,"score_spread":0.21545084992388655,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2109144185","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94952667,0.0011376314,0.03210723,0.0007032949,0.00078413956,0.0009258983,0.0030972569,0.0000805459,0.011637365],"genre_scores_gemma":[0.97326666,0.0003731968,0.011585927,0.0021528765,0.0006075588,0.00013087751,0.010728928,0.000041397074,0.0011125923],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989951,0.000024738445,0.00023817515,0.0002907341,0.00012088894,0.0003303167],"domain_scores_gemma":[0.9988265,0.000005962718,0.000074804404,0.0008521342,0.00006069069,0.0001799003],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00014592148,0.00017536178,0.00012284753,0.000038340993,0.00009162963,0.000064357606,0.00030129342,0.00009318422,0.0004260658],"category_scores_gemma":[0.00003492237,0.00016030257,0.0000675172,0.00008439413,0.000062670464,0.000019991932,0.00034974067,0.00011176995,0.0008076297],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026580086,0.000098727556,0.00040223473,0.00004846812,0.00007233882,9.755483e-7,0.00003159874,0.000015554111,0.49980053,0.00048481164,0.48751086,0.011507329],"study_design_scores_gemma":[0.0016288495,0.00022859637,0.00081745046,0.00008698481,0.000079923695,0.00003275885,0.00041202863,0.002796409,0.3571755,0.00021264753,0.6354303,0.0010985847],"about_ca_topic_score_codex":0.00013169885,"about_ca_topic_score_gemma":0.00001801064,"teacher_disagreement_score":0.1479194,"about_ca_system_score_codex":0.000007926505,"about_ca_system_score_gemma":0.00003883799,"threshold_uncertainty_score":0.9999704},"labels":[],"label_agreement":null},{"id":"W2111476723","doi":"10.1093/database/bar032","title":"NetSlim: high-confidence curated signaling maps","year":2011,"lang":"en","type":"article","venue":"Database","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Scheme for Promotion of Academic and Research Collaboration","keywords":"Computer science; Visualization; Set (abstract data type); Resource (disambiguation); Computational biology; Database; Information retrieval; Data science; World Wide Web; Data mining; Biology; Programming language","score_opus":0.022612611316079403,"score_gpt":0.2250225638603589,"score_spread":0.20240995254427951,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111476723","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8898342,0.0015828819,0.094409585,0.00012830777,0.0009980878,0.0004870373,0.0014909329,0.00007755117,0.010991369],"genre_scores_gemma":[0.98790133,0.00011873953,0.008016425,0.00067975227,0.0002001745,0.000009483812,0.0027863241,0.000016000246,0.00027179596],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99929684,0.000020118088,0.00019056263,0.00020014957,0.00006848392,0.0002238394],"domain_scores_gemma":[0.9993432,0.0000050828803,0.00007225992,0.00044315893,0.000044316344,0.00009195567],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016190684,0.00011903668,0.00008979045,0.000022388482,0.000062597814,0.000017881699,0.00021769718,0.00008317584,0.0001856296],"category_scores_gemma":[0.00001977825,0.00011075493,0.00003555862,0.00006135346,0.00004925996,0.000007762435,0.0001433924,0.00008692695,0.000111753274],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003135563,0.00017227701,0.0009089886,0.000082228056,0.00016540247,0.00005348479,0.00043166341,0.00009086006,0.8589731,0.013180795,0.1163962,0.009231461],"study_design_scores_gemma":[0.0017240221,0.0004572916,0.00091150496,0.00009843077,0.00008513871,0.00008007626,0.00040471047,0.0014830867,0.82402056,0.003031242,0.16659379,0.0011101204],"about_ca_topic_score_codex":0.00012942788,"about_ca_topic_score_gemma":0.000031078118,"teacher_disagreement_score":0.09806706,"about_ca_system_score_codex":0.0000042086117,"about_ca_system_score_gemma":0.000037865604,"threshold_uncertainty_score":0.45164552},"labels":[],"label_agreement":null},{"id":"W2113769137","doi":"10.1093/database/bav008","title":"mycoCLAP, the database for characterized lignocellulose-active proteins of fungal origin: resource and text mining curation support","year":2015,"lang":"en","type":"article","venue":"Database","topic":"Biofuel production and bioconversion","field":"Engineering","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Resource (disambiguation); Database; World Wide Web; Data curation; Information retrieval","score_opus":0.04390842278676899,"score_gpt":0.25269453764247773,"score_spread":0.20878611485570875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2113769137","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9797413,0.00032223653,0.009137497,0.0011666312,0.000754466,0.002168715,0.0055881008,0.00024607842,0.00087500067],"genre_scores_gemma":[0.9886385,0.00008929573,0.004814393,0.00017757431,0.00051907275,0.00014076737,0.005094041,0.000047110003,0.00047924474],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99925077,0.00003381727,0.00019592725,0.00020992219,0.00014968218,0.00015986786],"domain_scores_gemma":[0.99938,0.00004327225,0.000071360366,0.0003402319,0.00006760939,0.00009753585],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039811237,0.00012970748,0.00013618756,0.00005821998,0.00006940919,0.000024826582,0.000107172375,0.000048936552,0.000045691086],"category_scores_gemma":[0.00009593831,0.00009825822,0.000027291333,0.00011177317,0.00006642483,0.00047615997,0.000062440326,0.00011305378,0.00001174865],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009963552,0.000116938805,0.00038141455,0.0010334352,0.00008958263,0.000011357656,0.0024027296,0.000020121488,0.900762,0.00030511053,0.08024623,0.013634699],"study_design_scores_gemma":[0.0014593536,0.00015025605,0.00015907624,0.00005588966,0.00004735677,0.000025873725,0.0014753267,0.007932519,0.3643343,0.000009547494,0.624121,0.00022949072],"about_ca_topic_score_codex":0.00001671246,"about_ca_topic_score_gemma":0.000004103608,"teacher_disagreement_score":0.5438748,"about_ca_system_score_codex":0.000027687924,"about_ca_system_score_gemma":0.00004022848,"threshold_uncertainty_score":0.4006854},"labels":[],"label_agreement":null},{"id":"W2118284237","doi":"10.1093/database/bas036","title":"Recent advances in biocuration: Meeting Report from the fifth International Biocuration Conference","year":2012,"lang":"en","type":"article","venue":"Database","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Human Genome Research Institute; George Washington University; Wellcome Trust; Georgetown University; Institute of Genetics; University of Oxford; Ontario Institute for Cancer Research","keywords":"Library science; World Wide Web; Promotion (chess); Political science; Computer science","score_opus":0.03594583616335801,"score_gpt":0.3235142753631416,"score_spread":0.2875684391997836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2118284237","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9322315,0.042993978,0.010719639,0.007707835,0.002225937,0.00023637715,0.0007094216,0.000040745665,0.003134604],"genre_scores_gemma":[0.97707504,0.008876159,0.005165013,0.0004676354,0.0008352695,0.000026256721,0.007468792,0.000006637407,0.000079183505],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993414,0.00005377801,0.00017897335,0.00017592168,0.00011932551,0.00013058026],"domain_scores_gemma":[0.99954987,0.000039084895,0.00008749713,0.00023996235,0.000045979483,0.00003759526],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032277027,0.000070743634,0.000057130295,0.000014357456,0.000045403434,0.000020270327,0.00015879181,0.00005742065,0.00008836689],"category_scores_gemma":[0.00075482304,0.000049350932,0.000016678605,0.00005853199,0.000072449606,0.000019210795,0.00010250494,0.00006984292,0.000012828464],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016388379,0.00022893169,0.15018542,0.000011080992,0.000051686144,0.000031967258,0.0006259674,0.000012017676,0.12981674,0.00041041727,0.03265262,0.68580925],"study_design_scores_gemma":[0.00017373414,0.000015706206,0.006953333,0.000025053943,0.0000042094134,0.000013271561,0.00027387662,0.00008046814,0.014682802,0.000027730403,0.9776689,0.00008095729],"about_ca_topic_score_codex":0.000053138814,"about_ca_topic_score_gemma":0.00025498,"teacher_disagreement_score":0.94501626,"about_ca_system_score_codex":0.000009128554,"about_ca_system_score_gemma":0.000033403372,"threshold_uncertainty_score":0.20124726},"labels":[],"label_agreement":null},{"id":"W2118527670","doi":"10.1093/database/bar026","title":"International Cancer Genome Consortium Data Portal--a one-stop shop for cancer genomics data","year":2011,"lang":"en","type":"article","venue":"Database","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":672,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Institute for Cancer Research","funders":"","keywords":"Computer science; Genome; Genomics; Interface (matter); Genome browser; Software; Computational biology; World Wide Web; Biology; Gene; Genetics; Operating system","score_opus":0.12202126051096739,"score_gpt":0.3372931504936901,"score_spread":0.21527188998272268,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2118527670","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24379762,0.012159085,0.024510426,0.0010192817,0.0040715435,0.0013099799,0.7091202,0.00004635748,0.003965491],"genre_scores_gemma":[0.33512455,0.06175594,0.040426787,0.0048715877,0.0064667114,0.00051627966,0.5490809,0.0002272381,0.0015299851],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983488,0.000012955341,0.00030535544,0.00089540484,0.00012601182,0.0003114832],"domain_scores_gemma":[0.99687374,0.00002288356,0.00015888149,0.002668346,0.00013128082,0.00014485113],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025855468,0.00019136668,0.00017418839,0.000042271447,0.000081002596,0.00004040848,0.0019633821,0.00009486498,0.00068131735],"category_scores_gemma":[0.00017865788,0.00021138028,0.000040154653,0.00004694524,0.00009442149,0.000029681127,0.002240586,0.000088286404,0.000013080724],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012042176,0.0007647421,0.013361495,0.00016432999,0.0014159408,0.000046111825,0.00023849626,0.00013149143,0.5993649,0.001463344,0.36270362,0.01914137],"study_design_scores_gemma":[0.0007927033,0.00004499093,0.001047136,0.000014404504,0.00014215705,0.0000067745627,0.000059062004,0.001272851,0.0150603345,0.000022426444,0.98119366,0.00034348466],"about_ca_topic_score_codex":0.0016241916,"about_ca_topic_score_gemma":0.0041657803,"teacher_disagreement_score":0.61849004,"about_ca_system_score_codex":0.00003819407,"about_ca_system_score_gemma":0.00046233422,"threshold_uncertainty_score":0.8619838},"labels":[],"label_agreement":null},{"id":"W2125951746","doi":"10.1093/database/bau108","title":"The Virtual Xenbase: transitioning an online bioinformatics resource to a private cloud","year":2014,"lang":"en","type":"article","venue":"Database","topic":"Genetics, Bioinformatics, and Biomedical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Institute of Child Health and Human Development; University of Calgary","keywords":"Cloud computing; Resource (disambiguation); Computer science; World Wide Web; Operating system; Computer network","score_opus":0.021926973331574562,"score_gpt":0.2858661606597033,"score_spread":0.2639391873281287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2125951746","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87327546,0.00012392891,0.120719485,0.0029076445,0.0003977372,0.0005287091,0.001318254,0.00004963479,0.0006791268],"genre_scores_gemma":[0.88095635,0.0009213598,0.065164,0.014281094,0.0038761857,0.000079571226,0.03231939,0.00011621396,0.0022858465],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.998434,0.00010288821,0.00037800777,0.00022387263,0.00040253115,0.00045871898],"domain_scores_gemma":[0.99851936,0.000057145327,0.000066502864,0.00084936514,0.00009136677,0.00041624147],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000969579,0.00016457494,0.00012327344,0.000056891506,0.00032255467,0.00010719554,0.0005561339,0.00010069789,0.000014126792],"category_scores_gemma":[0.00069571094,0.0001169361,0.000058499205,0.00014493315,0.00019891246,0.000012224767,0.0002827692,0.0001718209,0.00007711023],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012026306,0.0007720469,0.00035340345,0.00028174632,0.0001833839,0.0000118190965,0.0014007608,0.00042030387,0.25657332,0.005351899,0.14799008,0.5854586],"study_design_scores_gemma":[0.00055987365,0.0009488338,0.00019505619,0.000031728294,0.000012134566,0.00001047899,0.0005235689,0.010331297,0.021348262,0.000027652928,0.9657789,0.00023222949],"about_ca_topic_score_codex":0.000010411831,"about_ca_topic_score_gemma":0.00012521906,"teacher_disagreement_score":0.8177888,"about_ca_system_score_codex":0.000011692623,"about_ca_system_score_gemma":0.00006699723,"threshold_uncertainty_score":0.47685158},"labels":[],"label_agreement":null},{"id":"W2131767696","doi":"10.1093/database/bar056","title":"GrameneMart: the BioMart data portal for the Gramene project","year":2012,"lang":"en","type":"article","venue":"Database","topic":"Genetic Mapping and Diversity in Plants and Animals","field":"Biochemistry, Genetics and Molecular Biology","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Ontario Institute for Cancer Research; European Bioinformatics Institute; Wellcome Trust; National Science Foundation","keywords":"Computer science; Software; Genome; Component (thermodynamics); Resource (disambiguation); World Wide Web; Information retrieval; Database; Biology; Gene; Genetics","score_opus":0.09068718542282403,"score_gpt":0.32453579311027186,"score_spread":0.23384860768744783,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2131767696","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.78210276,0.030807348,0.07781874,0.008237944,0.005165675,0.005708905,0.08137076,0.00014728383,0.008640569],"genre_scores_gemma":[0.9783401,0.00049078156,0.0020679417,0.0014744222,0.0011030452,0.0000512965,0.014819389,0.000015529526,0.0016375321],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99930125,0.000035899688,0.00009640575,0.00020818801,0.00009583447,0.00026241885],"domain_scores_gemma":[0.9988957,0.00005696836,0.000046727044,0.0009286784,0.000024658704,0.000047244986],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00066378736,0.00009866638,0.00006365393,0.000011718496,0.00028097632,0.000041184467,0.0005543647,0.00003945117,0.000028292729],"category_scores_gemma":[0.00013166966,0.00005246243,0.00004314484,0.000046971585,0.00007775348,0.000007231073,0.000452579,0.000043388558,0.000014325466],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001155442,0.00013703362,0.0033217813,0.000027839238,0.0001675353,0.0000015873118,0.00008994705,0.0000017999085,0.041934453,0.0012352305,0.9463928,0.0065744505],"study_design_scores_gemma":[0.0002454779,0.000055209344,0.00097309455,0.000004801211,0.000077095705,0.000024859897,0.00041447248,0.000096935946,0.004550677,0.000013622695,0.9934334,0.00011031563],"about_ca_topic_score_codex":0.00007009541,"about_ca_topic_score_gemma":0.0000271316,"teacher_disagreement_score":0.19623728,"about_ca_system_score_codex":0.000001327561,"about_ca_system_score_gemma":0.00003574468,"threshold_uncertainty_score":0.21610712},"labels":[],"label_agreement":null},{"id":"W2135504399","doi":"10.1093/database/bas006","title":"Aptamer base: a collaborative knowledge base to describe aptamers and SELEX experiments","year":2012,"lang":"en","type":"article","venue":"Database","topic":"Advanced biosensing and bioanalysis techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":93,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Aptamer; Systematic evolution of ligands by exponential enrichment; Computer science; Knowledge base; Molecular recognition; SELEX Aptamer Technique; Computational biology; Nucleic acid; Resource (disambiguation); Chemistry; Biology; World Wide Web; RNA; Molecular biology; Biochemistry; Gene; Molecule","score_opus":0.023836741096483142,"score_gpt":0.32388411801932165,"score_spread":0.3000473769228385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2135504399","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9890319,0.0024978637,0.005799453,0.0001825757,0.00012984224,0.00039284863,0.0009705689,0.000069272224,0.00092563854],"genre_scores_gemma":[0.9628462,0.00020679105,0.03469071,0.0007076293,0.00020271722,0.000035258767,0.00086636987,0.000024081475,0.00042019904],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988965,0.00008707002,0.00015931728,0.000385627,0.00010012973,0.00037138048],"domain_scores_gemma":[0.99906635,0.000013028906,0.000053701824,0.00043377923,0.0001127078,0.00032043946],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024805643,0.00020360244,0.0001659957,0.000075401585,0.00010424712,0.000022557293,0.00010037768,0.00008007373,0.000010679963],"category_scores_gemma":[0.00012945967,0.00017958446,0.00004256613,0.00025059856,0.00010123409,0.000017724044,0.00022651038,0.0000686753,0.000021276799],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000082236744,0.0001644777,0.0011509294,0.00001001427,0.00005256593,0.0000029680796,0.00019066085,1.5670622e-7,0.9726048,0.00004562903,0.021590639,0.004104887],"study_design_scores_gemma":[0.00024798038,0.00011731862,0.0001833307,0.000020120357,0.000036098827,0.000008520407,0.00062082044,0.000022457256,0.8673945,0.0000017328039,0.13108902,0.00025810528],"about_ca_topic_score_codex":0.000020872138,"about_ca_topic_score_gemma":0.00003143075,"teacher_disagreement_score":0.109498374,"about_ca_system_score_codex":0.000022022643,"about_ca_system_score_gemma":0.000043731703,"threshold_uncertainty_score":0.7323241},"labels":[],"label_agreement":null},{"id":"W2135548107","doi":"10.1093/database/baq026","title":"Literature curation of protein interactions: measuring agreement across major public databases","year":2010,"lang":"en","type":"article","venue":"Database","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":65,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Hospital for Sick Children","funders":"Canadian Institutes of Health Research; Hospital for Sick Children","keywords":"Data curation; Database; Focus (optics); Organism; Computer science; Data science; Information retrieval; Biology; Genetics","score_opus":0.02698590957156888,"score_gpt":0.2828197224518299,"score_spread":0.255833812880261,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2135548107","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9724824,0.00058143685,0.022648422,0.00024784845,0.00044841255,0.0004122392,0.002625363,0.00001254921,0.00054136297],"genre_scores_gemma":[0.9849272,0.00004725184,0.0063643535,0.000099509205,0.00029694694,0.000040622854,0.007963139,0.000010694983,0.00025028095],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999232,0.000020949023,0.0002533713,0.00019089237,0.000113341725,0.00018947394],"domain_scores_gemma":[0.99906087,0.0000064105325,0.00013853176,0.0005956728,0.00012691937,0.000071619455],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002951734,0.000113904134,0.000089857975,0.00003236451,0.00009085584,0.000059607297,0.000173856,0.000055616885,0.00006554498],"category_scores_gemma":[0.00011829353,0.00010209283,0.000047299665,0.00008962597,0.000050063805,0.000048610014,0.00021955952,0.00019357912,0.000010601688],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004461228,0.00008660779,0.00033134094,0.000082100865,0.00003726696,0.0000015319397,0.00009549277,0.000002886841,0.98633194,0.0012204829,0.00240668,0.009359049],"study_design_scores_gemma":[0.0008673307,0.00009055121,0.0004960045,0.00016977442,0.000018854824,0.000041421263,0.00019089648,0.0006927589,0.5784946,0.00010252991,0.41848877,0.00034647793],"about_ca_topic_score_codex":0.000024667908,"about_ca_topic_score_gemma":0.000511482,"teacher_disagreement_score":0.41608208,"about_ca_system_score_codex":0.0000051806137,"about_ca_system_score_gemma":0.000041937936,"threshold_uncertainty_score":0.41632247},"labels":[],"label_agreement":null},{"id":"W2137417655","doi":"10.1093/database/bap024","title":"Phenol-Explorer: an online comprehensive database on polyphenol contents in foods","year":2010,"lang":"en","type":"article","venue":"Database","topic":"Phytochemicals and Antioxidant Activities","field":"Medicine","cited_by":1414,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Institut National de la Recherche Agronomique; Danone","keywords":"Metabolome; Polyphenol; Food science; Database; Computer science; Biotechnology; Biology; Bioinformatics; Metabolomics; Biochemistry","score_opus":0.09133406312008532,"score_gpt":0.33085742175887245,"score_spread":0.23952335863878713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2137417655","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99381894,0.000087275104,0.000027810358,0.00045594055,0.00027852715,0.00037419295,0.0044327076,0.00012508979,0.00039954146],"genre_scores_gemma":[0.98648566,0.000068041634,0.0025562625,0.0019532791,0.00042697284,0.000026093676,0.008375613,0.000040589635,0.00006749885],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9984638,0.000039093014,0.00029988575,0.0004890877,0.00031853086,0.00038957372],"domain_scores_gemma":[0.99846965,0.00010497723,0.00008087626,0.0009729449,0.00007838831,0.0002931485],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009090985,0.00025579205,0.0004031524,0.00017331494,0.000057017267,0.00002203635,0.00019763049,0.00008202272,0.00019598988],"category_scores_gemma":[0.00016132208,0.00022060129,0.000064256325,0.00017925887,0.00015068403,0.0004359237,0.0001322353,0.00072603626,0.00006793081],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006155073,0.0023012485,0.0042569544,0.00008965431,0.000030067611,0.00026761394,0.00015598876,5.075842e-7,0.98673916,0.00053281494,0.0019854736,0.0030250358],"study_design_scores_gemma":[0.01638906,0.0016104409,0.09103515,0.0014499944,0.00018633639,0.00026723067,0.003486891,0.0035892217,0.8413929,0.000246899,0.03900682,0.0013390565],"about_ca_topic_score_codex":0.00028625215,"about_ca_topic_score_gemma":0.00029115705,"teacher_disagreement_score":0.14534624,"about_ca_system_score_codex":0.000025532629,"about_ca_system_score_gemma":0.00005582771,"threshold_uncertainty_score":0.8995859},"labels":[],"label_agreement":null},{"id":"W2138088864","doi":"10.1093/database/bau060","title":"A controlled vocabulary for pathway entities and events","year":2014,"lang":"en","type":"article","venue":"Database","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Institute for Cancer Research","funders":"National Human Genome Research Institute; National Institutes of Health; European Commission; European Bioinformatics Institute","keywords":"Computer science; Readability; Consistency (knowledge bases); Vocabulary; Information retrieval; Controlled vocabulary; World Wide Web; Protocol (science); Database; State (computer science); Programming language; Artificial intelligence; Linguistics","score_opus":0.01190032490260914,"score_gpt":0.25635823974965316,"score_spread":0.24445791484704402,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2138088864","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92711836,0.0026053921,0.067614414,0.0005425121,0.00034554038,0.00042922187,0.00072393793,0.000038473197,0.0005821768],"genre_scores_gemma":[0.9892692,0.00013861438,0.0070028566,0.00069396023,0.00027840494,0.000099242716,0.0013220469,0.000012361958,0.0011832984],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995025,0.00003495021,0.000096062155,0.00018314796,0.000051640112,0.00013173258],"domain_scores_gemma":[0.9996623,0.000044731132,0.00003128048,0.00018555029,0.000021378606,0.000054802516],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024274111,0.0000748048,0.0001257692,0.000016624874,0.000053296008,0.000008921597,0.00007515461,0.00006329128,0.0000071121317],"category_scores_gemma":[0.00045183557,0.000058804686,0.000040758023,0.0000138132,0.00006882133,0.0000015868392,0.00007433852,0.000028536406,0.0000032098246],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0029856903,0.00037469045,0.00815397,0.00039512402,0.0003977704,0.000008795597,0.00017629447,0.0000020678274,0.6770914,0.0047520497,0.09577949,0.20988262],"study_design_scores_gemma":[0.0077740555,0.00060580357,0.0009944565,0.00003353779,0.000039245155,0.000012633091,0.00010580165,0.00051203603,0.034142457,0.0004908541,0.95504814,0.00024099743],"about_ca_topic_score_codex":0.0000073949764,"about_ca_topic_score_gemma":0.000012155582,"teacher_disagreement_score":0.8592686,"about_ca_system_score_codex":0.000001450418,"about_ca_system_score_gemma":0.000016715067,"threshold_uncertainty_score":0.23979856},"labels":[],"label_agreement":null},{"id":"W2138782665","doi":"10.1093/database/bap026","title":"PhosphoGRID: a database of experimentally verified in vivo protein phosphorylation sites from the budding yeast Saccharomyces cerevisiae","year":2010,"lang":"en","type":"article","venue":"Database","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":101,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; University of British Columbia","funders":"Canadian Cancer Society Research Institute; Biotechnology and Biological Sciences Research Council; National Center for Research Resources; Directorate for Biological Sciences; National Institutes of Health; Scottish Funding Council","keywords":"Phosphorylation; Saccharomyces cerevisiae; Protein phosphorylation; Proteome; Biology; Proteomics; Phosphatase; Computational biology; Function (biology); Kinase; Biochemistry; Signal transduction; Yeast; Cell biology; Gene; Protein kinase A","score_opus":0.015524813481317587,"score_gpt":0.2758113290470898,"score_spread":0.26028651556577226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2138782665","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9895946,0.00029938147,0.0019262374,0.000102360675,0.000023814522,0.0004545464,0.006825733,0.00008259439,0.00069077284],"genre_scores_gemma":[0.91863227,0.00007306309,0.07818242,0.000046216228,0.00009763709,0.0004582186,0.00242249,0.000029455821,0.00005825272],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99890465,0.000012750531,0.0003403082,0.0003714373,0.00017880466,0.00019205995],"domain_scores_gemma":[0.9986346,0.00007973699,0.00020985294,0.0009812689,0.000034778306,0.000059773058],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00015535421,0.00017675341,0.00017402091,0.000028893523,0.00009939379,0.00003352382,0.0004475064,0.000075064694,0.0020836787],"category_scores_gemma":[0.00008401188,0.00014975823,0.000048347458,0.00016586776,0.000095576135,0.0002746721,0.00022449417,0.00035992748,0.000014110987],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000058045145,0.00011261157,0.0018280888,0.00003125828,0.000008416888,0.0000027735573,0.00014526254,0.0000016271707,0.99469376,0.0019927495,0.0004973572,0.00062804937],"study_design_scores_gemma":[0.00038401238,0.0000066307443,0.00008643069,0.00015341441,0.000010606512,0.0000014211644,0.00037079916,0.0002858089,0.9892261,0.00026012334,0.009042222,0.00017243766],"about_ca_topic_score_codex":0.0014152775,"about_ca_topic_score_gemma":0.0002940149,"teacher_disagreement_score":0.076256186,"about_ca_system_score_codex":0.000027826653,"about_ca_system_score_gemma":0.00003884786,"threshold_uncertainty_score":0.99882853},"labels":[],"label_agreement":null},{"id":"W2141158585","doi":"10.1093/database/bar020","title":"Curation of characterized glycoside hydrolases of Fungal