{"meta":{"query_hash":"d0588226f4e4","filters":{"venue":"GigaDB"},"cohort_total":13,"direct_labels_cover":0,"predictions_cover":13,"exported":13,"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/d0588226f4e4","api":"https://metacan.xera.ac/api/v1/cohort?venue=GigaDB"},"results":[{"id":"W6894188661","doi":"10.5524/100885","title":"Genomic data for the montane vole (Microtus montanus)","year":2021,"lang":"en","type":"dataset","venue":"GigaDB","topic":"","field":"","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"National Science Foundation of Sri Lanka","keywords":"Vole; Subspecies; Genome; Mitochondrial DNA; Montane ecology; Range (aeronautics)","score_opus":0.06062579880789461,"score_gpt":0.3029744775442766,"score_spread":0.242348678736382,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6894188661","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":[0.00004385567,0.014232784,0.000052015817,0.00039111168,0.0014226773,0.0018203206,0.98188573,0.00010867018,0.000042820906],"genre_scores_gemma":[0.000008232789,0.0006329626,0.0005001872,0.00048117113,0.0018181874,0.00036521698,0.99412346,0.000289488,0.0017810722],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9961668,0.0001372777,0.00065715023,0.0015606327,0.0005532004,0.00092492584],"domain_scores_gemma":[0.9881897,0.00053271785,0.0005101934,0.010414224,0.00017406826,0.00017908205],"candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009760622,0.0007289927,0.0008230132,0.00014666766,0.0003939409,0.00038392935,0.006133163,0.00047254778,0.0008718944],"category_scores_gemma":[0.00048482677,0.0005694355,0.00026027038,0.00033561527,0.00018545866,0.00020427289,0.0031643906,0.0008734639,0.008966586],"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":[0.000101856574,0.00009955772,0.000002775885,0.00015345111,0.00051308173,0.00018894002,0.000013313334,0.000019919735,0.0011029182,0.000004219981,0.99699515,0.0008047873],"study_design_scores_gemma":[0.0007604941,0.00003967149,0.00011316271,0.00009248994,0.0010202753,0.00015399142,0.000102730264,0.0002728289,0.00008457833,0.00002723168,0.99665654,0.000676025],"about_ca_topic_score_codex":0.0031027987,"about_ca_topic_score_gemma":0.009551177,"teacher_disagreement_score":0.013599821,"about_ca_system_score_codex":0.00038331238,"about_ca_system_score_gemma":0.0006365013,"threshold_uncertainty_score":0.9996757},"labels":[],"label_agreement":null},{"id":"W6894193726","doi":"10.5524/review.100316","title":"Peer review of \"A large and diverse collection of bovine genome sequences from the Canadian Cattle Genome Project\"","year":2015,"lang":"en","type":"article","venue":"GigaDB","topic":"Genetic and phenotypic traits in livestock","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Genome; Bovine genome; Genomics; Whole genome sequencing; DNA sequencing; Selection (genetic algorithm)","score_opus":0.030956077485476047,"score_gpt":0.26951458412013835,"score_spread":0.2385585066346623,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6894193726","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94012135,0.049445394,0.00023387015,0.0018765171,0.00020042431,0.0005644463,0.00090993807,0.000004675621,0.0066433647],"genre_scores_gemma":[0.99429446,0.0009925033,0.0019456445,0.000436332,0.00012730755,0.000011131735,0.00032262685,0.00000781386,0.001862185],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993942,0.000049073125,0.00013970879,0.00014343028,0.00015318721,0.00012045065],"domain_scores_gemma":[0.99938154,0.000008068055,0.00007608508,0.00019590293,0.0002639751,0.00007443451],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029392555,0.00007313535,0.0001177007,0.000017242079,0.000057258534,0.000005067467,0.00013555377,0.000063160434,0.000031888812],"category_scores_gemma":[0.00013495001,0.0000541746,0.000029272975,0.00008097611,0.0001035841,0.0000019352713,0.000050951487,0.00004443611,0.0000020737118],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008001578,0.0006931559,0.17700441,0.004457855,0.0018458233,0.000009290392,0.026112678,0.0003973007,0.2920646,0.011390299,0.47693977,0.008284635],"study_design_scores_gemma":[0.0008667955,0.0008918376,0.3911154,0.00020123596,0.00014147631,0.000013700163,0.0011405471,0.000004063937,0.0047126976,0.00081970484,0.59980726,0.00028527627],"about_ca_topic_score_codex":0.029110063,"about_ca_topic_score_gemma":0.037593007,"teacher_disagreement_score":0.28735194,"about_ca_system_score_codex":0.000014965679,"about_ca_system_score_gemma":0.00043700327,"threshold_uncertainty_score":0.9799684},"labels":[],"label_agreement":null},{"id":"W6894240833","doi":"10.5524/100514","title":"Supporting