origin","year":2011,"lang":"en","type":"article","venue":"Database","topic":"Biofuel production and bioconversion","field":"Engineering","cited_by":105,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Glycoside hydrolase; Enzyme; Ascomycota; Hemicellulose; Biology; Biochemistry; Cell wall; Glycoside; Cellulase; Gene; Database; Cellulose; Botany","score_opus":0.03900584823951406,"score_gpt":0.22278377362014143,"score_spread":0.18377792538062737,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2141158585","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9973745,0.00007295652,0.0010602727,0.000012689626,0.00033520887,0.00008104236,0.00032368337,0.000064971035,0.00067470776],"genre_scores_gemma":[0.9986104,0.00008650918,0.0009878,0.000009614292,0.000039844086,0.0000020903287,0.00022576968,0.0000062836566,0.00003170709],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9996496,0.000010181667,0.00014240445,0.00007261933,0.000063778854,0.00006142964],"domain_scores_gemma":[0.99973255,0.0000055782816,0.00003765729,0.00017646249,0.000021941258,0.000025808196],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006492267,0.000054612497,0.00008415254,0.000052113253,0.000008792656,0.0000015232924,0.00005377977,0.000025343717,0.00036258885],"category_scores_gemma":[0.000011358964,0.000049794515,0.00002337773,0.00007181754,0.000023885126,0.00024194273,0.000014889066,0.000043129447,0.000026035596],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007643335,0.000050651473,0.0010438238,0.00025036922,0.000014868934,0.0000021766436,0.00011765225,0.0000030511828,0.99603695,0.0001572135,0.0012053953,0.0010414241],"study_design_scores_gemma":[0.00027706134,0.000028880257,0.0019195614,0.000022334238,0.000012348395,0.000003798836,0.00002487033,0.0014449143,0.9875134,0.000009500073,0.008677372,0.00006590839],"about_ca_topic_score_codex":0.000051767463,"about_ca_topic_score_gemma":0.0000018879887,"teacher_disagreement_score":0.008523489,"about_ca_system_score_codex":0.000006013435,"about_ca_system_score_gemma":0.0000062023514,"threshold_uncertainty_score":0.39700937},"labels":[],"label_agreement":null},{"id":"W2146436858","doi":"10.1093/database/bau097","title":"MetaProx: the database of metagenomic proximons","year":2014,"lang":"en","type":"article","venue":"Database","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"University of Waterloo; Natural Sciences and Engineering Research Council of Canada; Wilfrid Laurier University","keywords":"Metagenomics; Computer science; Database; Inference; Operon; Information retrieval; Data mining; Computational biology; Biology; Gene; Genetics; Artificial intelligence","score_opus":0.0111480008181741,"score_gpt":0.23363944980633577,"score_spread":0.22249144898816167,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2146436858","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7116096,0.005452824,0.25816432,0.001282043,0.0009559113,0.0016699274,0.005101923,0.0000495967,0.01571382],"genre_scores_gemma":[0.98787016,0.00020060645,0.007553803,0.0007313217,0.00028232424,0.00003012944,0.0028881186,0.000021868052,0.00042165464],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99918866,0.00006528195,0.00025358572,0.00019450848,0.0001019736,0.00019601145],"domain_scores_gemma":[0.99870485,0.000024611816,0.00012849041,0.0010372942,0.0000404068,0.000064342945],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00065411674,0.00012578811,0.00013871981,0.000024120654,0.00007868427,0.000016022252,0.00038478058,0.000051579995,0.000039682483],"category_scores_gemma":[0.000083323626,0.00008437246,0.00007956959,0.00006962681,0.00011566819,0.000006242405,0.00031069646,0.00009631803,0.00002986332],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013707629,0.00015891716,0.0004208372,0.00016543349,0.00031157618,0.0000017896656,0.00012441612,0.00016413406,0.89182246,0.014346236,0.076644294,0.015702812],"study_design_scores_gemma":[0.00099575,0.00021821473,0.0003667967,0.00003185266,0.00019495541,0.000022836943,0.00014276333,0.006841005,0.2573221,0.00038423293,0.73307234,0.0004071561],"about_ca_topic_score_codex":0.000034383796,"about_ca_topic_score_gemma":0.00004828492,"teacher_disagreement_score":0.65642804,"about_ca_system_score_codex":0.0000033653519,"about_ca_system_score_gemma":0.00004001794,"threshold_uncertainty_score":0.3440609},"labels":[],"label_agreement":null},{"id":"W2147119862","doi":"10.1093/database/bar031","title":"The Reactome BioMart","year":2011,"lang":"pt","type":"article","venue":"Database","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Institute for Cancer Research","funders":"National Human Genome Research Institute; National Institutes of Health; European Commission","keywords":"Computer science; Suite; Interface (matter); Information retrieval; User interface; World Wide Web; Simple (philosophy); Database; Programming language","score_opus":0.026211106589249227,"score_gpt":0.24010133970795178,"score_spread":0.21389023311870256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147119862","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4055947,0.120057166,0.076258466,0.005157605,0.023442363,0.005364603,0.020978097,0.00026253032,0.34288445],"genre_scores_gemma":[0.9773796,0.0064001665,0.0015942659,0.0014577046,0.0010069116,0.000035828445,0.0038771336,0.000070985654,0.0081773745],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987425,0.00005327561,0.00034591797,0.00028258993,0.00011857998,0.00045713552],"domain_scores_gemma":[0.9983837,0.000020316436,0.00015667838,0.0012143621,0.000058142792,0.00016680975],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047343,0.00022083348,0.00012951774,0.000023986311,0.0002959031,0.00006134628,0.0005247204,0.00018247876,0.000119117445],"category_scores_gemma":[0.00004575757,0.00015821439,0.00011149322,0.00009508806,0.00019551248,0.000007766676,0.00047561017,0.00017565768,0.0003853262],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00072470016,0.00037149747,0.0012755274,0.00013796719,0.00067407446,0.00005595812,0.0010952139,8.1280285e-7,0.05099827,0.006443268,0.8363752,0.10184753],"study_design_scores_gemma":[0.0005048552,0.00021347564,0.0006765754,0.00003233344,0.00006473519,0.000038253987,0.0003847367,0.00045271046,0.014434018,0.00018764361,0.9826349,0.00037577417],"about_ca_topic_score_codex":0.00007013332,"about_ca_topic_score_gemma":0.00013372814,"teacher_disagreement_score":0.5717849,"about_ca_system_score_codex":0.000010785956,"about_ca_system_score_gemma":0.000093917515,"threshold_uncertainty_score":0.64517957},"labels":[],"label_agreement":null},{"id":"W2148200511","doi":"10.1093/database/bar038","title":"BioMart: a data federation framework for large collaborative projects","year":2011,"lang":"en","type":"article","venue":"Database","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":93,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Institute for Cancer Research","funders":"","keywords":"Computer science; Server; Annotation; Software; World Wide Web; Selection (genetic algorithm); Database; Operating system","score_opus":0.1032471517953839,"score_gpt":0.34675811195317946,"score_spread":0.24351096015779555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148200511","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029653493,0.0007940853,0.95706606,0.00029981916,0.0004965594,0.001094664,0.008869789,0.000036941896,0.0016885652],"genre_scores_gemma":[0.8280147,0.0002016172,0.12934989,0.0008964777,0.00047309167,0.00035522963,0.040194,0.000033079305,0.00048192666],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992503,0.000037060578,0.00011242498,0.00038915168,0.0000691452,0.00014190048],"domain_scores_gemma":[0.998913,0.000008340717,0.00007129523,0.00085721817,0.00009860484,0.000051525738],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017598057,0.00008609179,0.00006236635,0.000027512197,0.00012051993,0.0000251756,0.00023837722,0.00008185912,0.00004757688],"category_scores_gemma":[0.000231156,0.000078347584,0.000017124063,0.00010614256,0.000017085673,0.000013199418,0.00016698118,0.00003621355,0.000012617538],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005641891,0.00034542286,0.0011710713,0.000054131262,0.00005997384,0.0000017583242,0.0004223489,1.6612128e-7,0.6662821,0.020305734,0.30785948,0.0029336386],"study_design_scores_gemma":[0.000676476,0.00016038792,0.0006953979,0.000025315656,0.000020198888,0.0000017221548,0.000562907,0.00025236703,0.43532953,0.00039948343,0.5616824,0.0001938018],"about_ca_topic_score_codex":0.00000699918,"about_ca_topic_score_gemma":0.000061045575,"teacher_disagreement_score":0.8277162,"about_ca_system_score_codex":0.0000052317914,"about_ca_system_score_gemma":0.00012327886,"threshold_uncertainty_score":0.31949216},"labels":[],"label_agreement":null},{"id":"W2149332866","doi":"10.1093/database/baq029","title":"Damming the genomic data flood using a comprehensive analysis and storage data structure","year":2010,"lang":"en","type":"article","venue":"Database","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Montreal Heart Institute; Université de Montréal","funders":"","keywords":"Computer science; Data mining; Data structure; Search engine indexing; Database; Redundancy (engineering); Data management; Data redundancy; Computer data storage; Data set; Data processing; Software; Normalization (sociology); Big data; Table (database); Information retrieval; Operating system","score_opus":0.05690010147651383,"score_gpt":0.3044548854189972,"score_spread":0.24755478394248334,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2149332866","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30382735,0.00036884527,0.6791034,0.00014387697,0.00038070235,0.00013682063,0.015986798,0.000048022946,0.000004224437],"genre_scores_gemma":[0.37668216,0.00005547049,0.6004529,0.00046981446,0.00040449566,0.0000014525949,0.021906855,0.000018991639,0.000007847085],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982172,0.00008455231,0.00020166526,0.0009747404,0.00027215006,0.00024969075],"domain_scores_gemma":[0.9905367,0.00015616765,0.00012839628,0.009011734,0.00004723906,0.0001197629],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.000350014,0.0001742981,0.00021059636,0.00012466767,0.00043648347,0.0004470089,0.0054938816,0.00004765249,0.000040878127],"category_scores_gemma":[0.0000705504,0.00011848686,0.000019883531,0.00056255626,0.00010427614,0.0022767272,0.015608105,0.00039460039,0.0000055380883],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055786495,0.00027549604,0.0117299445,0.00014700863,0.0019363136,0.0005341456,0.0017175069,0.0010136634,0.76448464,0.006104971,0.023447985,0.18855251],"study_design_scores_gemma":[0.0001959398,0.0000047894146,0.006589511,0.0000075726466,0.00021549518,0.00005332448,0.00004492521,0.96441543,0.00012789873,0.000047756705,0.02811801,0.00017934036],"about_ca_topic_score_codex":0.0009331732,"about_ca_topic_score_gemma":0.00074670545,"teacher_disagreement_score":0.9634018,"about_ca_system_score_codex":0.0000074239742,"about_ca_system_score_gemma":0.00007479344,"threshold_uncertainty_score":0.9998869},"labels":[],"label_agreement":null},{"id":"W2149671003","doi":"10.1093/database/bar041","title":"BioMart Central Portal: an open database network for the biological community","year":2011,"lang":"en","type":"article","venue":"Database","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":170,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Institute for Cancer Research","funders":"Ontario Institute for Cancer Research; Cancer Research UK; Wellcome Trust","keywords":"Computer science; Variety (cybernetics); Interface (matter); Ontology; Database; Resource (disambiguation); World Wide Web; Biological database; Bioinformatics; Artificial intelligence; Computer network","score_opus":0.09830288862401737,"score_gpt":0.3035580759883937,"score_spread":0.2052551873643763,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2149671003","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7407761,0.0026483585,0.21818915,0.00040921156,0.0023142032,0.004971731,0.021691842,0.000111928115,0.008887442],"genre_scores_gemma":[0.92563117,0.00038926638,0.029461613,0.0029204115,0.0008025867,0.00015003486,0.04047907,0.00003727518,0.00012856544],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99890196,0.00012621404,0.0002545411,0.00022337395,0.000057754587,0.00043617826],"domain_scores_gemma":[0.9983127,0.000044316253,0.00010645477,0.0013318002,0.00004301304,0.00016170248],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009854884,0.00016813652,0.00014083917,0.000010306593,0.000470678,0.00006331066,0.0012677214,0.00010975346,0.00010920529],"category_scores_gemma":[0.00005483112,0.00011211307,0.000058695492,0.000065960725,0.0001609364,0.000021721477,0.0011085463,0.00018192246,0.000009592775],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002905216,0.0018421517,0.010099127,0.00010784215,0.0006856819,0.000026140193,0.0009573734,0.0001315358,0.061982706,0.022127703,0.8644991,0.034635447],"study_design_scores_gemma":[0.002895704,0.0020538548,0.014269864,0.00005358593,0.00016238814,0.00009160917,0.0014571045,0.0048750276,0.014148791,0.0018415888,0.9570268,0.0011236728],"about_ca_topic_score_codex":0.0005726091,"about_ca_topic_score_gemma":0.0009073549,"teacher_disagreement_score":0.18872753,"about_ca_system_score_codex":0.0000046871023,"about_ca_system_score_gemma":0.000055946366,"threshold_uncertainty_score":0.45718384},"labels":[],"label_agreement":null},{"id":"W2151991601","doi":"10.1093/database/bau095","title":"WholeCellSimDB: a hybrid relational/HDF database for whole-cell model predictions","year":2014,"lang":"en","type":"article","venue":"Database","topic":"Gene Regulatory Network Analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Prince Edward Island","funders":"National Center for Chronic Disease Prevention and Health Promotion; U.S. National Library of Medicine; National Institute of General Medical Sciences; National Institutes of Health","keywords":"Computer science; Python (programming language); JSON; Metadata; JavaScript; Database; Interface (matter); Relational database; Graphical user interface; Interoperability; SQL; Relational database management system; Information retrieval; World Wide Web; Programming language","score_opus":0.015070836204794637,"score_gpt":0.23656580453771275,"score_spread":0.22149496833291812,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151991601","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10325623,0.00049301516,0.88795906,0.00026256207,0.00013695256,0.00034696716,0.0065745143,0.00004290074,0.0009277683],"genre_scores_gemma":[0.8836184,0.000108493994,0.0420424,0.00068268797,0.0008318839,0.0001798821,0.06613497,0.00008151512,0.006319764],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99848336,0.000066392466,0.0002877405,0.00062948815,0.00020109124,0.00033194968],"domain_scores_gemma":[0.9983574,0.000036728303,0.00011823349,0.0011604637,0.00013830562,0.0001888826],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003972223,0.00021636185,0.00017659276,0.0000833096,0.00021199317,0.000025613364,0.00026460868,0.00008331684,0.000029494122],"category_scores_gemma":[0.00012811631,0.00022918853,0.00017048541,0.00011960402,0.000072094736,0.00001643071,0.00020365682,0.0001022293,0.00006531934],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010723676,0.00025780723,0.00067934394,0.000075150216,0.00012522972,0.0000017890388,0.000012308311,0.11266642,0.522112,0.00076976727,0.36268535,0.00050754467],"study_design_scores_gemma":[0.0010244801,0.000084859785,0.000050357612,0.000015177467,0.00018543041,0.000007597374,0.000010526377,0.5462779,0.062188406,0.00014987649,0.3896956,0.00030982896],"about_ca_topic_score_codex":0.0000087581775,"about_ca_topic_score_gemma":0.000032472642,"teacher_disagreement_score":0.8459167,"about_ca_system_score_codex":0.000018057026,"about_ca_system_score_gemma":0.00010536503,"threshold_uncertainty_score":0.9346037},"labels":[],"label_agreement":null},{"id":"W2156564520","doi":"10.1093/database/bar030","title":"Ensembl BioMarts: a hub for data retrieval across taxonomic space","year":2011,"lang":"en","type":"article","venue":"Database","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1542,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Biotechnology and Biological Sciences Research Council; Bill and Melinda Gates Foundation; European Commission; Directorate for Biological Sciences; Ontario Institute for Cancer Research; Wellcome Trust","keywords":"Ensembl; Computer science; Genome; World Wide Web; Annotation; Data science; Biology; Genomics; Artificial intelligence; Gene; Genetics","score_opus":0.10775340630988058,"score_gpt":0.3091795235511951,"score_spread":0.20142611724131454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2156564520","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9781812,0.0017780126,0.005075559,0.000084172374,0.00037412814,0.0003949381,0.013536969,0.000007126871,0.00056793477],"genre_scores_gemma":[0.9725448,0.00043212343,0.02064148,0.00026307482,0.00038266182,0.000028411228,0.0053291186,0.000034824774,0.00034354295],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989195,0.000019620518,0.00016540305,0.00053096557,0.000052495863,0.0003120405],"domain_scores_gemma":[0.9984652,0.000015868442,0.00007315078,0.00131368,0.000051265593,0.000080832084],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028880697,0.00015179685,0.0001343577,0.000015846204,0.00012946234,0.00001797985,0.00050168653,0.000070117414,0.000015886417],"category_scores_gemma":[0.00014765403,0.00014692637,0.000051493153,0.000043405686,0.00009095299,0.000002232052,0.0008648976,0.00003776995,0.000020874306],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00050535816,0.00009294627,0.0020531227,0.000032823456,0.00014635328,0.000004653548,0.00013092507,5.2485785e-7,0.9447855,0.0001678618,0.050642043,0.0014378839],"study_design_scores_gemma":[0.0009941044,0.00024918906,0.0021931734,0.000008330561,0.000046519246,0.000014456148,0.00022654507,0.00010325879,0.34467834,0.00005429231,0.65109855,0.00033321136],"about_ca_topic_score_codex":0.00012004175,"about_ca_topic_score_gemma":0.00019769745,"teacher_disagreement_score":0.60045654,"about_ca_system_score_codex":0.0000059173444,"about_ca_system_score_gemma":0.000048057518,"threshold_uncertainty_score":0.59914833},"labels":[],"label_agreement":null},{"id":"W2158197251","doi":"10.1093/database/baq023","title":"iRefWeb: interactive analysis of consolidated protein interaction data and their supporting evidence","year":2010,"lang":"en","type":"article","venue":"Database","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":223,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; SickKids Foundation; Hospital for Sick Children; University of Toronto","funders":"Canadian Institutes of Health Research; Hospital for Sick Children","keywords":"Computer science; Interface (matter); Interaction information; World Wide Web; Reliability (semiconductor); Database; Information retrieval","score_opus":0.026028351551974787,"score_gpt":0.3164998662923536,"score_spread":0.2904715147403788,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2158197251","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99159926,0.00009073283,0.006512306,0.000056538694,0.000078766345,0.00014347519,0.0013971137,0.00000486991,0.00011694931],"genre_scores_gemma":[0.99230653,0.000044698514,0.0014911529,0.00006736784,0.000050167862,0.000005459839,0.0060035256,0.000005992271,0.000025098325],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99931514,0.00002720011,0.00025568728,0.00023946741,0.000045883346,0.000116615614],"domain_scores_gemma":[0.9988373,0.00003509224,0.00022677069,0.0007832608,0.00006501495,0.00005254301],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003897612,0.00009436159,0.00014568659,0.00006990107,0.00003566689,0.000024949713,0.0002467635,0.000059932765,0.000051844905],"category_scores_gemma":[0.0002498524,0.00007703217,0.00003300155,0.00013247355,0.00007430971,0.000032244057,0.0005075449,0.00014972236,0.0000019182364],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009722054,0.000028528455,0.001057077,0.000023892724,0.00035053142,8.820716e-7,0.00013473544,0.0000062595855,0.98778063,0.000031995554,0.00073642447,0.00975181],"study_design_scores_gemma":[0.00058809516,0.00020739395,0.0025720838,0.00017667064,0.0006304167,0.000034508495,0.0017064866,0.17789717,0.78534573,0.00004848801,0.030291175,0.000501791],"about_ca_topic_score_codex":0.00007752089,"about_ca_topic_score_gemma":0.0004236044,"teacher_disagreement_score":0.20243493,"about_ca_system_score_codex":0.0000024832084,"about_ca_system_score_gemma":0.000035311514,"threshold_uncertainty_score":0.31412807},"labels":[],"label_agreement":null},{"id":"W2166240318","doi":"10.1093/database/bas056","title":"An overview of the BioCreative 2012 Workshop Track III: interactive text mining task","year":2013,"lang":"en","type":"article","venue":"Database","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":75,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Research in Immunology and Cancer","funders":"U.S. National Library of Medicine; National Human Genome Research Institute","keywords":"Computer science; Data curation; Annotation; Task (project management); Usability; Information retrieval; Data science; Biomedical text mining; Set (abstract data type); World Wide Web; Text mining; Natural language processing; Artificial intelligence; Human–computer interaction; Engineering","score_opus":0.0459006993030045,"score_gpt":0.3375506222957032,"score_spread":0.2916499229926987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2166240318","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99331355,0.003959665,0.00080797967,0.0004935715,0.00019436306,0.00020911185,0.0003532264,0.000015463502,0.00065309706],"genre_scores_gemma":[0.9957055,0.00026979743,0.002372187,0.0004300658,0.000112851885,0.000030060697,0.00045351946,0.000011908175,0.00061413704],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99916804,0.00010890193,0.00017529038,0.000261946,0.00010550052,0.00018032588],"domain_scores_gemma":[0.9991208,0.000052129017,0.000113450136,0.00056867744,0.00006694943,0.000078023586],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012808183,0.00012372379,0.00014389891,0.000022603494,0.000056406174,0.000016308748,0.00033339707,0.000100830934,0.0002320439],"category_scores_gemma":[0.0002182563,0.00007925399,0.00006836761,0.000109349436,0.0002491907,0.000015901738,0.00019055729,0.000106891486,0.000021510046],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013628582,0.0003728547,0.0023157268,0.00005696046,0.00016314305,0.0000035195903,0.0011281,0.000004367678,0.7473103,0.000111064444,0.120556585,0.1278411],"study_design_scores_gemma":[0.002349389,0.0008894436,0.042976536,0.00070691743,0.00016340334,0.00004759093,0.014892735,0.0005639925,0.6075033,0.00014784951,0.32883072,0.0009281509],"about_ca_topic_score_codex":0.000116060786,"about_ca_topic_score_gemma":0.00006430574,"teacher_disagreement_score":0.20827414,"about_ca_system_score_codex":0.0000062174213,"about_ca_system_score_gemma":0.00004009921,"threshold_uncertainty_score":0.3231884},"labels":[],"label_agreement":null},{"id":"W2166516661","doi":"10.1093/database/bas017","title":"How to link ontologies and protein-protein interactions to literature: text-mining approaches and the BioCreative experience","year":2012,"lang":"en","type":"article","venue":"Database","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Research in Immunology and Cancer","funders":"Biotechnology and Biological Sciences Research Council; National Center for Research Resources; Directorate for Biological Sciences; National Institutes of Health; Office of Research Infrastructure Programs, National Institutes of Health; Canadian Institutes of Health Research; European Commission; Wellcome Trust","keywords":"Computer science; Ontology; Information retrieval; Pipeline (software); Context (archaeology); Data curation; Information extraction; Consistency (knowledge bases); Workflow; Open Biomedical Ontologies; Biomedical text mining; Controlled vocabulary; Process (computing); Annotation; Vocabulary; Natural language processing; Upper ontology; Data science; Suggested Upper Merged Ontology; Artificial intelligence; Text mining; Semantic Web; Database","score_opus":0.045486472278633866,"score_gpt":0.294178056247657,"score_spread":0.24869158396902316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2166516661","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9774803,0.0043924027,0.008853842,0.008255932,0.00008043815,0.0005337961,0.00014704002,0.000026918398,0.00022932267],"genre_scores_gemma":[0.97430146,0.000039520284,0.023683576,0.00039790102,0.00022591256,0.00035866525,0.00010584029,0.000008778559,0.0008783588],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991629,0.00009372459,0.000101352045,0.00030861524,0.00008087417,0.00025253167],"domain_scores_gemma":[0.99939275,0.00005258112,0.000040366645,0.0003201268,0.00002856929,0.00016563348],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023630018,0.00014680056,0.0001368181,0.000041850224,0.00014795327,0.0001169919,0.00015059006,0.000074477015,0.0000028668971],"category_scores_gemma":[0.0012107656,0.00009076399,0.000023608764,0.000121705554,0.0003229362,0.000019701187,0.00040331564,0.00011235862,0.0000023988678],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013231552,0.00015565434,0.003410094,0.00012986042,0.00015537001,0.000011897098,0.026385771,7.7205266e-7,0.6326645,0.004296289,0.0066731363,0.32479352],"study_design_scores_gemma":[0.0015213921,0.0006190072,0.0052153426,0.00042237967,0.00004410509,0.00012206323,0.021356575,0.00005862735,0.40092808,0.00009723218,0.5688807,0.0007345551],"about_ca_topic_score_codex":0.000023419594,"about_ca_topic_score_gemma":0.000026965157,"teacher_disagreement_score":0.5622075,"about_ca_system_score_codex":0.000005513061,"about_ca_system_score_gemma":0.000012179298,"threshold_uncertainty_score":0.37012482},"labels":[],"label_agreement":null},{"id":"W2168670121","doi":"10.1093/database/bar051","title":"The Chado Natural Diversity module: a new generic database schema for large-scale phenotyping and genotyping data","year":2011,"lang":"en","type":"article","venue":"Database","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Division of Emerging Frontiers; National Institute of Allergy and Infectious Diseases; Division of Biological Infrastructure; National Institute of General Medical Sciences; Smithsonian Tropical Research Institute; National Human Genome Research Institute; Agricultural Research Service; National Institutes of Health; National Institute of Food and Agriculture; Smithsonian Institution; U.S. Department of Agriculture; Commonwealth Scientific and Industrial Research Organisation; National Evolutionary Synthesis Center; Agriculture and Agri-Food Canada; National Science Foundation","keywords":"Computer science; Modular design; Genotyping; Biological database; Relational database; Schema (genetic algorithms); Database; Information retrieval; Data mining; Bioinformatics; Biology; Programming language; Genotype","score_opus":0.05710983984248658,"score_gpt":0.25765207301269766,"score_spread":0.20054223317021108,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2168670121","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9098391,0.033511303,0.047098294,0.00024592315,0.0006927742,0.00072022097,0.007706202,0.000015858323,0.00017031413],"genre_scores_gemma":[0.94315493,0.0035828566,0.04632545,0.0006251623,0.0007104075,0.000024045587,0.0052008447,0.00004111366,0.00033519304],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99878675,0.000027904345,0.00015477987,0.00057589915,0.000087544904,0.0003671528],"domain_scores_gemma":[0.99852973,0.00002698513,0.000078585865,0.0011910343,0.000056465688,0.00011720814],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035984226,0.00017837751,0.00013400086,0.00002003297,0.0008003676,0.000030965042,0.0006312899,0.000050444403,0.0000058501923],"category_scores_gemma":[0.00012302217,0.00014386694,0.00003966337,0.00005743239,0.00007776283,0.000007737749,0.004023836,0.000082679806,0.0000032731796],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010376426,0.0002640639,0.02097065,0.00022051462,0.0008647817,0.000013095333,0.0017606937,0.0000064810165,0.85568255,0.0024262336,0.07645788,0.04029538],"study_design_scores_gemma":[0.0052585257,0.0002890018,0.025530864,0.000075541495,0.00050300785,0.00005775721,0.0018671186,0.015443172,0.10096364,0.0006052936,0.8477192,0.0016869131],"about_ca_topic_score_codex":0.0002499144,"about_ca_topic_score_gemma":0.0007800041,"teacher_disagreement_score":0.7712613,"about_ca_system_score_codex":0.0000066058683,"about_ca_system_score_gemma":0.0000559557,"threshold_uncertainty_score":0.61558616},"labels":[],"label_agreement":null},{"id":"W2169425537","doi":"10.1093/database/bau067","title":"Assisting manual literature curation for protein-protein interactions using BioQRator","year":2014,"lang":"en","type":"article","venue":"Database","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Institute for Research in Immunology and Cancer","funders":"U.S. National Library of Medicine; National Institutes of Health; Ministry of Education, Science and Technology; National Research Foundation of Korea; National Research Foundation","keywords":"Annotation; Computer science; Data curation; Task (project management); Information retrieval; World Wide Web; Artificial intelligence","score_opus":0.030990985643682793,"score_gpt":0.3347915863824545,"score_spread":0.3038006007387717,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2169425537","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6354731,0.0002329067,0.36268577,0.00027037112,0.00021287624,0.0003342621,0.0006257937,0.000036893573,0.00012806947],"genre_scores_gemma":[0.92434824,0.0000023359394,0.07161738,0.00016191555,0.00069146266,0.00008815578,0.0026894987,0.000016100395,0.00038489682],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993009,0.00005327164,0.0001441825,0.00026665136,0.000069824135,0.00016515865],"domain_scores_gemma":[0.99951535,0.000014887174,0.00007218268,0.0002587528,0.000079493824,0.00005935343],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020571485,0.00010542289,0.00008659378,0.00003642501,0.00013877975,0.00004951612,0.00010199842,0.00009420453,0.000008784784],"category_scores_gemma":[0.00081111316,0.000091169306,0.000048304264,0.00007079821,0.000049402093,0.000011221782,0.00007082133,0.0000911657,0.0000052320056],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049744758,0.000031818534,0.00005124902,0.00005381936,0.0000136268545,9.755894e-7,0.000021413789,0.0000019590718,0.98378,0.0002674818,0.0015112773,0.01421663],"study_design_scores_gemma":[0.0007102205,0.00028841008,0.00013613007,0.00032307341,0.000026502767,0.00002196606,0.00007236128,0.0049245534,0.6542705,0.00022926804,0.3386782,0.0003187466],"about_ca_topic_score_codex":0.000014373093,"about_ca_topic_score_gemma":0.000018890143,"teacher_disagreement_score":0.33716694,"about_ca_system_score_codex":0.000008773378,"about_ca_system_score_gemma":0.000029054901,"threshold_uncertainty_score":0.37177765},"labels":[],"label_agreement":null},{"id":"W2170283197","doi":"10.1093/database/bat026","title":"The PhosphoGRID Saccharomyces cerevisiae protein phosphorylation site database: version 2.0 update","year":2013,"lang":"en","type":"article","venue":"Database","topic":"Fungal and yeast genetics research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":108,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; Université de Montréal; Institute for Research in Immunology and Cancer; University of British Columbia","funders":"Biotechnology and Biological Sciences Research Council; Canadian Cancer Society Research Institute; Canadian Institutes of Health Research; National Center for Research Resources; Directorate for Biological Sciences; National Institutes of Health; Wellcome Trust","keywords":"Phosphorylation; Proteome; Saccharomyces cerevisiae; Computational biology; Protein phosphorylation; Protein function; Database; Function (biology); Biology; Yeast; Bioinformatics; Computer science; Biochemistry; Protein kinase A; Cell biology; Gene","score_opus":0.007943784022554383,"score_gpt":0.24274444773718434,"score_spread":0.23480066371462996,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170283197","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9902554,0.0052754837,0.00046231857,0.0010898091,0.00017441176,0.0008586978,0.001307642,0.000023908222,0.0005522883],"genre_scores_gemma":[0.9780493,0.003306373,0.0018637618,0.00032585012,0.0004042239,0.00023885338,0.012732436,0.000046459398,0.0030327453],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99851847,0.00009468122,0.00020945969,0.00044419948,0.00033119097,0.0004020151],"domain_scores_gemma":[0.9986683,0.00002209999,0.00007590587,0.0009121492,0.00015857934,0.00016296997],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00033757178,0.00018300618,0.000101873,0.000031010775,0.0003487591,0.00014510952,0.00042581838,0.00007656239,0.0005414903],"category_scores_gemma":[0.00012827275,0.0001303974,0.00006422082,0.00014914152,0.000113145834,0.000024901821,0.0005420178,0.00016987526,0.0014443934],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010235867,0.00004094385,0.00075617584,0.000027223918,0.000023860943,0.0000029079376,0.000007342405,0.0000053635763,0.9049791,0.00008234546,0.08587816,0.008094228],"study_design_scores_gemma":[0.00036125677,0.00009056717,0.00087634544,0.000025953721,0.000007700457,0.0000037733118,0.000035913938,0.00035137465,0.5870636,0.000021800386,0.4109929,0.00016879755],"about_ca_topic_score_codex":0.00023984711,"about_ca_topic_score_gemma":0.00005926962,"teacher_disagreement_score":0.32511473,"about_ca_system_score_codex":0.000014592761,"about_ca_system_score_gemma":0.000070781585,"threshold_uncertainty_score":0.9993331},"labels":[],"label_agreement":null},{"id":"W2170802261","doi":"10.1093/database/bar021","title":"A comprehensive manually curated reaction map of RANKL/RANK-signaling pathway","year":2011,"lang":"en","type":"article","venue":"Database","topic":"Bone Metabolism and Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"The Wellcome Trust DBT India Alliance; Council of Scientific and Industrial Research, India; Department of Biotechnology, Ministry of Science and Technology, India; Wellcome Trust","keywords":"RANKL; RANK Ligand; Osteoclast; NFAT; Activator (genetics); Cell biology; Biology; Signal transduction; Cancer research; PI3K/AKT/mTOR pathway; Transcription factor; Receptor; Biochemistry","score_opus":0.03295461600734513,"score_gpt":0.2515163771703015,"score_spread":0.2185617611629564,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170802261","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99501884,0.0019209398,0.0009969434,0.00001170568,0.00017487412,0.00013680835,0.0011471481,0.000016461432,0.00057627045],"genre_scores_gemma":[0.9951239,0.0000951902,0.0013014434,0.00016252583,0.00010365225,0.000011188164,0.0030598787,0.000015074089,0.00012710394],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99927336,0.000060432438,0.00018836645,0.00023742959,0.00009668111,0.00014371147],"domain_scores_gemma":[0.99930537,0.000007576399,0.00009541407,0.00039010495,0.00012098772,0.000080566046],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007197999,0.00011648058,0.00013516645,0.000036025118,0.00003698732,0.000005232492,0.000119661745,0.00005815671,0.000088770124],"category_scores_gemma":[0.000029436405,0.000108886394,0.00006730233,0.00005164165,0.000061644234,0.000009701441,0.00008710247,0.00004775623,0.000033640095],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003727911,0.00014216211,0.00034673128,0.000060122853,0.000037887505,0.000013840105,0.00005110962,0.0000011106843,0.9952389,0.00016571888,0.002649459,0.00092014496],"study_design_scores_gemma":[0.00082679203,0.00008127477,0.0031968665,0.000022381486,0.000051083065,0.000007915282,0.00016463744,0.000009333611,0.95126045,0.000047896796,0.04416977,0.00016160043],"about_ca_topic_score_codex":0.00016317987,"about_ca_topic_score_gemma":0.000010293585,"teacher_disagreement_score":0.04397847,"about_ca_system_score_codex":0.0000021277142,"about_ca_system_score_gemma":0.000050415725,"threshold_uncertainty_score":0.44402584},"labels":[],"label_agreement":null},{"id":"W2336698700","doi":"10.1093/database/baw013","title":"PhyloPro2.0: a database for the dynamic exploration of phylogenetically conserved proteins and their domain architectures across the Eukarya","year":2016,"lang":"en","type":"article","venue":"Database","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Hospital for Sick Children","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Hospital for Sick Children; University of Toronto","keywords":"Domain (mathematical analysis); Computer science; Visualization; Upload; Phylogenetic tree; Database; Protein domain; Interface (matter); Adjacency list; Data mining; Information retrieval; World Wide Web; Biology; Genetics","score_opus":0.02104871360495447,"score_gpt":0.26985288197856594,"score_spread":0.24880416837361147,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2336698700","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9209292,0.0029498222,0.066705406,0.0019145847,0.00006274207,0.0010024066,0.0064220275,0.0000030937701,0.000010698652],"genre_scores_gemma":[0.9957707,0.00079621817,0.002460588,0.00024371663,0.00010255673,0.00034639018,0.00022074039,0.000020469457,0.00003863404],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99905163,0.000080849815,0.00021019952,0.00033235442,0.00007871935,0.00024627263],"domain_scores_gemma":[0.9988735,0.0002024201,0.000104476334,0.00069136935,0.00008342976,0.000044811753],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004359955,0.00017742736,0.00014157138,0.000012939709,0.00024633872,0.000019854177,0.00030058075,0.00004604764,0.00000291372],"category_scores_gemma":[0.00017997352,0.00007725779,0.000070662296,0.000047687012,0.00048079516,0.000002017948,0.0003624075,0.000046995403,7.668509e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023515869,0.000035304343,0.00044154114,0.000033104476,0.00010671535,3.7330227e-7,0.00031847096,0.000007489021,0.985627,0.00032366576,0.00021092301,0.012660275],"study_design_scores_gemma":[0.0026826558,0.0006760749,0.012420132,0.000074342206,0.000070899434,0.00002282216,0.0020406784,0.00029002686,0.93830955,0.003318315,0.039651006,0.00044349904],"about_ca_topic_score_codex":0.00003197867,"about_ca_topic_score_gemma":0.00050785445,"teacher_disagreement_score":0.07484146,"about_ca_system_score_codex":0.0000041831213,"about_ca_system_score_gemma":0.000046923764,"threshold_uncertainty_score":0.31504813},"labels":[],"label_agreement":null},{"id":"W2338762894","doi":"10.1093/database/baw007","title":"2P2Idb v2: update of a structural database dedicated to orthosteric modulation of protein–protein interactions","year":2016,"lang":"en","type":"article","venue":"Database","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":80,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Nautical Research Society","funders":"Agence Nationale de la Recherche","keywords":"Protein Data Bank; Protein Data Bank (RCSB PDB); Database; Protein structure database; Protein–protein interaction; Planarity testing; Computer science; Protein structure; Protein ligand; Affinities; Interface (matter); Small molecule; Computational biology; Chemistry; Data mining; Information retrieval; Crystallography; Biology; Molecule; Stereochemistry; Biochemistry","score_opus":0.009674534010869559,"score_gpt":0.2678753414436307,"score_spread":0.25820080743276114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2338762894","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9305257,0.00007192743,0.06478913,0.00017788149,0.000075711294,0.0005387596,0.0037682916,0.0000126132545,0.000039969447],"genre_scores_gemma":[0.9851537,0.000008966917,0.011689925,0.000072381656,0.0000784533,0.000051877716,0.0027864887,0.000020037874,0.00013817979],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99888974,0.00005931171,0.00034735462,0.00034505254,0.0001665242,0.00019198682],"domain_scores_gemma":[0.99873775,0.000007860026,0.00021039826,0.00078415213,0.0001494717,0.0001103895],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011737625,0.00015982146,0.00017428087,0.00009704643,0.000038689624,0.0000066016405,0.00023956428,0.00006620906,0.0000937282],"category_scores_gemma":[0.00020634948,0.00011799126,0.00005933509,0.00017306214,0.00008204631,0.00002798457,0.00030271636,0.00006218097,0.00001066914],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027101627,0.000023906581,0.00065767777,0.000050614784,0.000034354365,0.0000024238495,0.000011239222,0.0000102213935,0.99050087,0.00034072655,0.00017366212,0.007923267],"study_design_scores_gemma":[0.00068078504,0.00017769026,0.0030108993,0.00016782148,0.000022142138,0.000012849688,0.000011663229,0.00020988005,0.9899404,0.0001794424,0.005373592,0.00021285079],"about_ca_topic_score_codex":0.00010756403,"about_ca_topic_score_gemma":0.00011449448,"teacher_disagreement_score":0.054627977,"about_ca_system_score_codex":0.000013803179,"about_ca_system_score_gemma":0.000071482624,"threshold_uncertainty_score":0.48115438},"labels":[],"label_agreement":null},{"id":"W2418383179","doi":"10.1093/database/baw090","title":"MET network in PubMed: a text-mined network visualization and curation system","year":2016,"lang":"en","type":"article","venue":"Database","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Institute for Cancer Research","funders":"National Human Genome Research Institute; National Institutes of Health; National Institute of General Medical Sciences; Ministry of Science and Technology, Taiwan; European Molecular Biology Laboratory","keywords":"Computer science; Task (project management); Metastasis; Data curation; Visualization; World Wide Web; Process (computing); Cancer; Information retrieval; Data science; Bioinformatics; Medicine; Artificial intelligence; Biology","score_opus":0.014714083094430574,"score_gpt":0.25834995446435843,"score_spread":0.24363587136992787,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2418383179","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88204974,0.0036439197,0.11236665,0.0002559011,0.0005699777,0.00042213677,0.00032353675,0.00007691405,0.00029122582],"genre_scores_gemma":[0.99682873,0.00022556365,0.00131821,0.00012827065,0.0004359431,0.000051487157,0.0008826157,0.000010308284,0.000118889795],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991333,0.000115191855,0.0001709202,0.00025909135,0.00007517218,0.00024631133],"domain_scores_gemma":[0.99959123,0.000046200454,0.000059687987,0.00021110929,0.000023237319,0.000068516136],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004995672,0.00009140822,0.00010997959,0.000022680611,0.000044030687,0.000014799591,0.000077929864,0.00010609488,0.000004943156],"category_scores_gemma":[0.0002699115,0.00006281375,0.000014514437,0.0001272588,0.000065486165,0.000007532234,0.00009988169,0.00003052959,0.0000048558372],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011269873,0.00019305949,0.3375963,0.00029495647,0.0001611057,0.000060690716,0.00013126146,0.00010867006,0.053344797,0.013810665,0.1980724,0.39509913],"study_design_scores_gemma":[0.007661907,0.001070371,0.3590662,0.0013216673,0.00011712787,0.00012646215,0.00049442396,0.0040029096,0.013148297,0.00039805626,0.6109591,0.0016334524],"about_ca_topic_score_codex":0.000034522276,"about_ca_topic_score_gemma":0.00025452196,"teacher_disagreement_score":0.4128867,"about_ca_system_score_codex":0.000012950456,"about_ca_system_score_gemma":0.00002136946,"threshold_uncertainty_score":0.25614706},"labels":[],"label_agreement":null},{"id":"W2509885322","doi":"10.1093/database/baw121","title":"BioCreative V BioC track overview: collaborative biocurator assistant task for BioGRID","year":2016,"lang":"en","type":"article","venue":"Database","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mount Sinai Hospital; Lunenfeld-Tanenbaum Research Institute; Université de Montréal; Institute for Research in Immunology and Cancer","funders":"National Institute of General Medical Sciences; Biotechnology and Biological Sciences Research Council; National Institutes of Health","keywords":"Computer science; Usability; Annotation; Task (project management); Interoperability; Classifier (UML); World Wide Web; Information retrieval; Data curation; Crowdsourcing; Natural language processing; Artificial intelligence; Human–computer interaction","score_opus":0.025597812753064744,"score_gpt":0.3119697022994703,"score_spread":0.2863718895464056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2509885322","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7156446,0.039578967,0.09639426,0.01097311,0.0018711583,0.0024061082,0.13180783,0.00030186487,0.0010220818],"genre_scores_gemma":[0.92039734,0.009502882,0.051242612,0.0026017423,0.0017935515,0.00077657285,0.009681187,0.00014072527,0.0038634022],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986824,0.00007859593,0.00023717237,0.0005319221,0.0001325207,0.0003374305],"domain_scores_gemma":[0.9989692,0.00010308985,0.00011831546,0.00048273406,0.00017139231,0.00015529583],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002507749,0.00021448183,0.0002125653,0.000057688183,0.000108646374,0.000023268572,0.00024138101,0.0001671251,0.00004899327],"category_scores_gemma":[0.0006980587,0.00013181144,0.00009907167,0.00020197063,0.0003583073,0.000008020858,0.00012220452,0.00005026371,0.000041676638],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033837295,0.00011205448,0.00035413072,0.00003135649,0.00010617557,0.0000065954832,0.000032560358,3.4289073e-8,0.79454553,0.00039250145,0.16562098,0.038459696],"study_design_scores_gemma":[0.000988979,0.00043707847,0.00039840656,0.000054459648,0.000024388703,0.0000034045183,0.00013477218,0.0000031588431,0.35239503,0.00004194397,0.6453107,0.00020766188],"about_ca_topic_score_codex":0.000019393048,"about_ca_topic_score_gemma":0.00005130734,"teacher_disagreement_score":0.47968972,"about_ca_system_score_codex":0.000019983347,"about_ca_system_score_gemma":0.00016796337,"threshold_uncertainty_score":0.53751147},"labels":[],"label_agreement":null},{"id":"W2516150684","doi":"10.1093/database/baw119","title":"Overview of the interactive task in BioCreative V","year":2016,"lang":"en","type":"article","venue":"Database","topic":"Biomedical and Engineering Education","field":"Engineering","cited_by":99,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Institute for Research in Immunology and Cancer; Ontario Institute for Cancer Research","funders":"U.S. National Library of Medicine; National Human Genome Research Institute; National Institute of General Medical Sciences; European Molecular Biology Laboratory; U.S. Department of Energy; Dirección General de Asuntos del Personal Académico, Universidad Nacional Autónoma de México; National Institutes of Health; National Science Foundation","keywords":"Computer science; Task (project management); Natural language processing; Information retrieval; World Wide Web; Artificial intelligence; Engineering","score_opus":0.017758986228998432,"score_gpt":0.252505487475985,"score_spread":0.23474650124698657,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2516150684","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97806734,0.0020004238,0.013180202,0.001375519,0.001632349,0.0002487519,0.001212617,0.00012433226,0.002158477],"genre_scores_gemma":[0.99961346,0.00015988335,0.00011724058,0.000016904918,0.00002339398,0.000008251683,0.000014183007,0.0000048698807,0.000041779098],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99977136,0.000007811152,0.000070116825,0.00004558664,0.00004506041,0.000060082293],"domain_scores_gemma":[0.9997872,0.000045313674,0.000008468266,0.00013426632,0.00000650706,0.000018221275],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000042163898,0.000038376795,0.000047566304,0.000028703033,0.0000036893887,0.0000011671232,0.00007233275,0.00001436826,0.00007405499],"category_scores_gemma":[0.00004388728,0.000019560879,0.000013389298,0.00012785013,0.00002115052,0.00007140706,0.00002271405,0.000040194696,0.000014439233],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005294213,0.0004072326,0.01584092,0.0026732867,0.00018856818,0.000009433461,0.003680715,0.00028484748,0.6460127,0.008158434,0.144757,0.17793392],"study_design_scores_gemma":[0.0024453483,0.000058326954,0.38759354,0.00729149,0.000057638645,0.000013269987,0.00039332843,0.016346136,0.38207096,0.00095285574,0.20196757,0.0008095521],"about_ca_topic_score_codex":0.000033844888,"about_ca_topic_score_gemma":0.000011143282,"teacher_disagreement_score":0.37175262,"about_ca_system_score_codex":0.00003141204,"about_ca_system_score_gemma":0.0000065209015,"threshold_uncertainty_score":0.08108502},"labels":[],"label_agreement":null},{"id":"W2568859793","doi":"10.1093/database/baw160","title":"FirebrowseR: an R client to the Broad Institute’s Firehose Pipeline","year":2016,"lang":"en","type":"article","venue":"Database","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":224,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Children's Hospital; University of Calgary","funders":"","keywords":"Computer science; Workflow; Pipeline (software); Application programming interface; Web service; Software; Database; World Wide Web; Interface (matter); Software engineering; Task (project management); Service (business); Operating system","score_opus":0.014081698061545926,"score_gpt":0.2552758913824826,"score_spread":0.24119419332093664,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2568859793","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84923846,0.0007701184,0.13562022,0.007630552,0.0014147455,0.00074188085,0.0022470052,0.000047688623,0.0022893182],"genre_scores_gemma":[0.9874388,0.00027598056,0.0022852898,0.0052371323,0.001056523,0.0000371203,0.0015154445,0.000020936279,0.0021327725],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992206,0.000023747501,0.00018941402,0.00023452524,0.00009526633,0.0002364425],"domain_scores_gemma":[0.9988702,0.000006966324,0.00004551971,0.0008810028,0.000037815025,0.0001584944],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024268849,0.00012206947,0.00007888664,0.000017718605,0.00010456528,0.000025366686,0.00035905614,0.000060585924,0.000054664815],"category_scores_gemma":[0.000053110238,0.00006648264,0.000042175332,0.000057929923,0.000058888883,0.000012217844,0.00028235247,0.000051647006,0.0002337969],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018300948,0.00014535322,0.0004836209,0.000015409183,0.000036057678,0.0000068527547,0.00014477698,0.00012182231,0.11734485,0.001122413,0.57621217,0.30418363],"study_design_scores_gemma":[0.00038534205,0.00011946353,0.00030440005,0.000019730005,0.000008502373,0.000009910288,0.000023159615,0.00036251277,0.009955897,0.000031396754,0.9886195,0.00016017583],"about_ca_topic_score_codex":0.00005290318,"about_ca_topic_score_gemma":0.0005554553,"teacher_disagreement_score":0.4124073,"about_ca_system_score_codex":0.000009444834,"about_ca_system_score_gemma":0.000043993085,"threshold_uncertainty_score":0.3005064},"labels":[],"label_agreement":null},{"id":"W2573117738","doi":"10.1093/database/baw147","title":"The BioC-BioGRID corpus: full text articles annotated for curation of protein–protein and genetic interactions","year":2016,"lang":"en","type":"article","venue":"Database","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mount Sinai Hospital; Lunenfeld-Tanenbaum Research Institute; Université de Montréal; Institute for Research in Immunology and Cancer","funders":"Biotechnology and Biological Sciences Research Council; National Institutes of Health","keywords":"Data curation; Annotation; Crowdsourcing; Computer science; Task (project management); Information retrieval; Gene Annotation; Pipeline (software); World Wide Web; Data science; Natural language processing; Computational biology; Artificial intelligence; Biology; Gene; Genome; Genetics; Engineering","score_opus":0.019403511412564904,"score_gpt":0.2759297630851905,"score_spread":0.2565262516726256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2573117738","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9710662,0.0010574234,0.02551145,0.0013936888,0.000060599185,0.0003446392,0.0005442362,0.0000125097895,0.000009284087],"genre_scores_gemma":[0.99329215,0.00015047271,0.005890212,0.0000332696,0.00009373903,0.00012455929,0.00015257692,0.00000824701,0.00025475098],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99942833,0.000038237704,0.0001615728,0.00018199912,0.000056501263,0.00013338146],"domain_scores_gemma":[0.9995033,0.000053051375,0.0000813247,0.00024967946,0.00006849495,0.000044109605],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011393637,0.000074678836,0.0000680319,0.00002094924,0.00009412682,0.000013879023,0.00009384326,0.00004471678,0.0000059491763],"category_scores_gemma":[0.0004474924,0.00004102988,0.000028956103,0.00004939031,0.0002462814,0.0000060725065,0.00006763715,0.000027654276,0.0000035257508],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001551587,0.000025544572,0.0001181388,0.000014720692,0.000017789664,5.7670394e-7,0.000009160304,7.52332e-8,0.8859626,0.00008546959,0.0013646481,0.1122461],"study_design_scores_gemma":[0.00057128456,0.00041027606,0.00067245256,0.00006853007,0.000012909456,0.000010549825,0.00007688805,0.00009093356,0.8648543,0.00017316018,0.13296415,0.00009456659],"about_ca_topic_score_codex":0.000016830929,"about_ca_topic_score_gemma":0.00009774917,"teacher_disagreement_score":0.1315995,"about_ca_system_score_codex":0.0000035780884,"about_ca_system_score_gemma":0.000025130968,"threshold_uncertainty_score":0.167315},"labels":[],"label_agreement":null},{"id":"W2626120835","doi":"10.1093/database/bax048","title":"PigVar: a database of pig variations and positive selection signatures","year":2017,"lang":"en","type":"article","venue":"Database","topic":"Genetic and phenotypic traits in livestock","field":"Biochemistry, Genetics and Molecular Biology","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Selection (genetic algorithm); Database; Computer science; Information retrieval; Artificial