data for \"Imaging tissues and cells beyond the diffraction limit with structured illumination microscopy and Bayesian image reconstruction\"","year":2018,"lang":"en","type":"dataset","venue":"GigaDB","topic":"","field":"","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 Science Foundation of Sri Lanka; Grantová Agentura České Republiky; SCIEX; České Vysoké Učení Technické v Praze","keywords":"Microscopy; Software; Optical sectioning; Data set; Resolution (logic); Image (mathematics); Image processing; Set (abstract data type); Raw data; Data acquisition","score_opus":0.011794021952554338,"score_gpt":0.3006095792707699,"score_spread":0.28881555731821557,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6894240833","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":[0.005051296,0.000312839,0.00064815005,0.0002532852,0.0007066119,0.0013710259,0.99155045,0.00008615113,0.000020212632],"genre_scores_gemma":[0.00085047743,0.00015935425,0.019338056,0.00011021468,0.00085484685,0.00005808021,0.97839415,0.00015165449,0.00008317498],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971061,0.0001400905,0.00057016476,0.0012602825,0.0003568095,0.00056658644],"domain_scores_gemma":[0.99642247,0.00027110422,0.0012621058,0.0016354538,0.00027017182,0.00013871749],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009141932,0.0005764048,0.0005021922,0.00028057137,0.00079257315,0.00081299426,0.0006099686,0.0002351761,0.00011665553],"category_scores_gemma":[0.0002683706,0.00043590512,0.00003619332,0.00021569715,0.0010499554,0.001324433,0.00039707366,0.00047708637,0.000029772782],"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":[0.0001393734,0.000016739152,0.0001216136,0.00030186804,0.00009968257,0.000006771564,0.00013034316,2.0356705e-7,0.01871004,0.0000016959111,0.97241265,0.008058996],"study_design_scores_gemma":[0.0011028356,0.00013826965,0.0006432426,0.00024949483,0.0008744896,0.0006607967,0.0009313985,0.0012074264,0.008490562,0.00032542314,0.9846194,0.0007566884],"about_ca_topic_score_codex":0.00027933947,"about_ca_topic_score_gemma":0.0009694938,"teacher_disagreement_score":0.018689906,"about_ca_system_score_codex":0.00010211247,"about_ca_system_score_gemma":0.00012174736,"threshold_uncertainty_score":0.99980927},"labels":[],"label_agreement":null},{"id":"W6912987433","doi":"10.5524/100307","title":"Supporting materials for \"Kronos: a workflow assembler for genome analytics and informatics\"","year":2017,"lang":"en","type":"dataset","venue":"GigaDB","topic":"","field":"","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":"Natural Sciences and Engineering Research Council of Canada; Genome Canada","keywords":"Workflow; Modular design; Executable; Python (programming language); Workflow management system; Codebase; Scalability; Workflow engine; Reuse; Software","score_opus":0.04601337461542012,"score_gpt":0.36253411777563943,"score_spread":0.31652074316021933,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6912987433","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":[0.0011673449,0.000115852876,0.0005951888,0.00003218702,0.00068601535,0.0029089644,0.9943669,0.00008488004,0.000042709475],"genre_scores_gemma":[0.00019623806,0.000056935416,0.008190875,0.00013464391,0.0010287872,0.00072669063,0.98897535,0.0001994277,0.000491064],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99630183,0.000038915186,0.0015427895,0.00047870458,0.00046666717,0.0011710874],"domain_scores_gemma":[0.9942786,0.00033396747,0.0030049807,0.0016674582,0.00044836666,0.0002666341],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0029319134,0.00071536883,0.0013579847,0.000413491,0.0005400487,0.001304811,0.001018711,0.00065416255,0.00017657747],"category_scores_gemma":[0.0020911505,0.00069815136,0.00022863672,0.00008450345,0.00014068763,0.0005717648,0.00040538434,0.00024364321,0.0008326777],"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":[0.00015070336,0.00003445846,0.000009791707,0.0026