intelligence","score_opus":0.011374282493286357,"score_gpt":0.26502520920620565,"score_spread":0.2536509267129193,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2626120835","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9056377,0.0008853086,0.08555085,0.0001969992,0.00023285692,0.00030448224,0.005095296,0.000011846581,0.0020846887],"genre_scores_gemma":[0.971545,0.00006144994,0.026486777,0.000079596466,0.00014671012,0.000008061464,0.0014714557,0.000009288264,0.00019170584],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99943656,0.00003379905,0.00010575719,0.00024083738,0.000071997,0.000111069545],"domain_scores_gemma":[0.9992756,0.000018793846,0.00010525413,0.00047818277,0.000063065294,0.000059051272],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010152824,0.0000911182,0.000082449915,0.000022828302,0.00020811109,0.000023344652,0.00016524289,0.00006300759,0.000026233774],"category_scores_gemma":[0.00020576271,0.0000881305,0.000022952569,0.000019780875,0.00011775306,0.000010209778,0.00017602359,0.000068628004,0.0000025310353],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018400581,0.00018686478,0.01146297,0.00005366204,0.00011728994,0.0000013699785,0.0001114605,0.00005137086,0.944718,0.033472072,0.006948129,0.0026928026],"study_design_scores_gemma":[0.001233961,0.00051629293,0.74449056,0.000069320966,0.00012679376,0.000022756822,0.000050186187,0.0001829299,0.245722,0.0009178823,0.0063136243,0.00035371055],"about_ca_topic_score_codex":0.00015540388,"about_ca_topic_score_gemma":0.000091559734,"teacher_disagreement_score":0.7330276,"about_ca_system_score_codex":0.0000025657796,"about_ca_system_score_gemma":0.000046286175,"threshold_uncertainty_score":0.35938576},"labels":[],"label_agreement":null},{"id":"W2786427465","doi":"10.1093/database/bax076","title":"Database of resistance related metabolites in Wheat Fusarium head blight Disease (MWFD)","year":2017,"lang":"en","type":"article","venue":"Database","topic":"Mycotoxins in Agriculture and Food","field":"Agricultural and Biological Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"National Research Council Canada","keywords":"Fusarium; Head (geology); Blight; Plant disease resistance; Resistance (ecology); Biology; Database; Botany; Computer science; Agronomy; Genetics; Gene","score_opus":0.026633827463476208,"score_gpt":0.25797562512058536,"score_spread":0.23134179765710916,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2786427465","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9776543,0.0036683618,0.0000020480852,0.0032255286,0.00025731063,0.00036614062,0.009874577,0.000051135456,0.004900648],"genre_scores_gemma":[0.9930747,0.0005849136,0.0002661346,0.0001694195,0.00016938569,0.000028981449,0.0044395365,0.0000017228668,0.0012651902],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99833804,0.000100244695,0.0004014867,0.0004972393,0.00030736983,0.00035560963],"domain_scores_gemma":[0.9987497,0.00013044664,0.00024399468,0.000571104,0.000073937736,0.00023083082],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039692875,0.00021088381,0.00031149818,0.000025814603,0.0003032988,0.000090672474,0.00084261765,0.000077581695,0.00042368934],"category_scores_gemma":[0.000418906,0.000079671045,0.000102284444,0.00025905133,0.00014946214,0.0006707772,0.00033698796,0.0002064594,0.0000610709],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040066318,0.0006922011,0.05166735,0.00011851604,0.000036530117,0.00019950235,0.00009026499,8.6081496e-7,0.9149776,0.0082229,0.02044843,0.0031451778],"study_design_scores_gemma":[0.00090940535,0.000076924094,0.71959686,0.00040927972,0.0000890627,0.0000048581687,0.00014890835,0.00003233224,0.060234495,0.0008102664,0.21707973,0.0006078732],"about_ca_topic_score_codex":0.0004214893,"about_ca_topic_score_gemma":0.005271915,"teacher_disagreement_score":0.8547431,"about_ca_system_score_codex":0.000015291462,"about_ca_system_score_gemma":0.00001697,"threshold_uncertainty_score":0.46391013},"labels":[],"label_agreement":null},{"id":"W2795044975","doi":"10.1093/database/bay032","title":"Biopanning data bank 2018: hugging next generation phage display","year":2018,"lang":"en","type":"article","venue":"Database","topic":"Bacteriophages and microbial interactions","field":"Environmental Science","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Natural Science Foundation of China","keywords":"Biopanning; Computer science; Data bank; Library science; Telecommunications; Biology","score_opus":0.10181567766062573,"score_gpt":0.31198551436850214,"score_spread":0.21016983670787642,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2795044975","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9797122,0.000056584642,0.011534262,0.00034508077,0.00122672,0.00017357142,0.002049031,0.00008646879,0.004816122],"genre_scores_gemma":[0.9844035,0.00002985279,0.0075778672,0.0007204052,0.0007612873,0.0000055660125,0.005010979,0.000018638955,0.0014719064],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99913126,0.000027505565,0.00014414854,0.0003896748,0.000093382914,0.00021403824],"domain_scores_gemma":[0.9989962,0.000014752235,0.000056526453,0.00084982254,0.0000052968217,0.00007740375],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00016922323,0.00010275651,0.00007092394,0.000031284126,0.0002875937,0.00011739563,0.0003779106,0.000025966841,0.008838445],"category_scores_gemma":[0.000034772504,0.000095057505,0.000017576745,0.00015710412,0.00012264965,0.0018086208,0.00077157747,0.00009283441,0.0044916077],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000041289322,0.000031766165,0.00021083535,0.0000017616794,0.000004062492,0.000006950175,0.00007338703,0.0000027331598,0.87711954,0.000015289803,0.11592122,0.0066083176],"study_design_scores_gemma":[0.0002542082,0.00004476936,0.006110254,0.000032357482,0.000035348785,0.00004773089,0.000066058055,0.02766637,0.07251802,0.0000030058864,0.8929295,0.0002923584],"about_ca_topic_score_codex":0.0009850716,"about_ca_topic_score_gemma":0.00071896863,"teacher_disagreement_score":0.80460155,"about_ca_system_score_codex":0.000049446295,"about_ca_system_score_gemma":0.0000063004286,"threshold_uncertainty_score":0.99628353},"labels":[],"label_agreement":null},{"id":"W2807602500","doi":"10.1093/database/bay044","title":"CircR2Disease: a manually curated database for experimentally supported circular RNAs associated with various diseases","year":2018,"lang":"en","type":"article","venue":"Database","topic":"Circular RNAs in diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":248,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"National Natural Science Foundation of China","keywords":"Computer science; Database; Circular RNA; Mechanism (biology); Disease; Computational biology; Bioinformatics; Biology; Gene; microRNA; Medicine; Genetics; Pathology","score_opus":0.014955260272099105,"score_gpt":0.28326290417516864,"score_spread":0.26830764390306955,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2807602500","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9371914,0.0024838324,0.019223267,0.000090800946,0.00031958547,0.001624617,0.038570326,0.00020182545,0.00029433295],"genre_scores_gemma":[0.9006192,0.00004959019,0.0008266128,0.0008870713,0.00043727175,0.0003483634,0.09648461,0.00012115007,0.00022611821],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9972718,0.00013790512,0.00038045787,0.0010843523,0.00043629913,0.0006891898],"domain_scores_gemma":[0.9972011,0.000048190166,0.00021646744,0.001566108,0.0004241219,0.00054400566],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00020504695,0.0004526373,0.00031865406,0.00010136919,0.0003194827,0.00010682919,0.0005870064,0.0001308799,0.00030183082],"category_scores_gemma":[0.0008246255,0.00044241565,0.00018494864,0.00027043096,0.00042840856,0.00004410298,0.00033514528,0.00009893424,0.000040755196],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018954603,0.0020796612,0.010661394,0.0001479084,0.001103619,0.0003863567,0.00006351616,0.0000108694485,0.9152968,0.0001877976,0.067603074,0.00056353933],"study_design_scores_gemma":[0.019583836,0.003447691,0.037940428,0.0005920319,0.0025031888,0.00021708255,0.0006236264,0.0014650722,0.77527416,0.00015821884,0.15426418,0.003930495],"about_ca_topic_score_codex":0.000054769796,"about_ca_topic_score_gemma":0.00011684141,"teacher_disagreement_score":0.14002265,"about_ca_system_score_codex":0.000072918716,"about_ca_system_score_gemma":0.0005290095,"threshold_uncertainty_score":0.99980277},"labels":[],"label_agreement":null},{"id":"W2890022719","doi":"10.1093/database/bay086","title":"Spfy: an integrated graph database for real-time prediction of bacterial phenotypes and downstream comparative analyses","year":2018,"lang":"en","type":"article","venue":"Database","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Agency of Canada","funders":"Public Health Agency of Canada","keywords":"Genome; Workflow; Computer science; Genomics; Computational biology; Comparative genomics; Identification (biology); In silico; Population; Biology; Data mining; Database; Genetics; Gene","score_opus":0.050896086236707855,"score_gpt":0.3228503856870912,"score_spread":0.2719542994503833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2890022719","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9796211,0.00019521872,0.0011719533,0.000007344073,0.00010818069,0.0002168892,0.018528944,0.0000048792617,0.0001455002],"genre_scores_gemma":[0.9715241,0.0003542704,0.010085584,0.000019868998,0.00036251193,0.000022528495,0.017585617,0.000011680699,0.000033843236],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992557,0.00004691714,0.00018612243,0.00032065614,0.000054462023,0.00013613666],"domain_scores_gemma":[0.99929494,0.00001865482,0.00009129717,0.00034981247,0.00017790306,0.00006740366],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012824353,0.00013698396,0.00018865053,0.00004511832,0.00009017598,0.000013800652,0.00009860384,0.000047733134,0.000031601772],"category_scores_gemma":[0.0000390354,0.00011625115,0.000036218436,0.000068330184,0.00023065977,0.0000044641274,0.00009935968,0.0000245695,0.0000019490903],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046016744,0.000080742626,0.0009222522,0.000016518281,0.00013280356,2.4138035e-7,0.00011976747,0.0000023766136,0.9944093,0.000038270584,0.0033224998,0.00049500755],"study_design_scores_gemma":[0.0012688895,0.0015656452,0.005804181,0.000024069273,0.00017913409,0.000004478855,0.0004403013,0.0006398914,0.9704586,0.00004774848,0.01935055,0.00021645572],"about_ca_topic_score_codex":0.00024462776,"about_ca_topic_score_gemma":0.00026004773,"teacher_disagreement_score":0.023950698,"about_ca_system_score_codex":0.0000034016718,"about_ca_system_score_gemma":0.000038766048,"threshold_uncertainty_score":0.47405842},"labels":[],"label_agreement":null},{"id":"W2914171828","doi":"10.1093/database/bay147","title":"Overview of the BioCreative VI Precision Medicine Track: mining protein interactions and mutations for precision medicine","year":2018,"lang":"en","type":"article","venue":"Database","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":75,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Institute for Research in Immunology and Cancer","funders":"U.S. National Library of Medicine; National Institute of General Medical Sciences; National Cancer Institute; National Institutes of Health","keywords":"Computer science; Task (project management); Precision medicine; Triage; F1 score; Relationship extraction; Precision and recall; Annotation; Information extraction; Named-entity recognition; Information retrieval; Relation (database); Personalized medicine; Natural language processing; Data science; Data mining; Artificial intelligence; Bioinformatics; Medicine; Genetics; Biology","score_opus":0.07326093043933397,"score_gpt":0.3871233921750868,"score_spread":0.31386246173575283,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2914171828","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9582034,0.0038829031,0.031158173,0.004018608,0.00043417286,0.00089176034,0.00068205554,0.000019625995,0.0007093024],"genre_scores_gemma":[0.9872432,0.000271616,0.010233301,0.00024336856,0.0004900059,0.000086424894,0.0006876171,0.000013971068,0.00073051744],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991817,0.000074784584,0.00024763276,0.0002522478,0.0001287034,0.00011491975],"domain_scores_gemma":[0.99914515,0.00018018717,0.00013779692,0.00033454256,0.00014731412,0.00005502225],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036563707,0.00010323907,0.00015760002,0.000045668337,0.00013604277,0.000003853531,0.00015419125,0.0000639827,0.000064497384],"category_scores_gemma":[0.002363009,0.000058615828,0.000033099324,0.0001321446,0.00074713666,0.0000062630475,0.00013019839,0.000057142577,0.0000011269506],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029431755,0.00008085088,0.00035787138,0.00010593345,0.00006258376,5.833111e-7,0.00093611947,3.228634e-7,0.81253576,0.0002522801,0.028776025,0.15659735],"study_design_scores_gemma":[0.0030735545,0.0032377474,0.008418423,0.002766217,0.00020392957,0.00004004377,0.0025524285,0.00052941183,0.49162078,0.0010542363,0.48621348,0.00028977045],"about_ca_topic_score_codex":0.000058181093,"about_ca_topic_score_gemma":0.00011006933,"teacher_disagreement_score":0.45743746,"about_ca_system_score_codex":0.000005825013,"about_ca_system_score_gemma":0.000033718527,"threshold_uncertainty_score":0.2828913},"labels":[],"label_agreement":null},{"id":"W2920215701","doi":"10.1093/database/baz033","title":"Update on cpnDB: a reference database of chaperonin sequences","year":2019,"lang":"en","type":"article","venue":"Database","topic":"Heat shock proteins research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Chaperonin; GroEL; Biology; Phylogenetic tree; Computational biology; Identification (biology); Sequence analysis; Sequence (biology); Database; Computer science; Genetics; Ecology; Gene","score_opus":0.03033648656265123,"score_gpt":0.3165121856923562,"score_spread":0.2861756991297049,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2920215701","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99307275,0.00029976422,0.00023047913,0.00017291046,0.000057659156,0.00035075573,0.0024835737,0.000010755558,0.0033213827],"genre_scores_gemma":[0.9924149,0.00041912356,0.0012933887,0.0002488851,0.00006272356,0.000031309486,0.0048245573,0.00001881644,0.00068632275],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986582,0.00009951638,0.00018860276,0.00046194615,0.00029327217,0.00029846447],"domain_scores_gemma":[0.99858665,0.000019380095,0.000053037587,0.0011483872,0.00007777818,0.000114787064],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003686598,0.0001363198,0.00014467043,0.000068855996,0.000036581692,0.000012509593,0.00042409974,0.00007684337,0.00056346407],"category_scores_gemma":[0.00017156774,0.00011870435,0.000035525027,0.000119358774,0.0000895252,0.000011739083,0.00037388667,0.00016268772,0.00057361287],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016850636,0.00007904601,0.0008738259,0.00007938876,0.000017549479,0.000010499286,0.000008313329,0.000009148887,0.9940237,0.0009749472,0.0025133472,0.0012417693],"study_design_scores_gemma":[0.0004675828,0.00040468978,0.0002475072,0.000078909026,0.0000043802215,0.000006865149,0.00003410463,0.00009960746,0.9028697,0.000010470519,0.095610045,0.00016611787],"about_ca_topic_score_codex":0.00018298124,"about_ca_topic_score_gemma":0.000054977405,"teacher_disagreement_score":0.093096696,"about_ca_system_score_codex":0.000013847018,"about_ca_system_score_gemma":0.00017855436,"threshold_uncertainty_score":0.7372824},"labels":[],"label_agreement":null},{"id":"W2951817054","doi":"10.1093/database/baz022","title":"AYbRAH: a curated ortholog database for yeasts and fungi spanning 600 million years of evolution","year":2019,"lang":"en","type":"article","venue":"Database","topic":"Fungal and yeast genetics research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Ontario Ministry of Research and Innovation; Natural Sciences and Engineering Research Council of Canada","keywords":"Biology; Phylogenetics; Phylogenetic tree; Genome; KEGG; Phylogenomics; Database; Computational biology; Gene; Genetics; Transcriptome; Clade","score_opus":0.017373495672108906,"score_gpt":0.2865527150731592,"score_spread":0.26917921940105033,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2951817054","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9916703,0.00159516,0.0040296647,0.000027395692,0.00009927705,0.00033118483,0.0021553931,0.0000064373257,0.00008515564],"genre_scores_gemma":[0.99206656,0.00029969343,0.002571003,0.000033321885,0.00007898446,0.000018199215,0.00452844,0.000017734557,0.0003860455],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991284,0.000038605252,0.00015931526,0.0003283616,0.00012956753,0.00021574067],"domain_scores_gemma":[0.9993444,0.000020388847,0.000059772916,0.00039562755,0.00009830626,0.00008152351],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024696073,0.00009602054,0.00011589522,0.00006767686,0.00003071482,0.000010607836,0.000121134246,0.0000720027,0.000027898814],"category_scores_gemma":[0.00012102393,0.0000976663,0.00003849916,0.00010362376,0.000058939724,0.0000091724,0.00021809564,0.000068982095,0.000022258379],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024146552,0.000043291453,0.008578976,0.00010756533,0.000021554257,0.000002978271,0.0000146315115,0.000023686855,0.9869092,0.00010586372,0.001716773,0.002234018],"study_design_scores_gemma":[0.0033102743,0.0010896754,0.035070498,0.00018959992,0.00005867267,0.000046595393,0.00018704368,0.0047506285,0.89754194,0.00006686098,0.057136975,0.0005512579],"about_ca_topic_score_codex":0.00004446952,"about_ca_topic_score_gemma":0.000015825563,"teacher_disagreement_score":0.08936728,"about_ca_system_score_codex":0.0000068437557,"about_ca_system_score_gemma":0.00006464734,"threshold_uncertainty_score":0.39827162},"labels":[],"label_agreement":null},{"id":"W2952216057","doi":"10.1093/database/baw015","title":"Wikidata as a semantic framework for the Gene Wiki initiative","year":2016,"lang":"en","type":"article","venue":"Database","topic":"Wikis in Education and Collaboration","field":"Social Sciences","cited_by":61,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Institute of General Medical Sciences; National Institute on Drug Abuse; National Institutes of Health","keywords":"SPARQL; Computer science; UniProt; World Wide Web; Dissemination; Metadata; XML; Linked data; JSON; Open data; Semantic Web; Database; RDF; Gene; Biology","score_opus":0.0685358047867713,"score_gpt":0.3994968071533139,"score_spread":0.33096100236654263,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2952216057","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06543783,0.00079926994,0.6611092,0.24599758,0.0051652095,0.0026227527,0.0046320036,0.00025580206,0.013980332],"genre_scores_gemma":[0.97629476,0.00067366107,0.0117284,0.006153515,0.0020016453,0.00032707464,0.00027062694,0.000017288028,0.002533059],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99925953,0.00010682988,0.00010115754,0.00016019387,0.00020338393,0.00016890715],"domain_scores_gemma":[0.9982049,0.0011567739,0.000066929286,0.00035689276,0.00014927388,0.00006525252],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00059495546,0.000057097506,0.00005524728,0.000025045021,0.0005615337,0.000073094845,0.0002892366,0.00004245331,0.00068808335],"category_scores_gemma":[0.0032371548,0.000033443448,0.000022324368,0.0002564564,0.00017945556,0.00038651624,0.000039723705,0.000046696812,0.0002783531],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003763434,0.000074086405,0.0005320892,0.000005448795,0.000025242742,0.0000010927095,0.009130755,2.6285488e-7,0.00045707548,0.8642065,0.10142232,0.024107514],"study_design_scores_gemma":[0.00019989621,0.000020559582,0.0005653776,0.000043406617,0.000024251252,3.9996513e-7,0.008396095,0.00001179425,0.0012509157,0.029091608,0.9602913,0.000104348714],"about_ca_topic_score_codex":0.00033839326,"about_ca_topic_score_gemma":0.0009860838,"teacher_disagreement_score":0.9108569,"about_ca_system_score_codex":0.000048144262,"about_ca_system_score_gemma":0.0004127556,"threshold_uncertainty_score":0.753403},"labels":[],"label_agreement":null},{"id":"W2964307465","doi":"10.1093/database/baz077","title":"Tripal v3: an ontology-based toolkit for construction of FAIR biological community databases","year":2019,"lang":"en","type":"article","venue":"Database","topic":"Research Data Management Practices","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"National Institute of Food and Agriculture; Agricultural Research Service; Genome Canada; Saskatchewan Pulse Growers; Cotton Incorporated; Washington Tree Fruit Research Commission; U.S. Department of Agriculture; National Science Foundation","keywords":"Computer science; Ontology; World Wide Web; Database; Information retrieval","score_opus":0.2573459647153449,"score_gpt":0.4068510443479609,"score_spread":0.149505079632616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964307465","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3643375,0.00002561012,0.6310281,0.0004467532,0.0002536219,0.00069260114,0.0027777648,0.00015176724,0.0002862902],"genre_scores_gemma":[0.55874944,0.000057758756,0.43204865,0.0005083528,0.000047776164,0.000081462706,0.008439631,0.000014137252,0.000052791016],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978438,0.0007880088,0.00029989769,0.00045834103,0.00028514257,0.00032483443],"domain_scores_gemma":[0.9954599,0.001343859,0.00022071428,0.0027347067,0.00012804217,0.00011275225],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0023342122,0.00014106391,0.00023987943,0.00018785732,0.00016779825,0.00023173571,0.0024303861,0.00004387873,0.000048286045],"category_scores_gemma":[0.0012693806,0.00012085446,0.000045789668,0.00029948933,0.00020989474,0.014280247,0.0010612027,0.00028647005,0.00003584963],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005541833,0.0012373079,0.018817095,0.00033044466,0.00006997211,0.000016369511,0.000080193284,0.00004279919,0.024590593,0.9330704,0.0033557585,0.017834872],"study_design_scores_gemma":[0.012765941,0.00741509,0.03556867,0.0002633657,0.00012455674,0.00007182182,0.0026390995,0.1043983,0.095180996,0.0033808702,0.7363141,0.001877201],"about_ca_topic_score_codex":0.0006288003,"about_ca_topic_score_gemma":0.00022782608,"teacher_disagreement_score":0.9296895,"about_ca_system_score_codex":0.000026879312,"about_ca_system_score_gemma":0.00011935336,"threshold_uncertainty_score":0.99950653},"labels":[],"label_agreement":null},{"id":"W2967909176","doi":"10.1093/database/baz089","title":"PICEAdatabase: a web database for Picea omics and phenotypic information","year":2019,"lang":"en","type":"article","venue":"Database","topic":"Molecular Biology Techniques and Applications","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Pinaceae; Picea abies; Biology; Transcriptome; Omics; Ecology; Bioinformatics; Botany; Pinus <genus>; Genetics; Gene","score_opus":0.007577377018596199,"score_gpt":0.2544863433214788,"score_spread":0.2469089663028826,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2967909176","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.80218726,0.0005103918,0.18034343,0.00039767782,0.00013441578,0.0015833131,0.014034184,0.000066602835,0.0007427314],"genre_scores_gemma":[0.7775472,0.0010507586,0.085268065,0.004220999,0.0002432266,0.0005736352,0.13049531,0.000050541796,0.0005502842],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99920887,0.000021316693,0.00019383742,0.00030658653,0.00006515056,0.00020421851],"domain_scores_gemma":[0.9990284,0.00001742766,0.000086097985,0.00071891723,0.00006814344,0.00008101683],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020736559,0.00014379367,0.00011434465,0.0000493665,0.00007943361,0.00002855917,0.0001801634,0.00009829116,0.000027512111],"category_scores_gemma":[0.000066965295,0.00014059458,0.00004156379,0.00006452308,0.000052344243,0.000029597577,0.0002382746,0.000076815166,0.000040863226],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012581829,0.000045973735,0.0012635026,0.00010434549,0.00002955478,4.4305236e-7,0.0000099431945,0.0000025461868,0.9693354,0.008029609,0.018241506,0.002811401],"study_design_scores_gemma":[0.0010780001,0.00017195233,0.0002774737,0.00001790446,0.00003425026,0.0000190998,0.00004583198,0.0012121001,0.105113454,0.000076774915,0.8916637,0.00028948503],"about_ca_topic_score_codex":0.000020100677,"about_ca_topic_score_gemma":0.000020114065,"teacher_disagreement_score":0.87342215,"about_ca_system_score_codex":0.0000071089726,"about_ca_system_score_gemma":0.00006277234,"threshold_uncertainty_score":0.5733281},"labels":[],"label_agreement":null},{"id":"W2992521260","doi":"10.1093/database/baz123","title":"Reactome and ORCID—fine-grained credit attribution for community curation","year":2019,"lang":"en","type":"article","venue":"Database","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Institute for Cancer Research","funders":"National Human Genome Research Institute; National Institutes of Health; Canada First Research Excellence Fund; National Institute of General Medical Sciences; European Molecular Biology Laboratory; Alfred P. Sloan Foundation","keywords":"Computer science; World Wide Web; Annotation; Attribution; Visibility; Interface (matter); Information retrieval; Data curation; Data science; Artificial intelligence","score_opus":0.017588765438800596,"score_gpt":0.25961206249851887,"score_spread":0.24202329705971828,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2992521260","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.945971,0.00016620755,0.051480748,0.00019218936,0.0001892651,0.00039830653,0.0013121908,0.000010835518,0.00027924817],"genre_scores_gemma":[0.9774829,0.00005391016,0.001920758,0.00025306703,0.00018276143,0.000017646082,0.019837266,0.000008922612,0.00024272378],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995719,0.000028260432,0.00012886828,0.0001035531,0.000041839663,0.00012558645],"domain_scores_gemma":[0.9994703,0.000020763264,0.000060727372,0.00035196103,0.000050344213,0.000045893295],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031957304,0.000079208374,0.000079278725,0.00001664398,0.000091397684,0.000021585114,0.0000846791,0.000077166165,0.000009875593],"category_scores_gemma":[0.000042052834,0.000074248994,0.000026898115,0.00003008662,0.000024447152,0.000009733933,0.00010553402,0.00008710843,0.000010654457],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003764718,0.00010540415,0.0019840815,0.00022314329,0.00006787079,4.6258802e-7,0.0001644212,0.00002805181,0.9397679,0.0043211146,0.037787855,0.015173208],"study_design_scores_gemma":[0.0047300654,0.0011731399,0.0061477027,0.00007406812,0.0000756083,0.00003419381,0.00038828078,0.014548032,0.086278334,0.0012149641,0.88459826,0.00073733844],"about_ca_topic_score_codex":0.00003550007,"about_ca_topic_score_gemma":0.0000680068,"teacher_disagreement_score":0.8534896,"about_ca_system_score_codex":0.000006660693,"about_ca_system_score_gemma":0.000020678352,"threshold_uncertainty_score":0.3027786},"labels":[],"label_agreement":null},{"id":"W3022201072","doi":"10.1093/databa/baaa022","title":"Why data citation isn't working, and what to do about it","year":2020,"lang":"en","type":"article","venue":"Database","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Discovery Centre","funders":"Wellcome Trust; Wellcome","keywords":"Computer science; Citation; Citation database; Information retrieval; Granularity; Process (computing); Database; Data science; Value (mathematics); World Wide Web; Scopus; MEDLINE","score_opus":0.3412421372747082,"score_gpt":0.4181307828633919,"score_spread":0.07688864558868369,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3022201072","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.082103066,0.003314089,0.6831976,0.21187198,0.006597495,0.0012775046,0.004845267,0.00031377818,0.0064792093],"genre_scores_gemma":[0.5860527,0.0009447692,0.10882723,0.2836331,0.0020749401,0.000033352688,0.01451171,0.00007417304,0.0038480007],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9970474,0.00010544796,0.0003588597,0.0012260865,0.0010578268,0.00020437934],"domain_scores_gemma":[0.99656695,0.0005217672,0.00009967585,0.0024435185,0.00007867994,0.00028941908],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0035739376,0.00010410399,0.00013972638,0.0001712524,0.0001712727,0.0038171702,0.0018812448,0.000017037728,0.00074544345],"category_scores_gemma":[0.0049675787,0.000084075655,0.000017106004,0.0011819906,0.000047293724,0.0023216233,0.0035730202,0.000078169076,0.0011815634],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011230521,0.000010111548,0.00043117628,0.000003361844,0.0000033568208,0.000009165978,0.00056573545,0.000028136765,0.000028699134,0.0002833555,0.7729446,0.22568105],"study_design_scores_gemma":[0.0001522831,0.0000173751,0.0011321,0.000060277784,0.000008308165,0.0000011041245,0.003115284,0.016937912,0.00001573015,0.00013248541,0.97831285,0.00011429927],"about_ca_topic_score_codex":0.000054116084,"about_ca_topic_score_gemma":0.000097051205,"teacher_disagreement_score":0.5743704,"about_ca_system_score_codex":0.000007228095,"about_ca_system_score_gemma":0.000019293328,"threshold_uncertainty_score":0.9995961},"labels":[],"label_agreement":null},{"id":"W3034243427","doi":"10.1093/database/baaa045","title":"Curation of cancer hallmark-based genes and pathways for in silico characterization of chemical carcinogenesis","year":2020,"lang":"en","type":"article","venue":"Database","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Kaohsiung Medical University Chung-Ho Memorial Hospital; National Health Research Institutes; Taipei Medical University; Kaohsiung Medical University; Ministry of Science and Technology, Taiwan","keywords":"Toxicogenomics; In silico; Carcinogen; Post hoc; Computer science; Data curation; Computational biology; Database; Biology; Data mining; Gene; Genetics; Medicine","score_opus":0.0536775691608744,"score_gpt":0.30342496570728045,"score_spread":0.24974739654640604,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3034243427","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6191543,0.00007283648,0.37974283,0.00035862433,0.000024202942,0.00012491176,0.0005142582,0.0000068892327,0.0000011898417],"genre_scores_gemma":[0.96336114,0.000015655705,0.0359741,0.00015719296,0.000027401951,0.000035048623,0.00042455958,0.000004669393,2.0326557e-7],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99933,0.0000534909,0.00021229708,0.00021037864,0.00012344518,0.000070393144],"domain_scores_gemma":[0.9994763,0.00016245578,0.00010639205,0.00013908962,0.00007676091,0.000039001312],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015057482,0.00006256018,0.00012987039,0.000052797877,0.000009843781,0.000010270604,0.0001603681,0.00001979217,0.0000027972796],"category_scores_gemma":[0.000102333135,0.00006476298,0.000023153538,0.00022997792,0.000023184193,0.00033107869,0.00008568868,0.000022418899,1.5044922e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004111673,0.000034409833,0.005423292,0.00016960928,0.0000036518268,5.866529e-7,0.00020169049,0.0011761974,0.9703939,0.003145006,0.000004888858,0.019405631],"study_design_scores_gemma":[0.000266534,0.000016896915,0.011372938,0.000018379898,0.0000040825594,1.3694923e-7,0.0000029168227,0.4481902,0.53997177,0.00007451222,0.000034950157,0.00004668122],"about_ca_topic_score_codex":0.00006304058,"about_ca_topic_score_gemma":0.000009202431,"teacher_disagreement_score":0.447014,"about_ca_system_score_codex":0.000012959394,"about_ca_system_score_gemma":0.000118479504,"threshold_uncertainty_score":0.26409575},"labels":[],"label_agreement":null},{"id":"W3036787676","doi":"10.1093/databa/baaa033","title":"FOBI: an ontology to represent food intake data and associate it with metabolomic data","year":2020,"lang":"en","type":"article","venue":"Database","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"European Institute of Innovation and Technology","keywords":"Ontology; Computer science; Open Biomedical Ontologies; Visualization; Data science; Ontology-based data integration; Information retrieval; Annotation; Workflow; Identification (biology); Data mining; Suggested Upper Merged Ontology; Database; Semantic Web; Artificial intelligence","score_opus":0.1022735384683664,"score_gpt":0.3213407420082993,"score_spread":0.21906720353993292,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3036787676","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9500591,0.0034176165,0.007366362,0.011312022,0.00015566993,0.0005159094,0.026666189,0.00003504166,0.00047205325],"genre_scores_gemma":[0.936976,0.0014334472,0.020561114,0.0069879107,0.00052095,0.000023724262,0.033352107,0.000047468704,0.00009728417],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979591,0.00009780636,0.00022306293,0.0012580281,0.00014502883,0.0003169859],"domain_scores_gemma":[0.99690765,0.000020958418,0.0000950929,0.0026449373,0.00004920435,0.00028214522],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003958357,0.00020999578,0.00032390218,0.000037958212,0.00009857445,0.000046877027,0.0011629645,0.00006704699,0.000028605322],"category_scores_gemma":[0.00058146636,0.000176528,0.000016101303,0.00014458911,0.00007394573,0.00003126193,0.003966822,0.00012567171,0.000011711173],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017441107,0.00042067107,0.017653966,0.00010937808,0.0020115941,0.0000843948,0.00045468967,0.000011428617,0.59402597,0.0015027532,0.37378323,0.008197825],"study_design_scores_gemma":[0.0013439225,0.001301829,0.0035925054,0.000008857483,0.0002497841,0.00002894487,0.0005265138,0.0005754513,0.020424211,0.000023101184,0.97143096,0.0004939516],"about_ca_topic_score_codex":0.00012776758,"about_ca_topic_score_gemma":0.0026224244,"teacher_disagreement_score":0.59764767,"about_ca_system_score_codex":0.00000520924,"about_ca_system_score_gemma":0.00006568592,"threshold_uncertainty_score":0.7198603},"labels":[],"label_agreement":null},{"id":"W3041921794","doi":"10.1093/database/baaa052","title":"Autophagy and Tumor Database: ATdb, a novel database connecting autophagy and tumor","year":2020,"lang":"en","type":"article","venue":"Database","topic":"Autophagy in Disease and Therapy","field":"Medicine","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Fundamental Research Funds for the Central Universities; Zhejiang University; Natural Science Foundation of Zhejiang Province; National Natural Science Foundation of China","keywords":"Autophagy; Carcinogenesis; Biology; Database; Context (archaeology); microRNA; Computational biology; Bioinformatics; Cancer; Computer science; Cancer research; Gene; Genetics; Apoptosis","score_opus":0.035899491770201165,"score_gpt":0.29222322821871366,"score_spread":0.2563237364485125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3041921794","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9733106,0.006836503,0.004023331,0.0017962744,0.00024743166,0.0009947083,0.011945271,0.00045801385,0.00038787653],"genre_scores_gemma":[0.95633966,0.00049349567,0.014167353,0.020268975,0.0009889712,0.00008058918,0.0073437733,0.00016486719,0.00015231698],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99691707,0.000086324464,0.00059059035,0.0012294928,0.000497521,0.00067900127],"domain_scores_gemma":[0.9970586,0.00029822745,0.00023096352,0.0010776792,0.000096277894,0.0012382966],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004206109,0.0005396983,0.0007494765,0.00015688445,0.00032695627,0.00010525445,0.00026386863,0.00006866395,0.0009409346],"category_scores_gemma":[0.0009074366,0.0005026904,0.00009849488,0.00040359204,0.0002541157,0.0007517575,0.00066605816,0.00056951464,0.00012960933],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003255374,0.0015776375,0.0039774952,0.0034799366,0.0007735343,0.0139510175,0.0018024239,0.0000056286103,0.9285197,0.008417358,0.025103372,0.009136499],"study_design_scores_gemma":[0.054126874,0.002550032,0.028606629,0.0029106853,0.0028835656,0.008590375,0.003923628,0.07335541,0.45853004,0.00017441643,0.3600496,0.004298762],"about_ca_topic_score_codex":0.00023626476,"about_ca_topic_score_gemma":0.000018281118,"teacher_disagreement_score":0.4699897,"about_ca_system_score_codex":0.000043693108,"about_ca_system_score_gemma":0.00025913367,"threshold_uncertainty_score":0.99997234},"labels":[],"label_agreement":null},{"id":"W3099269015","doi":"10.1093/database/baaa096","title":"The IMEx coronavirus interactome: an evolving map of <i>Coronaviridae</i> –host molecular interactions","year":2020,"lang":"en","type":"article","venue":"Database","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Discovery Centre; University Health Network","funders":"H2020 European Research Council; National Institute of Diabetes and Digestive and Kidney Diseases; National Institute of Allergy and Infectious Diseases; National Institute of General Medical Sciences; National Cancer Institute; Wellcome Trust; National Human Genome Research Institute; National Institute of Mental Health; National Heart, Lung, and Blood Institute; National Eye Institute; National Institute on Aging; Associazione Italiana per la Ricerca sul Cancro; Fondation pour la Recherche Médicale; Canada Foundation for Innovation; European Molecular Biology Laboratory; Natural Sciences and Engineering Research Council of Canada; International Business Machines Corporation","keywords":"Interactome; Coronaviridae; Coronavirus disease 2019 (COVID-19); Coronavirus; Computational biology; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Pandemic; Proteomics; Biology; Computer science; Disease; Medicine; Genetics; Infectious disease (medical specialty); Gene","score_opus":0.020227507019509622,"score_gpt":0.28447117888153034,"score_spread":0.2642436718620207,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3099269015","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91476214,0.0061537693,0.067086734,0.0036266323,0.0013567319,0.0008072538,0.0027472607,0.00006304847,0.0033964114],"genre_scores_gemma":[0.9953229,0.00011283386,0.0013989612,0.0014143971,0.00020210764,0.0000116969195,0.0014336191,0.000021684173,0.00008182812],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991077,0.000046227095,0.000305487,0.00021993961,0.000111834466,0.0002087722],"domain_scores_gemma":[0.99905664,0.000022081693,0.00014548628,0.00054235745,0.00008626406,0.00014719166],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014453118,0.00014211671,0.00011962281,0.000013387359,0.00011293392,0.000053305732,0.0003835816,0.00005095851,0.000073385876],"category_scores_gemma":[0.000060318587,0.00011447623,0.0000795305,0.000058588175,0.000092970055,0.000023326204,0.00031608596,0.00017096507,0.00004965748],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019477819,0.000066666296,0.00033891088,0.00003884334,0.00009449694,0.000008506819,0.00018904732,0.00010077519,0.9661389,0.00049616036,0.022818271,0.009514639],"study_design_scores_gemma":[0.00093312864,0.00052467687,0.0007057665,0.000056122313,0.00007415585,0.000033339653,0.0008503874,0.016039195,0.18575528,0.00006954799,0.7944581,0.0005003125],"about_ca_topic_score_codex":0.000038602593,"about_ca_topic_score_gemma":0.000059030353,"teacher_disagreement_score":0.78038365,"about_ca_system_score_codex":0.000009139587,"about_ca_system_score_gemma":0.000050081766,"threshold_uncertainty_score":0.4668205},"labels":[],"label_agreement":null},{"id":"W3101981777","doi":"10.1093/database/baaa079","title":"Measurement Recorder: developing a useful tool for making species descriptions that produces computable phenotypes","year":2020,"lang":"en","type":"article","venue":"Database","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Agriculture and Agri-Food Canada; University of Manitoba","funders":"National Science Foundation","keywords":"Computer science; Usability; Software; Set (abstract data type); Ontology; Reuse; Variation (astronomy); Character (mathematics); Information retrieval; Data science; Software engineering; Human–computer interaction; Programming language","score_opus":0.17239052536197122,"score_gpt":0.3014869736680668,"score_spread":0.1290964483060956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3101981777","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21921363,0.004027871,0.7663577,0.00801827,0.00062200625,0.0006969587,0.00064820016,0.00014567758,0.00026963884],"genre_scores_gemma":[0.8540167,0.00015995248,0.14191797,0.0023434141,0.00064395927,0.00007956636,0.00070476375,0.000024428582,0.00010919621],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99905896,0.000030852705,0.00014946004,0.00037076653,0.00015828216,0.00023166212],"domain_scores_gemma":[0.9995693,0.000013768754,0.000057746453,0.00021147128,0.00009651194,0.000051190098],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024030986,0.00012540283,0.00013487204,0.000019338224,0.00014286596,0.00004497489,0.00018715193,0.000058819158,0.00001753661],"category_scores_gemma":[0.00063414854,0.000110654655,0.00004858747,0.000077394216,0.00006725681,0.000006680304,0.00015760055,0.00005984437,0.0000078918165],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00057217403,0.00019205717,0.015418687,0.00080923183,0.00035875494,0.000013115606,0.0006344827,0.00007095023,0.6160818,0.00088434975,0.28193086,0.08303358],"study_design_scores_gemma":[0.0004306985,0.0001543636,0.0013654467,0.00009538631,0.000028940165,0.0000041947123,0.00027070043,0.00024956407,0.0819675,0.000040278002,0.91514,0.00025295423],"about_ca_topic_score_codex":0.000005694515,"about_ca_topic_score_gemma":0.00003330935,"teacher_disagreement_score":0.6348031,"about_ca_system_score_codex":0.000017269478,"about_ca_system_score_gemma":0.00010682317,"threshold_uncertainty_score":0.45123658},"labels":[],"label_agreement":null},{"id":"W3121051245","doi":"10.1093/database/baaa072","title":"People are essential to linking biodiversity data","year":2020,"lang":"en","type":"article","venue":"Database","topic":"Species Distribution and Climate Change","field":"Environmental Science","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Agriculture and Agri-Food Canada","funders":"Horizon 2020 Framework Programme; European Cooperation in Science and Technology; European Commission","keywords":"Digitization; Metadata; Biodiversity; Computer science; Herbarium; Data curation; Data science; Incentive; Citizen science; World Wide Web; Information retrieval; Ecology; Biology","score_opus":0.07942744792015947,"score_gpt":0.2676297436586908,"score_spread":0.1882022957385313,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3121051245","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95547867,0.000012548399,0.0011944197,0.013484628,0.00014709438,0.0001404525,0.027008098,0.00008972327,0.0024443811],"genre_scores_gemma":[0.9687755,0.000031802643,0.0005698575,0.009850895,0.00011142772,0.0000030057777,0.020612359,0.0000061637643,0.000038958646],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992562,0.0000133443655,0.0000643966,0.00032500245,0.00018851623,0.00015253038],"domain_scores_gemma":[0.99914175,0.0000105067675,0.000027760234,0.00061539584,0.0000034685302,0.00020113667],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00006768416,0.00006401836,0.00006739326,0.000006815022,0.00011418364,0.000033440996,0.0007317442,0.000017132843,0.068051465],"category_scores_gemma":[0.00012549419,0.000065298555,0.000014594407,0.00023231003,0.000029832798,0.00025240763,0.0032157355,0.00005696939,0.018339492],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020380114,0.00004152807,0.13802008,0.000010358259,0.0000033058386,0.000022888637,0.00031210342,0.000005329243,0.004768314,0.000026091155,0.85659206,0.00017754188],"study_design_scores_gemma":[0.00035561481,0.000023410252,0.1815169,0.000007742835,0.00002241931,0.0000023417147,0.0030148525,0.00045989585,0.0020838326,0.0000019222202,0.81226474,0.00024635007],"about_ca_topic_score_codex":0.00054547185,"about_ca_topic_score_gemma":0.00173443,"teacher_disagreement_score":0.04971197,"about_ca_system_score_codex":0.000058441274,"about_ca_system_score_gemma":0.0000029697062,"threshold_uncertainty_score":0.98242486},"labels":[],"label_agreement":null},{"id":"W3130317325","doi":"10.1093/database/baab006","title":"Curation of over 10 000 transcriptomic studies to enable data reuse","year":2021,"lang":"en","type":"article","venue":"Database","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":60,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; Genome British Columbia; University of British Columbia","funders":"National Institute of Mental Health; Natural Sciences and Engineering Research Council of Canada","keywords":"Metadata; Computer science; Reuse; Software; Data curation; Gemma; World Wide Web; Database; Information retrieval; Data science; Biology","score_opus":0.09921660307901177,"score_gpt":0.3764284461266624,"score_spread":0.2772118430476506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3130317325","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9750338,0.008697136,0.0077362885,0.0021965047,0.0005575391,0.0002762487,0.004509044,0.000019232908,0.0009741718],"genre_scores_gemma":[0.9653775,0.0024855863,0.0071455133,0.0009998312,0.0002785509,0.000036512476,0.018857818,0.000022984517,0.004795699],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993147,0.000040856863,0.00014453224,0.0003195024,0.00009333382,0.00008705322],"domain_scores_gemma":[0.99777037,0.0000055702185,0.000041730833,0.0020306897,0.00010640956,0.000045237182],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011406491,0.0000663417,0.00008453682,0.000023865716,0.000030923115,0.000008962059,0.0003796448,0.00003307928,0.00018246885],"category_scores_gemma":[0.00039277697,0.00006288498,0.000019568124,0.00010318025,0.000019900537,0.000013821807,0.00044293975,0.000027405076,0.000012723546],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039790968,0.000031989584,0.000081142534,0.000021466254,0.000019530804,0.0000010201775,0.000040945688,0.0000050711315,0.71449953,0.000043915414,0.28479466,0.0004209184],"study_design_scores_gemma":[0.00019773601,0.000021845311,0.00023668505,0.000017690487,0.000012943424,0.0000011666407,0.00016668219,0.00002525478,0.6092438,0.000020407373,0.38999912,0.00005664242],"about_ca_topic_score_codex":0.000014960111,"about_ca_topic_score_gemma":0.000084027015,"teacher_disagreement_score":0.10525572,"about_ca_system_score_codex":0.0000068451677,"about_ca_system_score_gemma":0.00007598367,"threshold_uncertainty_score":0.2564375},"labels":[],"label_agreement":null},{"id":"W3159409148","doi":"10.1093/database/baab021","title":"Increasing metadata coverage of SRA BioSample entries using deep learning–based named entity recognition","year":2021,"lang":"en","type":"article","venue":"Database","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research; National Institutes of Health; National Institute of General Medical Sciences; Canadian Institute for Advanced Research","keywords":"Metadata; Computer science; Named-entity recognition; Information retrieval; Artificial intelligence; Deep learning; Natural language processing; World Wide Web","score_opus":0.040499717845373796,"score_gpt":0.29040079590886664,"score_spread":0.24990107806349285,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3159409148","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9088464,0.0013294492,0.08848692,0.000048029775,0.00011244576,0.000051572002,0.0010597217,0.000018532215,0.000046930152],"genre_scores_gemma":[0.94909245,0.00030748194,0.034835428,0.0001803405,0.00008935053,0.0000036147171,0.015437802,0.000013524956,0.000040019953],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99890184,0.00024446347,0.00020752115,0.00031103604,0.00014837216,0.00018678916],"domain_scores_gemma":[0.999254,0.00008700849,0.000117845295,0.0003518255,0.00011910809,0.00007021322],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003590198,0.000114275834,0.00017394467,0.000041377378,0.00009522476,0.000035766716,0.00011786779,0.00010800498,0.00011359344],"category_scores_gemma":[0.0024682363,0.00011362202,0.00007026361,0.00014408975,0.0001452039,0.000012917365,0.00019600891,0.00011223288,0.0000042377364],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018661114,0.0001686676,0.009135325,0.00011711526,0.00009304475,0.00004246615,0.00002449843,0.00003492086,0.9619601,0.000012476545,0.0002500227,0.027974788],"study_design_scores_gemma":[0.0009974871,0.000118495765,0.0011815269,0.00009198205,0.000114298,0.000050709,0.00022192836,0.0013843805,0.92942154,0.000040897117,0.06611771,0.00025903576],"about_ca_topic_score_codex":0.00024929753,"about_ca_topic_score_gemma":0.00009793047,"teacher_disagreement_score":0.065867685,"about_ca_system_score_codex":0.000010634356,"about_ca_system_score_gemma":0.00012874042,"threshold_uncertainty_score":0.46333715},"labels":[],"label_agreement":null},{"id":"W3163423203","doi":"10.1093/database/baab030","title":"Integration of 1:1 orthology maps and updated datasets into Echinobase","year":2021,"lang":"en","type":"article","venue":"Database","topic":"Echinoderm biology and ecology","field":"Agricultural and Biological Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Science Foundation","keywords":"Echinoderm; Strongylocentrotus purpuratus; Resource (disambiguation); Biology; Genome; Variety (cybernetics); Computer science; Data science; Evolutionary biology; Sea urchin; Computational biology; Ecology; Gene; Artificial intelligence; Genetics","score_opus":0.017294260163247997,"score_gpt":0.2432262885103951,"score_spread":0.2259320283471471,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3163423203","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99469656,0.00020718126,0.00003101583,0.0011066011,0.000087410815,0.000048393496,0.0036496746,0.000019319592,0.00015385587],"genre_scores_gemma":[0.9400974,0.0001282707,0.0009743238,0.00063873647,0.000036773727,0.0000032597973,0.05806979,4.1066465e-7,0.000051044906],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99929833,0.0001372635,0.00015818444,0.00024363215,0.000034311295,0.00012824766],"domain_scores_gemma":[0.99964815,0.00011602638,0.000058553407,0.00009118261,0.000035165445,0.000050910192],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017679094,0.00007654424,0.00013456661,0.0000094957895,0.00009168358,0.0000070154465,0.000096417694,0.000092971575,0.00083254045],"category_scores_gemma":[0.00013129356,0.00003189831,0.000020297202,0.0001539869,0.000108332155,0.0001134516,0.00017248625,0.000104666906,0.0000243068],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042649408,0.0000999459,0.041112293,0.000007882975,0.000011767978,0.00007023232,0.000039009614,2.0015709e-7,0.92681015,0.0026985358,0.009738247,0.019369066],"study_design_scores_gemma":[0.0009390891,0.0006111616,0.4381188,0.00004747405,0.000093759496,0.0004852292,0.0012271055,0.00035273706,0.41132933,0.0072802757,0.13889483,0.0006202288],"about_ca_topic_score_codex":0.0005153928,"about_ca_topic_score_gemma":0.020378761,"teacher_disagreement_score":0.5154809,"about_ca_system_score_codex":0.000003807262,"about_ca_system_score_gemma":0.000008639824,"threshold_uncertainty_score":0.9974968},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"National Human Genome Research Institute; National Institutes of Health","keywords":"Computer science; Operationalization; World Wide Web; Data science","score_opus":0.20312183623828936,"score_gpt":0.4157198848331276,"score_spread":0.21259804859483825,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3170771812","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.952533,0.009935922,0.011097659,0.011087933,0.0010047415,0.00086986064,0.004395448,0.000053332344,0.009022096],"genre_scores_gemma":[0.5188601,0.0026198423,0.37741476,0.008894127,0.0010360786,0.00029519224,0.08226245,0.00007805302,0.008539435],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99862707,0.00013317225,0.00022232113,0.00063499,0.00015056088,0.00023189765],"domain_scores_gemma":[0.99853295,0.00004521611,0.000033589124,0.0012351923,0.00006869196,0.000084386724],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00066907116,0.00011613329,0.00016043757,0.00003171723,0.000071695285,0.000106663676,0.0010716292,0.00008485681,0.00017003772],"category_scores_gemma":[0.0023108958,0.00010554914,0.000018624196,0.00014870986,0.0000634168,0.000016783593,0.0044500977,0.000090353235,0.000055005567],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039905927,0.0006435062,0.026007833,0.00010512948,0.0002052516,0.0006415655,0.00028830126,0.00030440517,0.6102062,0.0025952475,0.18379405,0.17480947],"study_design_scores_gemma":[0.0007493924,0.000084739506,0.007018701,0.00007741098,0.000014254169,0.00003025051,0.0004721,0.0004641301,0.027601294,0.000053293115,0.96317047,0.0002639691],"about_ca_topic_score_codex":0.00022449672,"about_ca_topic_score_gemma":0.003848924,"teacher_disagreement_score":0.7793764,"about_ca_system_score_codex":0.000015505288,"about_ca_system_score_gemma":0.00034827442,"threshold_uncertainty_score":0.55467284},"labels":[],"label_agreement":null},{"id":"W3176752316","doi":"10.1093/database/baab035","title":"Which methods are the most effective in enabling novice users to participate in ontology creation? A usability study","year":2021,"lang":"en","type":"article","venue":"Database","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Government of Canada; Agriculture and Agri-Food Canada; University of Manitoba","funders":"Canadian Institutes of Health Research; National Science Foundation","keywords":"Usability; Wizard; Computer science; Ontology; Interoperability; World Wide Web; Set (abstract data type); Think aloud protocol; Data curation; Data science; Information retrieval; Human–computer interaction","score_opus":0.03992296776808297,"score_gpt":0.40249750443283333,"score_spread":0.36257453666475037,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3176752316","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9954387,0.00028258303,0.0024472564,0.0011961038,0.00009129749,0.0003824604,0.00006999625,0.000009189432,0.00008244498],"genre_scores_gemma":[0.99467343,0.000016301312,0.0042951475,0.0005669033,0.00004084574,0.00022853856,0.00014953727,0.0000073804354,0.000021936088],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99784154,0.0010763436,0.00023697331,0.00048813355,0.00009076105,0.00026626384],"domain_scores_gemma":[0.99888027,0.00033411707,0.000046892186,0.0005747729,0.000094872084,0.000069082605],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015462872,0.000116870484,0.0002040718,0.00004563285,0.000055242464,0.000018611538,0.00018468438,0.0000929211,0.000014460473],"category_scores_gemma":[0.0057222135,0.00008842239,0.000023153134,0.0005720299,0.0000721802,0.0000041311773,0.0002951084,0.0001810981,0.0000054418647],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034058274,0.001082018,0.8694698,0.00004170467,0.00006879904,0.00008941861,0.0023845485,0.00022880023,0.09090616,0.000023459155,0.00030861417,0.035056047],"study_design_scores_gemma":[0.0018264711,0.00048588103,0.89539444,0.0000662492,0.000043246582,0.000013103183,0.01940522,0.00038228303,0.069095254,0.000046889912,0.012937726,0.00030321762],"about_ca_topic_score_codex":0.0010050009,"about_ca_topic_score_gemma":0.046234917,"teacher_disagreement_score":0.045229916,"about_ca_system_score_codex":0.00002957826,"about_ca_system_score_gemma":0.000090913614,"threshold_uncertainty_score":0.9711688},"labels":[],"label_agreement":null},{"id":"W3177341850","doi":"10.1093/database/baab032","title":"MetamORF: a repository of unique short open reading frames identified by both experimental and computational approaches for gene and metagene analyses","year":2021,"lang":"en","type":"article","venue":"Database","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Agence Nationale de la Recherche; Canadian Institutes of Health Research; Aix-Marseille Université","keywords":"ORFS; Open reading frame; Genome; Biology; Gene; Genome browser; Computational biology; Genetics; Computer science; Genomics","score_opus":0.08106924100586585,"score_gpt":0.34013706402289134,"score_spread":0.25906782301702547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3177341850","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9024368,0.009213028,0.08716283,0.000031177817,0.00003285748,0.00030506132,0.00072075863,0.000003823322,0.00009370225],"genre_scores_gemma":[0.91985196,0.00009376547,0.07699339,0.00006317822,0.000028578625,0.00008049678,0.0026377684,0.000013089578,0.00023775117],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99925137,0.00008714486,0.00016915497,0.0003332813,0.00007292416,0.00008611128],"domain_scores_gemma":[0.999603,0.000031148982,0.0000588257,0.00021856753,0.00003511852,0.00005338204],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022028701,0.00009755673,0.00017558847,0.00002001532,0.00008497139,0.000059362734,0.000105666666,0.00005092013,0.000006079957],"category_scores_gemma":[0.000043688717,0.00009366239,0.000038205006,0.000033903656,0.000054330838,0.000014350341,0.00024394882,0.00002212618,6.769552e-8],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057216665,0.00006043292,0.0001213792,0.000029711466,0.00017700424,0.0000043099712,0.00003279034,0.00001001717,0.99831223,0.00024679425,0.000490324,0.0004578033],"study_design_scores_gemma":[0.00023677848,0.000057667774,0.00008527436,0.000011124393,0.00007573491,0.000028147517,0.00026463027,0.00032893673,0.99769455,0.00008049348,0.001028394,0.000108273554],"about_ca_topic_score_codex":0.000040727733,"about_ca_topic_score_gemma":0.000003051421,"teacher_disagreement_score":0.017415214,"about_ca_system_score_codex":0.00000332649,"about_ca_system_score_gemma":0.00003938212,"threshold_uncertainty_score":0.38194415},"labels":[],"label_agreement":null},{"id":"W3177366615","doi":"10.1093/database/baab038","title":"ReMeDy: a platform for integrating and sharing published stem cell research data with a focus on iPSC trials","year":2021,"lang":"en","type":"article","venue":"Database","topic":"Pluripotent Stem Cells Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Center for Advancing Translational Sciences; National Heart, Lung, and Blood Institute; Canadian Institutes of Health Research; National Institutes of Health","keywords":"Focus (optics); Data sharing; Computer science; Data science; Stem cell; World Wide Web; Research data; Internet privacy; Medicine; Biology; Data curation; Alternative medicine","score_opus":0.1962832745826133,"score_gpt":0.39653851683930136,"score_spread":0.20025524225668806,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3177366615","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9723103,0.0029504371,0.007241068,0.0016109707,0.00015063162,0.0021864667,0.007957132,0.000036089823,0.0055569154],"genre_scores_gemma":[0.9615588,0.0006099228,0.00874651,0.00016601033,0.00053334207,0.0002548824,0.02440885,0.00009094042,0.0036307352],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9974233,0.00022053302,0.00032765677,0.0010743488,0.00044985043,0.00050430134],"domain_scores_gemma":[0.9971124,0.00040672082,0.000090015084,0.0018846483,0.0003204689,0.00018578248],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005517184,0.00016465271,0.00027979835,0.00011249561,0.00021355176,0.00030625323,0.0006866654,0.00010422138,0.00002629559],"category_scores_gemma":[0.0015459696,0.00012602909,0.000039009734,0.00023774175,0.00008070993,0.000042049796,0.0017642583,0.000322133,0.00000691937],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017132654,0.00023540294,0.00059510296,0.000388097,0.00013133683,0.00013456735,0.00007785529,0.0000036739336,0.9346472,0.00050474046,0.04215756,0.01941118],"study_design_scores_gemma":[0.0029222523,0.0006032674,0.000034566958,0.00020175552,0.00003087996,0.000037822803,0.0008319954,0.0016767798,0.9324113,0.000096845564,0.06087636,0.00027615618],"about_ca_topic_score_codex":0.0000826076,"about_ca_topic_score_gemma":0.0005445202,"teacher_disagreement_score":0.019135023,"about_ca_system_score_codex":0.000026197777,"about_ca_system_score_gemma":0.00032743014,"threshold_uncertainty_score":0.51393175},"labels":[],"label_agreement":null},{"id":"W3181498676","doi":"10.1093/database/baab040","title":"Standardization of assay representation in the Ontology for Biomedical Investigations","year":2021,"lang":"en","type":"review","venue":"Database","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"National Institute of Allergy and Infectious Diseases; National Human Genome Research Institute; Bill and Melinda Gates Foundation; National Institutes of Health; National Science Foundation","keywords":"Standardization; Ontology; Computer science; Process (computing); Open Biomedical Ontologies; Software engineering; Representation (politics); Hierarchy; Process ontology; Information retrieval; Ontology Inference Layer; OWL-S; Term (time); World Wide Web; Semantic Web; Suggested Upper Merged Ontology; Programming language; Semantic Web Stack","score_opus":0.11938547991577698,"score_gpt":0.4300302172784989,"score_spread":0.3106447373627219,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3181498676","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000009433865,0.9184007,0.07866023,0.00018311755,0.0001497541,0.0003847769,0.002149114,0.0000047106796,0.000058157217],"genre_scores_gemma":[0.000020838806,0.9458528,0.008409889,0.00008753524,0.00015710991,0.00020071573,0.045221552,0.000012159915,0.000037367576],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985679,0.00043574526,0.0004135294,0.0003038761,0.00014553139,0.00013343524],"domain_scores_gemma":[0.9989564,0.0002890414,0.00019349117,0.00046227683,0.00006388702,0.000034928773],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00076861883,0.00012801225,0.00047070105,0.00007933599,0.000035042656,0.000009859468,0.00025082825,0.00029051158,0.000010443223],"category_scores_gemma":[0.002906001,0.000086467175,0.00015001248,0.00027193545,0.00023703462,0.00000191664,0.000083169085,0.000121930716,9.218752e-7],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009504584,0.00012418073,0.000024384133,0.0027448477,0.000098256074,0.0000089372525,0.0000684545,0.0000013983295,0.00015381571,0.0008545421,0.048835266,0.94707644],"study_design_scores_gemma":[0.00018271257,0.00007452468,0.0000030584167,0.00088706496,0.00012830993,0.000018796842,0.00009090492,0.000008310556,0.00007283802,0.000039213428,0.9984065,0.00008773279],"about_ca_topic_score_codex":0.00002063958,"about_ca_topic_score_gemma":0.00007595328,"teacher_disagreement_score":0.94957125,"about_ca_system_score_codex":0.000011472778,"about_ca_system_score_gemma":0.0003712887,"threshold_uncertainty_score":0.3526029},"labels":[],"label_agreement":null},{"id":"W3190629400","doi":"10.1093/database/baab051","title":"OUP accepted manuscript","year":2021,"lang":"en","type":"article","venue":"Database","topic":"Banana Cultivation and Research","field":"Agricultural and Biological Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Computer science; Interoperability; Metadata; Schema (genetic algorithms); World Wide Web; Open source; Database; Software; Information retrieval","score_opus":0.06820757546597621,"score_gpt":0.27493018157125854,"score_spread":0.2067226061052823,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3190629400","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97972447,0.00019545504,0.000013343956,0.0070913085,0.00014326506,0.00007498359,0.0004953086,0.000066359724,0.012195537],"genre_scores_gemma":[0.97986704,0.0001242802,0.00043344835,0.001717179,0.0003077441,0.000011269604,0.0052404623,6.7418875e-7,0.0122979],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994431,0.00004524049,0.00006860676,0.00015850103,0.00014266142,0.00014188372],"domain_scores_gemma":[0.9997491,0.00003973971,0.000012505125,0.00005737251,0.00006541247,0.00007587131],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000087279615,0.000044149972,0.00005022699,0.0000039370225,0.000106957756,0.000044322118,0.00011345025,0.000025503821,0.013300976],"category_scores_gemma":[0.0000830865,0.000014408567,0.000029215998,0.00027930617,0.000020375312,0.000094917734,0.00009943982,0.000073752155,0.00041322602],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005046913,0.000070747396,0.001301486,0.000003188969,0.0000045767533,0.00004897035,0.000009535955,1.15831384e-7,0.792047,0.00060132926,0.06416957,0.1417384],"study_design_scores_gemma":[0.0001117212,0.00001628274,0.12948018,0.000008645872,0.0000024656179,0.000007901754,0.00025524356,0.000041817755,0.057534978,0.00002868895,0.8124153,0.0000967549],"about_ca_topic_score_codex":0.00010970108,"about_ca_topic_score_gemma":0.0003078686,"teacher_disagreement_score":0.7482457,"about_ca_system_score_codex":0.000006082728,"about_ca_system_score_gemma":0.0000071682844,"threshold_uncertainty_score":0.987601},"labels":[],"label_agreement":null},{"id":"W3203751410","doi":"10.1093/database/baab062","title":"Classifying domain-specific text documents containing ambiguous keywords","year":2021,"lang":"en","type":"article","venue":"Database","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development","keywords":"Computer science; Set (abstract data type); Domain (mathematical analysis); Information retrieval; Artificial intelligence; Naive Bayes classifier; Overfitting; Identifier; Machine learning; Support vector machine; Ambiguity; Data mining; Artificial neural network","score_opus":0.027044701699820522,"score_gpt":0.290375614861075,"score_spread":0.26333091316125445,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3203751410","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95916,0.008451284,0.023613235,0.0007899738,0.0008023744,0.000113832786,0.00032575757,0.000079193596,0.006664358],"genre_scores_gemma":[0.95517635,0.0013202607,0.03509782,0.0016207277,0.00064962654,0.00003193194,0.0038893262,0.000041776813,0.002172184],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987103,0.000085253545,0.00020937272,0.0004745297,0.00017915762,0.000341434],"domain_scores_gemma":[0.9991483,0.000020313317,0.00006026316,0.00057463814,0.000061780775,0.00013467434],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021286999,0.0001571609,0.00016552105,0.000030150406,0.00013428208,0.000054195494,0.00020313975,0.00013937878,0.00017716619],"category_scores_gemma":[0.00010854963,0.00014820516,0.00007361401,0.00012469788,0.00013926529,0.000004884457,0.00031939827,0.00015334296,0.00007622842],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018540477,0.00018714674,0.0035335568,0.000044638105,0.00012556287,0.00056977256,0.00014228502,0.00000223147,0.7762683,0.001037699,0.07155318,0.14635023],"study_design_scores_gemma":[0.00080682174,0.00011056994,0.0014208661,0.000042264535,0.000009397978,0.00007289772,0.0007003581,0.0000049229848,0.05204681,0.000069774534,0.9444986,0.00021672278],"about_ca_topic_score_codex":0.000030188932,"about_ca_topic_score_gemma":0.000034580153,"teacher_disagreement_score":0.8729454,"about_ca_system_score_codex":0.000017288152,"about_ca_system_score_gemma":0.00009049035,"threshold_uncertainty_score":0.6043631},"labels":[],"label_agreement":null},{"id":"W4210447837","doi":"10.1093/database/baac001","title":"Authors’ attitude toward adopting a new workflow to improve the computability of phenotype publications","year":2022,"lang":"en","type":"article","venue":"Database","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Agriculture and Agri-Food Canada; University of Ottawa; University of Manitoba","funders":"","keywords":"Workflow; Ambiguity; Computer science; World Wide Web; Knowledge management; Database","score_opus":0.04305262788612411,"score_gpt":0.30935208021017413,"score_spread":0.26629945232405,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210447837","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79157656,0.0020749085,0.17449097,0.02597365,0.0012727586,0.0009748632,0.002689219,0.00013157517,0.0008154615],"genre_scores_gemma":[0.9523068,0.000008638372,0.045273233,0.0008661919,0.00020213748,0.000060974504,0.00081844133,0.000010779571,0.00045280147],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991658,0.00008331213,0.00017088518,0.00026642997,0.00014968522,0.00016389559],"domain_scores_gemma":[0.99917495,0.000042510725,0.00006401416,0.0005751576,0.000041972326,0.00010139209],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046204287,0.00007633589,0.00009498003,0.000024466439,0.00014412691,0.0000135239015,0.0004186668,0.00003518118,0.00010335033],"category_scores_gemma":[0.00056285853,0.000058721664,0.00004859119,0.0002181539,0.00008054123,0.000002082527,0.0007720683,0.00013696529,0.0000053602353],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027304006,0.0005064808,0.0076157735,0.00007388801,0.00014941797,0.0000028756308,0.0011448796,0.00051284506,0.20419559,0.001445867,0.24407679,0.5400026],"study_design_scores_gemma":[0.00037291774,0.0003458311,0.007505092,0.000008366038,0.000026529284,0.0000053009926,0.00046383022,0.0002979759,0.0063244035,0.00013784062,0.9843319,0.00018000293],"about_ca_topic_score_codex":0.0001470324,"about_ca_topic_score_gemma":0.00003457717,"teacher_disagreement_score":0.7402551,"about_ca_system_score_codex":0.000012722294,"about_ca_system_score_gemma":0.00014048588,"threshold_uncertainty_score":0.23945999},"labels":[],"label_agreement":null},{"id":"W4212800016","doi":"10.1093/database/baac009","title":"Evaluating the predictive accuracy of curated biological pathways in a public knowledgebase","year":2022,"lang":"en","type":"article","venue":"Database","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; University of New Brunswick; University of Toronto; Ontario Institute for Cancer Research","funders":"National Human Genome Research Institute","keywords":"Biological pathway; Downregulation and upregulation; Computer science; Signal transduction; Computational biology; Biology; Genetics; Gene; Gene expression","score_opus":0.09095347415119943,"score_gpt":0.32690795826394903,"score_spread":0.2359544841127496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4212800016","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99549186,0.0007893693,0.0011901723,0.00014842575,0.00012700885,0.00033372172,0.0012806975,0.0000071836444,0.0006315535],"genre_scores_gemma":[0.99655086,0.00006641575,0.0003726227,0.00022102789,0.000065177956,0.00010749494,0.0025885673,0.0000069671532,0.000020872734],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99900174,0.00021846982,0.0002771277,0.0001874512,0.000118512224,0.00019667603],"domain_scores_gemma":[0.99927753,0.000073836054,0.00014516815,0.00040671945,0.00005593873,0.000040793162],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010028832,0.000093377035,0.00010415763,0.000036786263,0.00013410763,0.000011284254,0.00032573083,0.000041193485,0.00010710805],"category_scores_gemma":[0.00043358337,0.00006665084,0.000046533452,0.0002044722,0.00007917697,0.000005948372,0.0006959287,0.00019627524,0.0000035806092],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001463414,0.0012050417,0.0084371,0.00009713828,0.00021055333,0.000023188286,0.0016776879,0.00521908,0.86848795,0.0057440205,0.025269462,0.082165346],"study_design_scores_gemma":[0.0123926345,0.011432168,0.014420524,0.00014125824,0.00013516223,0.00021479152,0.0128408605,0.6165348,0.06402993,0.003593274,0.26214817,0.002116378],"about_ca_topic_score_codex":0.000017254228,"about_ca_topic_score_gemma":0.000019752104,"teacher_disagreement_score":0.804458,"about_ca_system_score_codex":0.000018001132,"about_ca_system_score_gemma":0.00015520715,"threshold_uncertainty_score":0.27179426},"labels":[],"label_agreement":null},{"id":"W4224325974","doi":"10.1093/database/baac069","title":"Multi-label classification for biomedical literature: an overview of the BioCreative VII LitCovid Track for COVID-19 literature topic annotations","year":2022,"lang":"en","type":"article","venue":"Database","topic":"Topic Modeling","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"U.S. National Library of Medicine; Medical Research Council; National Institutes of Health","keywords":"Computer science; Coronavirus disease 2019 (COVID-19); Annotation; Named-entity recognition; Scientific literature; Information retrieval; Data science; Artificial intelligence; Natural language processing; World Wide Web; Task (project management); Medicine; Infectious disease (medical specialty)","score_opus":0.2046024088696558,"score_gpt":0.4089928303778776,"score_spread":0.2043904215082218,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224325974","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003593328,0.002214431,0.9734788,0.007575963,0.0005042857,0.0011931912,0.011364441,0.00006995558,0.0000055976257],"genre_scores_gemma":[0.08294737,0.000137929,0.8932693,0.00823726,0.00031961472,0.0018216162,0.012775332,0.00003178602,0.00045978138],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984652,0.00020963505,0.00032236002,0.0005128819,0.00028779218,0.00020212465],"domain_scores_gemma":[0.9981571,0.00031825402,0.00017920406,0.0010384575,0.0001649724,0.00014201482],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058937626,0.00013269215,0.00015779943,0.000121245714,0.0004620696,0.00011778362,0.0010319767,0.00005491254,0.00001312205],"category_scores_gemma":[0.0005225941,0.0001031118,0.00009429118,0.00081858126,0.00005778573,0.00056302076,0.0002874008,0.0001922685,5.8110163e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021045099,0.0028753928,0.00047443793,0.0023286922,0.00012844181,0.000017749413,0.04446766,0.0004650312,0.03714182,0.797538,0.026107,0.08824534],"study_design_scores_gemma":[0.0020211227,0.00020713048,0.00043210425,0.00009573454,0.000031063806,0.000016612667,0.00027314137,0.8489129,0.00043542485,0.0028650374,0.14449675,0.00021295689],"about_ca_topic_score_codex":0.000018956935,"about_ca_topic_score_gemma":0.000015106885,"teacher_disagreement_score":0.84844786,"about_ca_system_score_codex":0.00009847521,"about_ca_system_score_gemma":0.00029358035,"threshold_uncertainty_score":0.42047772},"labels":[],"label_agreement":null},{"id":"W4225573257","doi":"10.1093/database/baac034","title":"GrainGenes: a data-rich repository for small grains genetics and genomics","year":2022,"lang":"en","type":"article","venue":"Database","topic":"Wheat and Barley Genetics and Pathology","field":"Agricultural and Biological Sciences","cited_by":96,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Agriculture and Agri-Food Canada","funders":"Agricultural Research Service","keywords":"Genome browser; Genome; Triticeae; Genomics; Biology; Interoperability; Metadata; World Wide Web; Genetics; Database; Computational biology; Computer science; Gene","score_opus":0.06471702717790244,"score_gpt":0.24476727253286695,"score_spread":0.1800502453549645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225573257","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9898322,0.0020489222,0.00005794088,0.00039537865,0.00022649796,0.00023694833,0.007083368,0.000021069218,0.000097630895],"genre_scores_gemma":[0.97123855,0.00069874857,0.00566243,0.001267742,0.0008815651,0.00014285631,0.019518012,0.0000041287126,0.00058593927],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991627,0.000059139653,0.00013875545,0.0003660034,0.00007402974,0.00019941642],"domain_scores_gemma":[0.999584,0.00010129901,0.000046603975,0.0001745153,0.000021346357,0.0000721954],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002986402,0.000091014954,0.00010426556,0.000009093608,0.0005882284,0.000035813566,0.00037385087,0.000027307004,0.000041235886],"category_scores_gemma":[0.000016023243,0.000042928776,0.000024688601,0.00009820853,0.000040666997,0.000025760186,0.00067956775,0.000073391806,0.0000012657738],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006433915,0.0001410469,0.0047589336,0.000020213116,0.000021518721,0.000034590303,0.00017833128,0.00001362074,0.9239274,0.00037603156,0.0110126175,0.059451357],"study_design_scores_gemma":[0.00032912492,0.0005845541,0.0074785943,0.0000028597267,0.000057975878,0.00012840619,0.0006565065,0.0017770238,0.005096198,0.0004120592,0.9831524,0.00032430183],"about_ca_topic_score_codex":0.00008064782,"about_ca_topic_score_gemma":0.0003588474,"teacher_disagreement_score":0.9721398,"about_ca_system_score_codex":0.000008987208,"about_ca_system_score_gemma":0.000012912012,"threshold_uncertainty_score":0.45242366},"labels":[],"label_agreement":null},{"id":"W4297260078","doi":"10.1093/database/baac088","title":"ChemBioPort: an online portal to navigate the structure, function and chemical inhibition of the human proteome","year":2022,"lang":"en","type":"article","venue":"Database","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; University of New Brunswick; Structural Genomics Consortium; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs; Québec Consortium for Drug Discovery","keywords":"Druggability; Computer science; Function (biology); Domain (mathematical analysis); Chemical database; Human proteome project; Ontology; Architecture; Proteome; Computational biology; Information retrieval; Bioinformatics; Chemistry; Biology; Proteomics; Biochemistry","score_opus":0.029578339846526556,"score_gpt":0.29806326734176203,"score_spread":0.26848492749523545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297260078","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9810626,0.000010064875,0.016902372,0.00064960064,0.00014619659,0.00031195668,0.00087753765,0.000024190838,0.000015498576],"genre_scores_gemma":[0.9899245,1.3790294e-7,0.008771592,0.00048906,0.000059523085,0.000018056564,0.0007214398,0.0000057728453,0.000009932024],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989328,0.00014254605,0.00017544249,0.00027567675,0.00036996038,0.00010362224],"domain_scores_gemma":[0.99924326,0.000035613117,0.0000991261,0.00053519546,0.00003701529,0.00004982028],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003787373,0.00008033316,0.000076871525,0.000034668956,0.00022994688,0.000036236517,0.00040736,0.000011869393,0.0000349238],"category_scores_gemma":[0.00003471288,0.00005456029,0.000026799371,0.00037401044,0.000054910102,0.00030133824,0.0010828325,0.00018922136,4.1878687e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003469303,0.00023981908,0.0006175912,0.000027943111,0.00001591279,0.00000776524,0.0005941318,0.0034236975,0.9317891,0.056521837,0.000564265,0.0061632516],"study_design_scores_gemma":[0.0018858396,0.0006048438,0.22824965,0.00008463285,0.00007966905,0.000408387,0.0006332118,0.09482647,0.592548,0.07485333,0.00495763,0.00086832716],"about_ca_topic_score_codex":0.000057148354,"about_ca_topic_score_gemma":0.000015940168,"teacher_disagreement_score":0.3392411,"about_ca_system_score_codex":0.000022412778,"about_ca_system_score_gemma":0.000053162017,"threshold_uncertainty_score":0.2224904},"labels":[],"label_agreement":null},{"id":"W4302275377","doi":"10.1093/database/baac084","title":"Overview of the COVID-19 text mining tool interactive demonstration track in BioCreative VII","year":2022,"lang":"en","type":"article","venue":"Database","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Institute for Research in Immunology and Cancer","funders":"U.S. National Library of Medicine; National Institute of General Medical Sciences; National Human Genome Research Institute; Canadian Institutes of Health Research; National Institutes of Health","keywords":"Coronavirus disease 2019 (COVID-19); Computer science; Track (disk drive); Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); 2019-20 coronavirus outbreak; Information retrieval; Natural language processing; Artificial intelligence; World Wide Web; Virology; Medicine","score_opus":0.05752538837657176,"score_gpt":0.34534285423608096,"score_spread":0.2878174658595092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4302275377","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.995656,0.00095358095,0.0008086525,0.0008834228,0.00012355835,0.0001662616,0.0009694213,0.0000077413615,0.00043132406],"genre_scores_gemma":[0.9975205,0.00007641147,0.00080991123,0.0008996683,0.000025172865,0.000042546577,0.0005184783,0.000005355257,0.00010193853],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991835,0.00020759067,0.00017253467,0.00020714966,0.00011954646,0.000109724395],"domain_scores_gemma":[0.9995074,0.00007866722,0.00010105717,0.00026257464,0.000015260644,0.000034996472],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029370442,0.000075739816,0.00010016794,0.000033921395,0.00008894307,0.0000050376852,0.00020550206,0.000038197737,0.0001268669],"category_scores_gemma":[0.00068621855,0.000058236474,0.000047968522,0.00016989642,0.0001292342,0.00000391997,0.00029560225,0.0001174991,0.0000011933686],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013639708,0.0010531157,0.080226116,0.0002935255,0.00021114385,0.000052880587,0.0044540158,0.00033128867,0.75273633,0.0010487011,0.070537634,0.08769129],"study_design_scores_gemma":[0.004209052,0.0013176057,0.047220875,0.00016344819,0.00009473473,0.00018331347,0.019864237,0.0010631859,0.23457359,0.00025407827,0.69027233,0.0007835434],"about_ca_topic_score_codex":0.000120979195,"about_ca_topic_score_gemma":0.00017643358,"teacher_disagreement_score":0.6197347,"about_ca_system_score_codex":0.000031874624,"about_ca_system_score_gemma":0.00015885643,"threshold_uncertainty_score":0.23748145},"labels":[],"label_agreement":null},{"id":"W4303685210","doi":"10.1093/database/baac086","title":"HSDatabase—a database of highly similar duplicate genes from plants, animals, and algae","year":2022,"lang":"en","type":"article","venue":"Database","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; Dalhousie University","funders":"","keywords":"Algae; Gene; Database; Biology; Computational biology; Computer science; Botany; Genetics","score_opus":0.016419549707939383,"score_gpt":0.23257291969946828,"score_spread":0.2161533699915289,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4303685210","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91392934,0.02218093,0.00019566425,0.00016292192,0.00012916801,0.00018185719,0.063131094,0.0000055237556,0.00008349678],"genre_scores_gemma":[0.973786,0.006242081,0.0035407075,0.0004336769,0.00016496379,0.00006464803,0.01568004,0.000033282235,0.000054578843],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99866885,0.000078238394,0.0002650382,0.0005706556,0.00017305533,0.00024418224],"domain_scores_gemma":[0.9988772,0.000036553905,0.00012872736,0.00082279654,0.00003294654,0.00010173554],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021706185,0.0002006328,0.00022404545,0.00004873612,0.00020534768,0.000011155573,0.00031357518,0.00003476032,0.000088812456],"category_scores_gemma":[0.000032686432,0.00020767478,0.000051339404,0.00006871591,0.00010634692,0.0000021956187,0.0015440973,0.00009813955,0.000004366057],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019323021,0.00008599483,0.0042636152,0.000026439995,0.00011501129,0.000017900475,0.00003712732,0.000025186266,0.9821112,0.00013879129,0.01176837,0.0012171422],"study_design_scores_gemma":[0.0011855902,0.0002988667,0.008930026,0.000014037112,0.00008782442,0.000029442059,0.00038427836,0.00016817755,0.46656558,0.00006615779,0.5218265,0.00044353982],"about_ca_topic_score_codex":0.00049810414,"about_ca_topic_score_gemma":0.00007813341,"teacher_disagreement_score":0.5155456,"about_ca_system_score_codex":0.0000074309,"about_ca_system_score_gemma":0.00005203515,"threshold_uncertainty_score":0.8468731},"labels":[],"label_agreement":null},{"id":"W4304757261","doi":"10.1093/database/baac081","title":"KinMod database: a tool for investigating metabolic regulation","year":2022,"lang":"en","type":"article","venue":"Database","topic":"Microbial Metabolic Engineering and Bioproduction","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Ontology; Homogeneous; Data mining; Missing data; Metabolic network; Systems biology; Database; Computational biology; Machine learning; Biology; Mathematics","score_opus":0.015007313350069081,"score_gpt":0.24721977959840397,"score_spread":0.2322124662483349,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4304757261","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9582214,0.0015518214,0.034554828,0.0002854361,0.0007540534,0.0005250288,0.004013655,0.000054122636,0.000039648654],"genre_scores_gemma":[0.93203133,0.00008591933,0.0341644,0.00051455095,0.0014105279,0.00036430973,0.03038668,0.00004898642,0.0009933115],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99912566,0.00004987131,0.00016622926,0.0003623061,0.00011298663,0.00018292769],"domain_scores_gemma":[0.9993598,0.000004414282,0.000067083,0.00048499374,0.000040267423,0.000043449152],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044091095,0.000112364534,0.000101814374,0.00005147763,0.00021562046,0.00001548039,0.00014425776,0.000027409198,0.000055097138],"category_scores_gemma":[0.00023941211,0.00012098953,0.00005190905,0.0001430139,0.000023654753,0.000009038889,0.00020683269,0.00008570261,0.0000035051298],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031260188,0.000031490716,0.000071356284,0.000028094817,0.000019815256,3.379185e-7,0.000015480267,0.0006866942,0.9799047,0.0009115464,0.016341709,0.001957524],"study_design_scores_gemma":[0.00036604755,0.000048101178,0.00026176247,0.0000046139976,0.000027442216,0.000022016147,0.000021310098,0.00060841464,0.43891168,0.000024860361,0.5595461,0.00015765522],"about_ca_topic_score_codex":0.000028827264,"about_ca_topic_score_gemma":0.000004464384,"teacher_disagreement_score":0.54320437,"about_ca_system_score_codex":0.00000923997,"about_ca_system_score_gemma":0.000044963646,"threshold_uncertainty_score":0.49338096},"labels":[],"label_agreement":null},{"id":"W4313706978","doi":"10.1093/database/baac109","title":"Developing a disease-specific annotation protocol for <i>VHL</i> gene curation using Hypothes.is","year":2023,"lang":"en","type":"article","venue":"Database","topic":"Genomics and Rare Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sinai Health System; Princess Margaret Cancer Centre; Canada Research Chairs; Hospital for Sick Children; University Health Network; Toronto General Hospital; University of New Brunswick; University of Toronto; Ontario Institute for Cancer Research","funders":"National Human Genome Research Institute; VHL Alliance; Princess Margaret Cancer Foundation","keywords":"Annotation; Data curation; Protocol (science); Computer science; Disease; Computational biology; Biology; World Wide Web; Bioinformatics; Medicine; Pathology","score_opus":0.1263615011844818,"score_gpt":0.3555056672103924,"score_spread":0.2291441660259106,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313706978","genre_codex":"empirical","genre_gemma":"protocol","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8072715,0.00014555544,0.11043617,0.00053027883,0.00025336805,0.0735383,0.00769758,0.000091334565,0.00003589935],"genre_scores_gemma":[0.31747535,0.000392891,0.10731651,0.0047278274,0.004056628,0.46414685,0.100571886,0.00039654865,0.0009155206],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99924505,0.00001837299,0.0001550099,0.00031151102,0.000085918204,0.00018411445],"domain_scores_gemma":[0.9994762,0.000009783877,0.00006595717,0.0002777773,0.00009048713,0.00007977357],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009778961,0.000110569534,0.000067133966,0.000048700873,0.0001465836,0.000041064544,0.00009668976,0.000035811998,0.000008979312],"category_scores_gemma":[0.00004794904,0.00010904756,0.00005851558,0.00012028546,0.000019627543,0.000012240367,0.000071089074,0.000020188201,0.000018660483],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039199032,0.000060912455,0.0005947869,0.00018695767,0.000029845833,0.000016723714,0.00004819834,0.00029129972,0.9693438,0.00040366655,0.026398772,0.002233044],"study_design_scores_gemma":[0.0016987602,0.00007142802,0.0027661067,0.00007077942,0.000030204485,0.000008152388,0.00008671981,0.005528041,0.25424373,0.00053296244,0.7344726,0.0004905212],"about_ca_topic_score_codex":0.0000042118318,"about_ca_topic_score_gemma":0.0000029850053,"teacher_disagreement_score":0.71510005,"about_ca_system_score_codex":0.000017706929,"about_ca_system_score_gemma":0.00015916002,"threshold_uncertainty_score":0.44468305},"labels":[],"label_agreement":null},{"id":"W4319062633","doi":"10.1093/database/baac108","title":"Automatic Extraction of Medication Mentions from Tweets—Overview of the BioCreative VII Shared Task 3 Competition","year":2023,"lang":"en","type":"article","venue":"Database","topic":"Topic Modeling","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"U.S. National Library of Medicine","keywords":"Timeline; Computer science; Task (project management); Natural language processing; Artificial intelligence; Class (philosophy); Information retrieval; World Wide Web","score_opus":0.06896966406581621,"score_gpt":0.32966677997371774,"score_spread":0.2606971159079015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319062633","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2703361,0.00022241725,0.72472715,0.0017294154,0.00054369756,0.00035461338,0.0015784549,0.00017562341,0.00033251938],"genre_scores_gemma":[0.98020285,0.0000887091,0.018543402,0.000053504697,0.000030732197,0.000025119924,0.0010214868,0.0000045373354,0.000029629296],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990821,0.00010468851,0.00026056453,0.00018126468,0.00029268442,0.00007871854],"domain_scores_gemma":[0.9988688,0.0001454231,0.00022075912,0.00068165595,0.00005710122,0.000026218639],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002659544,0.00005754115,0.00010275259,0.000076046665,0.00006224982,0.000013565926,0.0004197155,0.000022497305,0.00013861181],"category_scores_gemma":[0.00009365621,0.000045675213,0.00004350899,0.00045882116,0.00003468279,0.00039792483,0.00021148016,0.000056867833,0.000040295767],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018076142,0.00092633016,0.005795345,0.0011383796,0.00035732167,0.000012598949,0.0109688835,0.0014395105,0.50332266,0.32406536,0.018462203,0.13349336],"study_design_scores_gemma":[0.00044173896,0.000020974621,0.089988664,0.0006755069,0.00005590725,0.000002161138,0.00020338738,0.88171947,0.020116312,0.004892936,0.0017577494,0.0001252014],"about_ca_topic_score_codex":0.00036188288,"about_ca_topic_score_gemma":0.00004437166,"teacher_disagreement_score":0.88027996,"about_ca_system_score_codex":0.000024876468,"about_ca_system_score_gemma":0.000047633468,"threshold_uncertainty_score":0.18625812},"labels":[],"label_agreement":null},{"id":"W4319825965","doi":"10.1093/database/baac112","title":"Coronavirus Immunotherapeutic Consortium Database","year":2023,"lang":"en","type":"article","venue":"Database","topic":"SARS-CoV-2 and COVID-19 Research","field":"Medicine","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Fast Grants; GHR Foundation; Mastercard Foundation; Wellcome Trust; National Institute of Allergy and Infectious Diseases; Bill and Melinda Gates Foundation","keywords":"Coronavirus disease 2019 (COVID-19); Coronavirus; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); 2019-20 coronavirus outbreak; Virology; Database; Computer science; World Wide Web; Library science; Medicine; Infectious disease (medical specialty); Outbreak; Pathology","score_opus":0.1494326824191115,"score_gpt":0.4207830660524239,"score_spread":0.2713503836333124,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319825965","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98897964,0.0015467225,0.00025012714,0.00076997397,0.00039946454,0.0007029409,0.0027755853,0.0005998186,0.003975705],"genre_scores_gemma":[0.7576165,0.0003569205,0.0011615768,0.2300368,0.0008965761,0.00038373456,0.00755767,0.00025550945,0.0017346999],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99806774,0.00006796928,0.00027907713,0.00045553967,0.0005594909,0.00057018537],"domain_scores_gemma":[0.9982809,0.00021923249,0.0000474198,0.0012801838,0.00008894304,0.00008331205],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005587994,0.00019388359,0.00027305668,0.00027798951,0.00012308022,0.000036811125,0.00026672607,0.00006514702,0.00026937504],"category_scores_gemma":[0.00024827552,0.00017172463,0.00009113553,0.00076525455,0.00017812046,0.00020219709,0.00027352085,0.00035803553,0.007064425],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00094136305,0.0003361912,0.03181704,0.000308091,0.00017132818,0.0023340029,0.00015358513,1.018308e-7,0.90713286,0.00090294593,0.03581255,0.020089917],"study_design_scores_gemma":[0.0024394037,0.00012655667,0.006437493,0.00011365971,0.00007505688,0.00010203856,0.0001658677,0.00071436696,0.12969965,0.000041514235,0.8598581,0.00022628892],"about_ca_topic_score_codex":0.00065685634,"about_ca_topic_score_gemma":0.00006249677,"teacher_disagreement_score":0.82404554,"about_ca_system_score_codex":0.00006939348,"about_ca_system_score_gemma":0.00033043567,"threshold_uncertainty_score":0.99370867},"labels":[],"label_agreement":null},{"id":"W4323519786","doi":"10.1093/database/baad005","title":"Chemical identification and indexing in full-text articles: an overview of the NLM-Chem track at BioCreative VII","year":2023,"lang":"en","type":"article","venue":"Database","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"H2020 Marie Skłodowska-Curie Actions; U.S. National Library of Medicine; Fundação para a Ciência e a Tecnologia; Natural Sciences and Engineering Research Council of Canada; European Commission; University of Oxford; Albaha University; National Institutes of Health; Nvidia","keywords":"Computer science; Search engine indexing; Named-entity recognition; Identification (biology); Information retrieval; Natural language processing; Task (project management); Normalization (sociology); Artificial intelligence","score_opus":0.06945455733307294,"score_gpt":0.3394277437636137,"score_spread":0.26997318643054075,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4323519786","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99853474,0.0008894466,0.000049863764,0.00023453594,0.000034641198,0.00007374916,0.00014685791,0.000011584428,0.000024594803],"genre_scores_gemma":[0.9987619,0.00039693105,0.00018978615,0.00006769646,0.000029222108,0.0000109892035,0.0004419832,0.0000062356494,0.000095276526],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993312,0.00005653215,0.00016466338,0.00022893958,0.00009246448,0.00012622944],"domain_scores_gemma":[0.9995424,0.000027078491,0.000057942503,0.00031020364,0.000018909906,0.00004347498],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002554114,0.000070087975,0.00008981664,0.000028448647,0.000036566256,0.000007656301,0.00013689674,0.00008027554,0.000012057052],"category_scores_gemma":[0.00023957863,0.00005120518,0.000025629484,0.00020676739,0.00019883917,0.000005062895,0.00022815229,0.00005995901,0.0000072076086],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000040222443,0.000039541177,0.0038691573,0.00003903819,0.000008182266,0.0000017456206,0.00020895292,9.648403e-7,0.9849169,0.000049562717,0.0008658094,0.009959907],"study_design_scores_gemma":[0.00038797842,0.000044557368,0.03432652,0.00006229308,0.000011382201,0.000008244596,0.00058145693,0.00034056124,0.9607348,0.00006597093,0.0033380014,0.00009826126],"about_ca_topic_score_codex":0.000030761494,"about_ca_topic_score_gemma":0.0000855906,"teacher_disagreement_score":0.030457363,"about_ca_system_score_codex":0.0000083625655,"about_ca_system_score_gemma":0.00001877503,"threshold_uncertainty_score":0.20880868},"labels":[],"label_agreement":null},{"id":"W4362515160","doi":"10.1093/database/baad016","title":"PurificationDB: database of purification conditions for proteins","year":2023,"lang":"en","type":"article","venue":"Database","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Canadian Institutes of Health Research","keywords":"UniProt; Computer science; Database; Function (biology); Column (typography); Information retrieval; Chemistry; Biology","score_opus":0.0200547654024743,"score_gpt":0.2963510366646304,"score_spread":0.2762962712621561,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362515160","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.71478075,0.00049156527,0.22150524,0.000953022,0.00034920723,0.0031430828,0.058006655,0.00013464064,0.00063580717],"genre_scores_gemma":[0.83560944,0.00019678968,0.015380119,0.00013370953,0.00022406153,0.0007596178,0.14701003,0.00003041174,0.0006558265],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992977,0.000021397846,0.00018227467,0.00026222446,0.00009020002,0.00014623653],"domain_scores_gemma":[0.9990662,0.000016025226,0.00009448518,0.00066056295,0.00011278098,0.00004999868],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018209078,0.000086731285,0.00008196699,0.00006858176,0.00008087827,0.000008695697,0.00017876357,0.00006153781,0.000015266503],"category_scores_gemma":[0.00022849132,0.00008719281,0.000049627426,0.00018013545,0.00006428952,0.000009358418,0.00007036333,0.000038624185,0.000021268852],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038478192,0.000033619963,0.00012286309,0.00008308314,0.000018507371,6.040453e-7,0.000011231931,0.000021760896,0.97859985,0.0071491757,0.013414899,0.0005059056],"study_design_scores_gemma":[0.00065234007,0.00011228276,0.0016053596,0.00002654439,0.000034347882,0.000005269739,0.00006540018,0.0011413674,0.9161212,0.0010938611,0.07894101,0.00020103813],"about_ca_topic_score_codex":0.000015169181,"about_ca_topic_score_gemma":0.000020619154,"teacher_disagreement_score":0.20612513,"about_ca_system_score_codex":0.000004777815,"about_ca_system_score_gemma":0.00007035856,"threshold_uncertainty_score":0.35556197},"labels":[],"label_agreement":null},{"id":"W4365135058","doi":"10.1093/database/baad021","title":"NbThermo: a new thermostability database for nanobodies","year":2023,"lang":"en","type":"article","venue":"Database","topic":"Monoclonal and Polyclonal Antibodies Research","field":"Medicine","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Thermostability; Database; Computer science; Melting temperature; Chemistry; Materials science; Biochemistry","score_opus":0.11078268293147928,"score_gpt":0.3938353857990054,"score_spread":0.28305270286752615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4365135058","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95713466,0.0012320847,0.0012780159,0.017848207,0.00046549263,0.0022060215,0.014756047,0.00054706715,0.0045324173],"genre_scores_gemma":[0.581168,0.0051574097,0.039989498,0.010718107,0.006423979,0.0011683716,0.112308145,0.00046687768,0.24259962],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983151,0.000044125918,0.00025379742,0.00044634257,0.00040008986,0.0005405203],"domain_scores_gemma":[0.998293,0.0004320943,0.00003977845,0.0007376609,0.00010806085,0.00038944793],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0005618333,0.00018866573,0.0002988701,0.00013636342,0.00017397653,0.000024186653,0.00019544481,0.000051236828,0.001020687],"category_scores_gemma":[0.00062484515,0.00014157542,0.00015256804,0.0003887292,0.00013387439,0.00014853031,0.00026800105,0.00018559996,0.0009461275],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0035023685,0.000335127,0.0113257645,0.0012290397,0.00020922293,0.00032697484,0.00045784796,0.0000017165225,0.17187294,0.0045453436,0.7631386,0.043055072],"study_design_scores_gemma":[0.003275937,0.00038956065,0.019281797,0.00022646792,0.000110822075,0.000067273955,0.00031629126,0.0017843882,0.024277523,0.0009932062,0.94888985,0.00038688397],"about_ca_topic_score_codex":0.00069107715,"about_ca_topic_score_gemma":0.000113186616,"teacher_disagreement_score":0.37596664,"about_ca_system_score_codex":0.00003200759,"about_ca_system_score_gemma":0.00028184446,"threshold_uncertainty_score":0.99989253},"labels":[],"label_agreement":null},{"id":"W4366492899","doi":"10.1093/database/baad023","title":"CARD*Shark: automated prioritization of literature curation for the Comprehensive Antibiotic Resistance Database","year":2023,"lang":"en","type":"article","venue":"Database","topic":"Antibiotic Resistance in Bacteria","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Canadian Institutes of Health Research; Cisco Systems Canada; Canada Foundation for Innovation; McMaster University; Cisco Systems","keywords":"Computer science; Database; Scope (computer science); Prioritization; Task (project management); Information retrieval; Triage; World Wide Web; Data science; Medicine; Business","score_opus":0.0199321420995732,"score_gpt":0.30137823407599623,"score_spread":0.281446091976423,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366492899","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95869786,0.0036641525,0.015251478,0.0004404353,0.0007607866,0.0014638443,0.019397527,0.00020370376,0.0001202246],"genre_scores_gemma":[0.9408724,0.0015779043,0.003934307,0.00013184757,0.00026249973,0.000016038979,0.052453462,0.000039313883,0.00071226485],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989528,0.00006704675,0.00026409348,0.0003527813,0.00015187913,0.0002113794],"domain_scores_gemma":[0.99865305,0.00009359902,0.00015882657,0.00076559396,0.0002898691,0.00003906285],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020754855,0.00014776636,0.0001505136,0.00005360513,0.00013977088,0.000046005112,0.000245018,0.000089359964,0.0000043993164],"category_scores_gemma":[0.0003372355,0.00011843907,0.00006552399,0.00037144645,0.0001053587,0.000026775517,0.00012055484,0.00006442078,0.000009014916],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025217576,0.000029939445,0.0007914124,0.00042938613,0.00006098395,0.00000726844,0.00005869184,0.000044737455,0.9023647,0.00069969136,0.095136724,0.0001242986],"study_design_scores_gemma":[0.0023112467,0.00019119852,0.050951954,0.0011463376,0.00019657752,0.000016955006,0.0005621844,0.012719471,0.73800355,0.000057394314,0.19313025,0.000712867],"about_ca_topic_score_codex":0.000007933821,"about_ca_topic_score_gemma":0.00004564277,"teacher_disagreement_score":0.16436113,"about_ca_system_score_codex":0.000010326238,"about_ca_system_score_gemma":0.00006701533,"threshold_uncertainty_score":0.4829805},"labels":[],"label_agreement":null},{"id":"W4376224614","doi":"10.1093/database/baad030","title":"PYK-SubstitutionOME: an integrated database containing allosteric coupling, ligand affinity and mutational, structural, pathological, bioinformatic and computational information about pyruvate kinase isozymes","year":2023,"lang":"en","type":"article","venue":"Database","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Basic Energy Sciences; National Center for Research Resources; National Institute of General Medical Sciences; National Institute on Aging; Natural Sciences and Engineering Research Council of Canada; Office of Science; National Institutes of Health; W. M. Keck Foundation; U.S. Department of Energy","keywords":"Allosteric regulation; Computational biology; Function (biology); Computer science; Genome; Database; Biology; Bioinformatics; Biochemistry; Genetics; Gene; Enzyme","score_opus":0.015264263407754641,"score_gpt":0.2664963883285539,"score_spread":0.2512321249207992,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4376224614","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98437095,0.00025828872,0.011385112,0.000056433215,0.000082603416,0.000283825,0.0034758411,0.00006647387,0.000020491794],"genre_scores_gemma":[0.9248691,0.0002995489,0.007387289,0.00041897895,0.00004441595,0.00002705357,0.06693803,0.0000095262185,0.0000060246066],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998977,0.000031647844,0.00034745163,0.0002686325,0.0001531646,0.00022208986],"domain_scores_gemma":[0.9992675,0.000038106587,0.00016344913,0.00025498267,0.00013144434,0.0001445051],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026922335,0.00020898214,0.00016644207,0.00012768303,0.00028235008,0.00016576712,0.00012661108,0.000104553124,0.000011795899],"category_scores_gemma":[0.0001936565,0.00018237413,0.000023459768,0.00019665956,0.00024131987,0.0001961524,0.0001926473,0.00013210296,0.000011597146],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005614952,0.00047387357,0.07383131,0.003858949,0.00111352,0.0007286208,0.010270289,0.12385134,0.63192576,0.043888375,0.011581091,0.09286189],"study_design_scores_gemma":[0.0059542214,0.0012484498,0.110303536,0.000253916,0.00015692304,0.00044091893,0.0031897223,0.8472894,0.013686848,0.001985206,0.013687713,0.0018031837],"about_ca_topic_score_codex":0.000043269312,"about_ca_topic_score_gemma":0.00003407568,"teacher_disagreement_score":0.723438,"about_ca_system_score_codex":0.000012664035,"about_ca_system_score_gemma":0.000092450806,"threshold_uncertainty_score":0.74370015},"labels":[],"label_agreement":null},{"id":"W4377862296","doi":"10.1093/database/baad038","title":"CIGAF—a database and interactive platform for insect-associated trichomycete fungi","year":2023,"lang":"en","type":"article","venue":"Database","topic":"Infectious Diseases and Mycology","field":"Veterinary","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto","keywords":"Metadata; Biology; Data collection; World Wide Web; Field (mathematics); Ecology; Database; Computer science","score_opus":0.08022745347238294,"score_gpt":0.3457302355413059,"score_spread":0.26550278206892297,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4377862296","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97338486,0.0001567668,0.00046343185,0.00007502966,0.00064549805,0.00072408956,0.02313531,0.0003893682,0.0010256591],"genre_scores_gemma":[0.9826598,0.00019565308,0.00013822693,0.00051131647,0.0001653791,0.00026992417,0.015539648,0.0000456265,0.00047440644],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99866813,0.00005677442,0.00024429357,0.0004386757,0.00012136944,0.00047073566],"domain_scores_gemma":[0.9985202,0.00070306,0.000117830634,0.00040079627,0.0000866224,0.00017146807],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003485986,0.00020252836,0.00025568955,0.00025647535,0.00027558845,0.000046865553,0.00013785696,0.00008548924,0.00030492013],"category_scores_gemma":[0.0006586472,0.00019797326,0.00008892173,0.00038124842,0.000055821463,0.0005172351,0.00032586156,0.00018216646,0.00031188564],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.01236658,0.0018030416,0.01955562,0.0010053202,0.0015447193,0.0035289545,0.0023925789,0.000010404294,0.08590551,0.009897885,0.81913817,0.0428512],"study_design_scores_gemma":[0.028782234,0.008175598,0.16071932,0.0005887804,0.0013816177,0.000927043,0.0034618,0.029628899,0.0034194891,0.002673071,0.7568393,0.0034028506],"about_ca_topic_score_codex":0.00031275474,"about_ca_topic_score_gemma":0.00015989042,"teacher_disagreement_score":0.1411637,"about_ca_system_score_codex":0.00008179695,"about_ca_system_score_gemma":0.000064485546,"threshold_uncertainty_score":0.80731153},"labels":[],"label_agreement":null},{"id":"W4385969415","doi":"10.1093/database/baad055","title":"Tissue-specific transcriptomes reveal potential mechanisms of microbiome heterogeneity in an ancient fish","year":2023,"lang":"en","type":"article","venue":"Database","topic":"Cancer-related molecular mechanisms research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada; Manitoba Hydro","keywords":"Biology; Transcriptome; Vertebrate; Cecum; Microbiome; De novo transcriptome assembly; Sturgeon; Model organism; Gene; Zoology; Evolutionary biology; Genetics; Fish <Actinopterygii>; Gene expression; Ecology; Fishery","score_opus":0.023523564965304996,"score_gpt":0.30154293962552803,"score_spread":0.27801937466022303,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385969415","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96041834,0.00031175435,0.03571287,0.00009623162,0.00029729525,0.00039050396,0.0027191304,0.000029859406,0.000024021894],"genre_scores_gemma":[0.9908984,0.0003106164,0.0012709503,0.00015601674,0.000078314144,0.000039553433,0.007071914,0.00004167244,0.00013257015],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9982972,0.00012925733,0.00028562773,0.00057027466,0.00027577346,0.00044187935],"domain_scores_gemma":[0.99899006,0.0000042698894,0.000055414734,0.00072837254,0.000081679325,0.00014020702],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004386285,0.0001680614,0.00018772291,0.00024113021,0.000049783517,0.000022296992,0.00036725847,0.0001512465,0.00006554029],"category_scores_gemma":[0.000020893112,0.0001858723,0.00008225797,0.00048930023,0.00007078233,0.000011713351,0.0002077555,0.0001394093,0.000029815219],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015195184,0.000115937015,0.000008201648,0.000042835745,0.000018626948,0.000094345865,0.00002769517,0.00011683147,0.9929861,0.00006597459,0.004460803,0.0019107203],"study_design_scores_gemma":[0.00081686955,0.00029699414,0.000501443,0.00002164289,0.000007882017,0.000023567003,0.00004854803,0.000103603794,0.9857905,0.00003431059,0.012166177,0.0001884667],"about_ca_topic_score_codex":0.000048681904,"about_ca_topic_score_gemma":0.00021016154,"teacher_disagreement_score":0.034441918,"about_ca_system_score_codex":0.000029921961,"about_ca_system_score_gemma":0.0000791178,"threshold_uncertainty_score":0.75796527},"labels":[],"label_agreement":null},{"id":"W4387479018","doi":"10.1093/database/baad063","title":"ESOMIR: a curated database of biomarker genes and miRNAs associated with esophageal cancer","year":2023,"lang":"en","type":"article","venue":"Database","topic":"MicroRNA in disease regulation","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Shanghai Jiao Tong University; Science and Technology Commission of Shanghai Municipality; King Saud University; National Natural Science Foundation of China; National Science Foundation","keywords":"microRNA; Database; Gene; Computational biology; Biomarker; Bioinformatics; Biology; Computer science; Genetics","score_opus":0.021802113412344958,"score_gpt":0.28589287277100256,"score_spread":0.2640907593586576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387479018","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99125046,0.0021693578,0.00012805389,0.000052717358,0.00004868482,0.00018626759,0.006113337,0.000028513323,0.000022625518],"genre_scores_gemma":[0.9784879,0.00060791965,0.0002297726,0.000050974384,0.000044597342,0.000037912727,0.020293167,0.000027455446,0.00022031247],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991503,0.00006061647,0.00015721066,0.00031559,0.00012906859,0.00018726029],"domain_scores_gemma":[0.9993179,0.000018494115,0.00010675558,0.00037273823,0.000094462244,0.000089655325],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016182319,0.00013193897,0.00012408211,0.000069907066,0.000049289047,0.00001302734,0.000099065044,0.00006278377,0.00004777598],"category_scores_gemma":[0.00009648337,0.00011576131,0.00002688623,0.0002828528,0.000105727304,0.0000122655865,0.00015762149,0.000036939036,0.0000059157896],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017059139,0.000054045573,0.015712064,0.00006118438,0.00014574474,0.00002697754,0.000012029993,0.000018603187,0.97352827,0.000016822863,0.009469345,0.00078433537],"study_design_scores_gemma":[0.0025093001,0.00011143381,0.14670935,0.00022422233,0.00017782312,0.000013228729,0.000044430544,0.0024065645,0.8387257,0.0000073577994,0.008658612,0.00041200742],"about_ca_topic_score_codex":0.00016407257,"about_ca_topic_score_gemma":0.00028443325,"teacher_disagreement_score":0.1348026,"about_ca_system_score_codex":0.00001101902,"about_ca_system_score_gemma":0.0000935382,"threshold_uncertainty_score":0.4720609},"labels":[],"label_agreement":null},{"id":"W4389579251","doi":"10.1093/database/baad088","title":"Genotype and phenotype data standardization, utilization and integration in the big data era for agricultural sciences","year":2023,"lang":"en","type":"review","venue":"Database","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada; Saskatchewan Research Council (Canada)","funders":"Réseau de cancérologie Rossy; U.S. Department of Agriculture; National Institute of Food and Agriculture; National Science Foundation","keywords":"Data science; Raw data; Context (archaeology); Standardization; Computer science; Metadata; Annotation; Data collection; Biology; World Wide Web; Bioinformatics","score_opus":0.298928971651219,"score_gpt":0.3947060009767093,"score_spread":0.09577702932549031,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389579251","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00020468335,0.97941715,0.0024995366,0.000055930854,0.00015802127,0.000698688,0.016940502,0.0000025561947,0.000022939039],"genre_scores_gemma":[0.00029138612,0.9294894,0.000776704,0.000032079457,0.0002813865,0.000035619178,0.069066584,0.000012491622,0.000014383135],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99886805,0.00008548394,0.00022989775,0.00059651077,0.000092254304,0.00012781945],"domain_scores_gemma":[0.99896246,0.00007776346,0.00011032312,0.0007807007,0.00004815573,0.000020573123],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007679857,0.00016635664,0.00024966872,0.000044761873,0.00017314947,0.000092546674,0.00062583876,0.000064751446,4.6817323e-7],"category_scores_gemma":[0.00037686268,0.00009853124,0.000014648302,0.00020268951,0.000107831926,0.0000053774033,0.0009297686,0.00006143079,7.773967e-7],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012949611,0.000026075852,0.000018683148,0.001510176,0.00007286683,6.7010495e-7,0.000063418316,0.0000017949521,0.00023505984,0.00059535675,0.009048839,0.9884141],"study_design_scores_gemma":[0.00014140518,0.00009591212,0.00011694784,0.00035856693,0.00018701445,0.000005267623,0.0001238941,0.00011667971,0.000005708103,0.000048072772,0.99863565,0.00016487774],"about_ca_topic_score_codex":0.000036541263,"about_ca_topic_score_gemma":0.000817704,"teacher_disagreement_score":0.98958683,"about_ca_system_score_codex":0.0000045459565,"about_ca_system_score_gemma":0.00012620211,"threshold_uncertainty_score":0.40179875},"labels":[],"label_agreement":null},{"id":"W4396685747","doi":"10.1093/database/baae031","title":"Pathway-based, reaction-specific annotation of disease variants for elucidation of molecular phenotypes","year":2024,"lang":"en","type":"article","venue":"Database","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; University of New Brunswick; University of Toronto; Ontario Institute for Cancer Research","funders":"National Institute of General Medical Sciences; National Institutes of Health; National Human Genome Research Institute; University of Toronto; European Commission; European Bioinformatics Institute","keywords":"Context (archaeology); Disease; Phenotype; Computational biology; Biology; Annotation; Genetics; Functional genomics; Clinical phenotype; Genomics; Gene; Genome; Medicine","score_opus":0.011007310499580822,"score_gpt":0.24289168076111675,"score_spread":0.23188437026153594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396685747","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2888513,0.0031299898,0.70200425,0.00014299258,0.0003796775,0.00045170906,0.0047711413,0.000015550317,0.00025336925],"genre_scores_gemma":[0.9838736,0.00010577068,0.0065112207,0.000055660807,0.00009704558,0.000023596263,0.009291767,0.000014108521,0.000027201993],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994428,0.00001405641,0.00021802542,0.00015817127,0.00007818514,0.00008875646],"domain_scores_gemma":[0.99949837,0.000017566463,0.00007881689,0.00028313397,0.00007895032,0.00004317791],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001605142,0.00007719355,0.00007828787,0.00004694701,0.000020426995,0.000010812235,0.00007372059,0.000044984827,0.000008805824],"category_scores_gemma":[0.000027315371,0.00007503539,0.00006607432,0.0000750891,0.000034289715,0.00000928958,0.000024306297,0.000031199408,0.0000032739872],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024296173,0.000050851402,0.000017781424,0.0003235087,0.000034392084,0.0000012923047,0.00002006171,0.00044921506,0.9761828,0.005027253,0.0032648882,0.014384974],"study_design_scores_gemma":[0.0007693311,0.00023316366,0.00038779163,0.00017825229,0.00007214688,0.0000012590867,0.00004429522,0.021399297,0.8563266,0.0010284943,0.1193155,0.00024388116],"about_ca_topic_score_codex":0.0000057329316,"about_ca_topic_score_gemma":0.0000025328477,"teacher_disagreement_score":0.69549304,"about_ca_system_score_codex":0.000005894949,"about_ca_system_score_gemma":0.00010191971,"threshold_uncertainty_score":0.30598542},"labels":[],"label_agreement":null},{"id":"W4399484747","doi":"10.1093/database/baae014","title":"The Immunopeptidomics Ontology (ImPO)","year":2024,"lang":"en","type":"article","venue":"Database","topic":"vaccines and immunoinformatics approaches","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"Fundação para a Ciência e a Tecnologia; Fundacja na rzecz Nauki Polskiej","keywords":"Computer science; Ontology; Information retrieval; World Wide Web; Software engineering; Philosophy; Epistemology","score_opus":0.011308519225832094,"score_gpt":0.24988501513391972,"score_spread":0.23857649590808763,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399484747","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88880783,0.06862397,0.015882717,0.002962066,0.0029536113,0.0006850644,0.00083450467,0.00013464039,0.019115582],"genre_scores_gemma":[0.98117226,0.006846022,0.0018928148,0.00067223934,0.0005737082,0.000068078145,0.0033498653,0.00004875361,0.0053762444],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994437,0.000018915227,0.00015922611,0.00014159965,0.00005290175,0.00018362235],"domain_scores_gemma":[0.9994176,0.000021459156,0.000021504336,0.0004914935,0.000019359248,0.000028605302],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002301467,0.00009303572,0.0000604744,0.000016344851,0.00013281795,0.00010336125,0.00024020833,0.00005048134,0.000015287145],"category_scores_gemma":[0.000050203464,0.00005935239,0.00005686232,0.000055219425,0.000045988232,0.000006695579,0.00019625941,0.0000932443,0.00010403948],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002559701,0.00007543752,0.00022195913,0.00016770573,0.0004397307,0.000028060453,0.00024678066,0.000025809368,0.514424,0.05375262,0.34360814,0.08675377],"study_design_scores_gemma":[0.00015702561,0.000059186154,0.000079234975,0.000011582049,0.0000130606995,0.00007118391,0.00011112892,0.0014220538,0.017358385,0.00009762808,0.9805108,0.00010874039],"about_ca_topic_score_codex":0.000020163152,"about_ca_topic_score_gemma":0.000032272725,"teacher_disagreement_score":0.63690263,"about_ca_system_score_codex":0.0000063488023,"about_ca_system_score_gemma":0.000054946227,"threshold_uncertainty_score":0.24203204},"labels":[],"label_agreement":null},{"id":"W4401535430","doi":"10.1093/database/baae073","title":"Functional implications of glycans and their curation: insights from the workshop held at the 16th Annual International Biocuration Conference in Padua, Italy","year":2024,"lang":"en","type":"article","venue":"Database","topic":"Glycosylation and Glycoproteins Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; University of British Columbia","funders":"National Institute of General Medical Sciences; National Heart, Lung, and Blood Institute; National Institutes of Health; National Human Genome Research Institute; Biotechnology and Biological Sciences Research Council; Novo Nordisk Fonden","keywords":"Data curation; Glycan; Function (biology); Glycosylation; Computer science; Data science; World Wide Web; Computational biology; Biology; Biochemistry; Genetics; Glycoprotein","score_opus":0.029365272496693136,"score_gpt":0.29121867497272247,"score_spread":0.26185340247602934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401535430","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95960206,0.002590593,0.014506513,0.017926244,0.00022999349,0.00037039575,0.003908075,0.000011031305,0.00085511757],"genre_scores_gemma":[0.99193615,0.00028746674,0.000058787187,0.00019387354,0.0001675813,0.000059014048,0.006744834,0.0000060787015,0.00054622494],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993415,0.0000638354,0.00015900408,0.00023371607,0.00012338087,0.00007856189],"domain_scores_gemma":[0.9994261,0.000110782144,0.00003438955,0.00028858852,0.00011119764,0.000028916415],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011695032,0.00008021379,0.000051804793,0.00003803564,0.00009686432,0.000058805646,0.00015904444,0.00004902341,0.00019957866],"category_scores_gemma":[0.00009624092,0.000046333986,0.000027575126,0.00014285614,0.0001282775,0.000032233398,0.0001773208,0.000107168635,0.000014345107],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025617328,0.000110277244,0.0045455997,0.000018907434,0.00012967038,0.0000034934283,0.0015353725,0.00012646813,0.9144975,0.020356635,0.04157631,0.016843604],"study_design_scores_gemma":[0.0011772228,0.00013142313,0.10883661,0.00015205453,0.000025500325,0.00003725925,0.0037209298,0.007477401,0.1651136,0.0018683277,0.71108377,0.00037588418],"about_ca_topic_score_codex":0.00015939103,"about_ca_topic_score_gemma":0.0038419806,"teacher_disagreement_score":0.74938387,"about_ca_system_score_codex":0.000015915608,"about_ca_system_score_gemma":0.000105483516,"threshold_uncertainty_score":0.21852463},"labels":[],"label_agreement":null},{"id":"W4401978887","doi":"10.1093/database/baae085","title":"Autoinhibited Protein Database: a curated database of autoinhibitory domains and their autoinhibition mechanisms","year":2024,"lang":"en","type":"article","venue":"Database","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Research Foundation of Korea","keywords":"Allosteric regulation; Database; Drug discovery; Mechanism (biology); Computational biology; Computer science; Biology; Bioinformatics; Biochemistry; Enzyme","score_opus":0.018850469998935308,"score_gpt":0.2772149938642937,"score_spread":0.2583645238653584,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401978887","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045170117,0.0013787901,0.9450982,0.0007814354,0.00055528973,0.00083878386,0.005218485,0.0008112282,0.00014765015],"genre_scores_gemma":[0.52335536,0.00006792333,0.4691344,0.0003535254,0.00020243616,0.0001981775,0.00643455,0.00009657883,0.00015706233],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960824,0.00059571833,0.0007634807,0.0013416976,0.0006892196,0.00052743335],"domain_scores_gemma":[0.99712956,0.00066735473,0.0002078763,0.0015520585,0.00017300833,0.00027012752],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0019312953,0.00048710426,0.00044452614,0.0006624463,0.00020769084,0.0003437887,0.00074582914,0.00010262293,0.000071177376],"category_scores_gemma":[0.00022891755,0.00042992854,0.00013301698,0.0015928026,0.00021042662,0.0034183434,0.0015154775,0.00046629258,0.0000674405],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000373253,0.00022773391,0.0000016982129,0.00070788135,0.00007091173,0.00025871213,0.00039623067,0.00024192274,0.6694411,0.31103116,0.0026899637,0.014895356],"study_design_scores_gemma":[0.0006820169,0.00012656675,0.00005341002,0.0013709012,0.000030808802,0.00020275214,0.00006540324,0.7189325,0.25764158,0.017715039,0.0026248347,0.0005541729],"about_ca_topic_score_codex":0.0001404304,"about_ca_topic_score_gemma":0.000024861072,"teacher_disagreement_score":0.7186906,"about_ca_system_score_codex":0.00011264031,"about_ca_system_score_gemma":0.0005862023,"threshold_uncertainty_score":0.9998152},"labels":[],"label_agreement":null},{"id":"W4405227333","doi":"10.1093/database/baae116","title":"Probe my Pathway (PmP): a portal to explore the chemical coverage of the human Reactome","year":2024,"lang":"en","type":"article","venue":"Database","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; University of Toronto","funders":"Structural Genomics Consortium; Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Computer science; Information retrieval; World Wide Web; Data science","score_opus":0.019083017541008565,"score_gpt":0.2575803154624792,"score_spread":0.23849729792147067,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405227333","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9918422,0.0005739521,0.00234793,0.0006159165,0.0002936002,0.00042545245,0.000907823,0.00001570735,0.0029773954],"genre_scores_gemma":[0.9977035,0.00002998267,0.00020057826,0.0005882866,0.00024770797,0.000029548595,0.0008589661,0.000014975088,0.00032646276],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99932754,0.000017463892,0.00019922439,0.00017868941,0.00011551608,0.00016157662],"domain_scores_gemma":[0.99925184,0.000009824299,0.000041955253,0.00062048197,0.000021786767,0.000054103926],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018636983,0.00010682633,0.00008400577,0.000013616658,0.000056503162,0.000031987252,0.0003224091,0.00006373567,0.000031716132],"category_scores_gemma":[0.00002406306,0.000059777136,0.000088768196,0.00009685334,0.00006638549,0.0000047504805,0.0003786587,0.0001380239,0.00001584108],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019207833,0.00003190641,0.00006963126,0.000072217415,0.000052846226,0.000007580266,0.0003982723,0.0000097566635,0.9474742,0.002423662,0.045389827,0.0040509114],"study_design_scores_gemma":[0.00030869897,0.000100594974,0.00022582538,0.00013388762,0.00003807631,0.000051358802,0.00024141806,0.0002460154,0.4647215,0.00051451585,0.53315127,0.0002668072],"about_ca_topic_score_codex":0.000012828118,"about_ca_topic_score_gemma":0.000011568566,"teacher_disagreement_score":0.48776147,"about_ca_system_score_codex":0.0000060671,"about_ca_system_score_gemma":0.00006159816,"threshold_uncertainty_score":0.24376409},"labels":[],"label_agreement":null},{"id":"W4407006479","doi":"10.1093/database/baae097","title":"Helping authors produce FAIR taxonomic data: evaluation of an author-driven phenotype data production prototype","year":2025,"lang":"en","type":"article","venue":"Database","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Museum of Nature; Agriculture and Agri-Food Canada; Université de Montréal; Ministry of Natural Resources and Forestry; University of Manitoba; University of Ottawa","funders":"National Science Foundation","keywords":"Computer science; Ontology; Workflow; Character (mathematics); Vocabulary; World Wide Web; Information retrieval; Data science; Artificial intelligence; Database","score_opus":0.15365448967522466,"score_gpt":0.40095387990632747,"score_spread":0.2472993902311028,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407006479","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97535914,0.0017320188,0.012774525,0.0020327093,0.0017576927,0.0024158307,0.0034116304,0.000100303914,0.00041612686],"genre_scores_gemma":[0.93079364,0.000052317406,0.025776522,0.00005817165,0.0004781728,0.00010153384,0.042469636,0.000017604489,0.00025237413],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980034,0.00030779827,0.00028837033,0.0009615979,0.00024909482,0.00018971229],"domain_scores_gemma":[0.99639744,0.000014350829,0.00013888815,0.0032066163,0.00018515869,0.00005756842],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026415738,0.00013826444,0.00016104263,0.000075900665,0.00010387692,0.000020751473,0.0010090085,0.00013018321,0.000015252121],"category_scores_gemma":[0.0031903395,0.0001276721,0.000017029493,0.00019476943,0.0001544092,0.00003920555,0.0010466927,0.00015062504,0.0000065655527],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006444222,0.00065635453,0.0019222304,0.00041886445,0.00024383179,0.0000020373316,0.00009805061,0.00022648745,0.5014652,0.000171519,0.08665017,0.40750083],"study_design_scores_gemma":[0.002455461,0.001070446,0.010229233,0.00054022647,0.0008716529,0.000015515607,0.0009119744,0.08092292,0.27283096,0.00031055082,0.62886864,0.0009724309],"about_ca_topic_score_codex":0.00008657167,"about_ca_topic_score_gemma":0.00019540252,"teacher_disagreement_score":0.54221845,"about_ca_system_score_codex":0.000019452491,"about_ca_system_score_gemma":0.00044971408,"threshold_uncertainty_score":0.52063173},"labels":[],"label_agreement":null},{"id":"W4410539343","doi":"10.1093/database/baaf008","title":"An exploratory study combining Virtual Reality and Semantic Web for life science research using Graph2VR","year":2025,"lang":"en","type":"article","venue":"Database","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"H2020 Health","keywords":"Computer science; Virtual reality; World Wide Web; Exploratory research; Semantic Web; Information retrieval; Web of science; Social Semantic Web; Data science; Human–computer interaction; MEDLINE; Sociology","score_opus":0.14193607316905618,"score_gpt":0.44667886393519246,"score_spread":0.3047427907661363,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410539343","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9936637,0.00033568416,0.005327679,0.000099818455,0.00013476812,0.00025095697,0.00013811425,0.000018534172,0.000030700645],"genre_scores_gemma":[0.99847513,0.00003963279,0.0011264143,0.00013441457,0.000055097145,0.000029070412,0.000117414136,0.0000063092684,0.000016513975],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99869144,0.00017406415,0.00015152634,0.0004907963,0.00020069632,0.0002914646],"domain_scores_gemma":[0.9990909,0.00007374182,0.00002794562,0.000514685,0.00015075433,0.00014193758],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027436283,0.00008766724,0.00012093485,0.0001591964,0.0004462246,0.000061948595,0.00029582612,0.000061009636,0.0000012695588],"category_scores_gemma":[0.0012113973,0.000079014135,0.00001739856,0.0003594593,0.0008433961,0.00001205553,0.00038008747,0.00011814329,4.902697e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026370323,0.00059545424,0.014798664,0.000080936894,0.000051345876,0.000009188286,0.00052376604,0.000008087166,0.9700859,0.0008212267,0.004423598,0.008338109],"study_design_scores_gemma":[0.026049646,0.023238333,0.05696822,0.0011733653,0.00056833966,0.000046519544,0.2494966,0.094600715,0.42868108,0.0022325143,0.11334872,0.0035959363],"about_ca_topic_score_codex":0.000052304662,"about_ca_topic_score_gemma":0.00014243982,"teacher_disagreement_score":0.54140484,"about_ca_system_score_codex":0.000010136537,"about_ca_system_score_gemma":0.0004353026,"threshold_uncertainty_score":0.3432044},"labels":[],"label_agreement":null},{"id":"W4414493406","doi":"10.1093/database/baaf053","title":"p53motifDB: integration of genomic information and tumour suppressor p53 binding motifs","year":2025,"lang":"en","type":"article","venue":"Database","topic":"Cancer-related Molecular Pathways","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of General Medical Sciences; University at Albany; National Institutes of Health; Canadian Centre for Applied Research in Cancer Control","keywords":"Suppressor; Chromatin; Gene; Transcription factor; Genome; DNA; DNA binding site; Human genome; Promoter","score_opus":0.011861195864569407,"score_gpt":0.2605337110777503,"score_spread":0.2486725152131809,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414493406","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98204786,0.00025963294,0.0148129845,0.0003411165,0.00019032558,0.00035842304,0.0006208896,0.000038125097,0.0013306375],"genre_scores_gemma":[0.99506944,0.00009460593,0.0021748473,0.00019771264,0.000021702033,0.00001177334,0.0023137403,0.0000074628824,0.000108683314],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99938947,0.000020202515,0.00025875372,0.00011349747,0.00011266142,0.00010539628],"domain_scores_gemma":[0.99951726,0.000026102636,0.000086897,0.00025058273,0.00006994996,0.00004918728],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016572812,0.00008562443,0.00014908204,0.00026663477,0.000034876088,0.000015824615,0.00004860781,0.00005002419,0.000045904784],"category_scores_gemma":[0.00019889144,0.00008113281,0.000030331812,0.00016767305,0.000037622896,0.00026632438,0.00007294907,0.00013830113,0.000029184133],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011260878,0.000033336462,0.00049587555,0.00023909294,0.000036187088,0.0000061657556,0.00026175013,0.00001606548,0.98537225,0.0011573846,0.004359176,0.007910114],"study_design_scores_gemma":[0.0034061214,0.00014092575,0.021859206,0.00087363634,0.00023816862,0.00005063942,0.0005117857,0.008840218,0.9463106,0.000056676145,0.01753452,0.00017749456],"about_ca_topic_score_codex":0.00014422629,"about_ca_topic_score_gemma":0.000025209989,"teacher_disagreement_score":0.039061636,"about_ca_system_score_codex":0.000070596056,"about_ca_system_score_gemma":0.00010703462,"threshold_uncertainty_score":0.33084998},"labels":[],"label_agreement":null},{"id":"W4414533220","doi":"10.1093/database/baaf044","title":"GExplore 1.5: a comprehensive <i>Caenorhabditis elegans</i> database for the analysis of gene function with a new user-friendly web interface","year":2025,"lang":"en","type":"article","venue":"Database","topic":"Genetics, Aging, and Longevity in Model Organisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Emily Carr University of Art and Design; Simon Fraser University","funders":"","keywords":"Interface (matter); Proteome; User interface; Function (biology); Gene; Online database; The Internet; Web application; Graphical user interface","score_opus":0.013398199947390752,"score_gpt":0.2579205502741165,"score_spread":0.24452235032672573,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414533220","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31919706,0.0020271565,0.67425483,0.0003552502,0.00019163279,0.0004369512,0.0034909223,0.000016184207,0.000030016736],"genre_scores_gemma":[0.97492266,0.000666082,0.013066297,0.001148084,0.00017977704,0.00007789919,0.008970046,0.00003834827,0.0009307939],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987532,0.000045798915,0.00025770956,0.0005149732,0.00016650333,0.00026185045],"domain_scores_gemma":[0.99829507,0.00007030669,0.00014402559,0.0011667657,0.00023745051,0.00008637649],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014108591,0.00022968222,0.00029580254,0.00014143709,0.0001365863,0.000036207326,0.00038911452,0.0000766084,0.000034354754],"category_scores_gemma":[0.000061503,0.00017622198,0.00015112755,0.00047051668,0.00013358267,0.00001433781,0.00019779058,0.00010848709,0.0000029973412],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008368425,0.00014666926,0.0018592972,0.000120608405,0.0027814538,0.0000029055145,0.00016998831,0.004027871,0.9070206,0.00019930804,0.0817323,0.0011021046],"study_design_scores_gemma":[0.0022651097,0.00062154204,0.002797474,0.000061174294,0.004734122,0.000007614111,0.00089301076,0.0045357747,0.5843905,0.000013163663,0.39926568,0.00041479524],"about_ca_topic_score_codex":0.000343022,"about_ca_topic_score_gemma":0.0018949208,"teacher_disagreement_score":0.66118854,"about_ca_system_score_codex":0.000013430494,"about_ca_system_score_gemma":0.00021666764,"threshold_uncertainty_score":0.7186124},"labels":[],"label_agreement":null},{"id":"W4416865968","doi":"10.1093/database/baag027","title":"Large-scale Manual Curation and Harmonization of Metadata from Metagenomic and Cancer Genomic Repositories: Challenges and Solutions","year":2025,"lang":"en","type":"preprint","venue":"Database","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Population and Public Health","funders":"National Cancer Institute; National Institutes of Health","keywords":"Metadata; Data curation; Harmonization; Geospatial metadata; Ontology; Standardization; Metadata repository; Digital curation","score_opus":0.041418253084737164,"score_gpt":0.30703858055245375,"score_spread":0.2656203274677166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416865968","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6937303,0.26816744,0.021375021,0.0005721851,0.00040395558,0.00024013202,0.015451743,0.000017651137,0.000041610834],"genre_scores_gemma":[0.6332026,0.3275019,0.01824368,0.000121430705,0.00048015825,0.000102043545,0.019886296,0.000024251181,0.00043765438],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99900955,0.0000728953,0.00021400482,0.00051492604,0.000065302964,0.00012331744],"domain_scores_gemma":[0.9993313,0.00003116425,0.00013728596,0.00039929914,0.000046765737,0.000054190066],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018632066,0.00015258843,0.00023819556,0.000043610566,0.00007893661,0.000032706088,0.00010896121,0.00022479997,0.000003418806],"category_scores_gemma":[0.00009142914,0.00014531484,0.000023389828,0.000019951969,0.00015519845,0.000010839356,0.0011424178,0.00012469095,1.20502e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004049982,0.0002882854,0.0045223827,0.0023239683,0.0020369203,0.00001253386,0.0047948663,0.000045743913,0.8560136,0.00144913,0.0055267652,0.12258082],"study_design_scores_gemma":[0.0064973366,0.00067433785,0.11694472,0.002016754,0.005422632,0.00005145516,0.011953242,0.010707486,0.34256783,0.002906745,0.49700978,0.0032476727],"about_ca_topic_score_codex":0.0004065079,"about_ca_topic_score_gemma":0.0006693873,"teacher_disagreement_score":0.51344573,"about_ca_system_score_codex":0.000009124186,"about_ca_system_score_gemma":0.00008616962,"threshold_uncertainty_score":0.59257674},"labels":[],"label_agreement":null}]}