256805,0.00033663042,0.000004199337,0.000083792984,0.000010681443,0.0005404643,0.000009018641,0.9958873,0.00030729274],"study_design_scores_gemma":[0.0013669139,0.00016040349,0.00011215123,0.00030706645,0.00088907394,0.000016758613,0.0000666223,0.00016871707,0.00027799798,0.0003664412,0.9954413,0.0008265356],"about_ca_topic_score_codex":0.000042101703,"about_ca_topic_score_gemma":0.00011327215,"teacher_disagreement_score":0.007595686,"about_ca_system_score_codex":0.00023468812,"about_ca_system_score_gemma":0.0003956863,"threshold_uncertainty_score":0.9999453},"labels":[],"label_agreement":null},{"id":"W6913037803","doi":"10.5524/100977","title":"Supporting data for \"Future-proofing and maximizing the utility of metadata: The PHA4GE SARS-CoV-2 contextual data specification package\"","year":2022,"lang":"en","type":"dataset","venue":"GigaDB","topic":"","field":"","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":"Biotechnology and Biological Sciences Research Council; Fundação para a Ciência e a Tecnologia; Genome Canada","keywords":"Interoperability; Consistency (knowledge bases); Contextual design; Standardization; Data integration; Data aggregator; Data quality; Data consistency; Alliance","score_opus":0.23914696435148422,"score_gpt":0.40076059941166364,"score_spread":0.16161363506017942,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6913037803","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":[0.00024668878,0.004063546,0.00066389394,0.00084000966,0.00093259074,0.0029924081,0.99014276,0.00007748609,0.000040637875],"genre_scores_gemma":[0.0016050716,0.0003658462,0.00062550657,0.00032893417,0.0011918079,0.00018809368,0.99549407,0.00016479655,0.000035866644],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99275315,0.0010291514,0.0017483628,0.0023327894,0.0012377308,0.0008988155],"domain_scores_gemma":[0.9764266,0.0019702932,0.0029430015,0.018386323,0.00019946088,0.000074302734],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.014527734,0.00075086096,0.0011186127,0.00018314051,0.0012087679,0.00065675925,0.011922088,0.00024771062,0.00083207677],"category_scores_gemma":[0.0039036975,0.00049788074,0.00015052129,0.0006210323,0.000737752,0.0020619037,0.0111095,0.0014434233,0.000037970225],"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":[0.00023102375,0.00011219896,0.000016633543,0.0003782817,0.0004897079,0.000008446376,0.00015737057,2.1309825e-7,0.0016182591,0.00012655732,0.991926,0.004935297],"study_design_scores_gemma":[0.0007444226,0.000042147833,0.00019916988,0.000053138454,0.0013434022,0.000048826852,0.002845003,0.00093397143,0.0009384977,0.00013806878,0.9922179,0.00049542746],"about_ca_topic_score_codex":0.0008590318,"about_ca_topic_score_gemma":0.0018388559,"teacher_disagreement_score":0.01632653,"about_ca_system_score_codex":0.000089518755,"about_ca_system_score_gemma":0.0004146601,"threshold_uncertainty_score":0.9997473},"labels":[],"label_agreement":null},{"id":"W6932006301","doi":"10.5524/100443","title":"Supporting data for \"The Long Noncoding RNA Landscape of Neuroendocrine Prostate Cancer and its Clinical Implications\"","year":2018,"lang":"en","type":"dataset","venue":"GigaDB","topic":"Hydrocarbon exploration and reservoir analysis","field":"Engineering","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":"Mitacs; Terry Fox Foundation","keywords":"Prostate cancer; FOXA1; Transcriptome; Long non-coding RNA; Context (archaeology); Transcription factor; HOTAIR; Gene","score_opus":0.060321479259479116,"score_gpt":0.37453589883204275,"score_spread":0.31421441957256363,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6932006301","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":[0.00096060516,0.002212917,0.00044998227,0.0008951778,0.00042464197,0.00044986335,0.9945461,0.000047802507,0.000012866131],"genre_scores_gemma":[0.018650882,0.011892792,0.00006556893,0.00009803632,0.0007328715,0.00013540965,0.96825945,0.000039396313,0.00012561714],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99858075,0.000026531123,0.0006676462,0.00033823808,0.00013598024,0.00025083576],"domain_scores_gemma":[0.9984026,0.00026051895,0.00023889338,0.0009169439,0.00009540198,0.00008562651],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039288434,0.00018269425,0.0003733944,0.00009241143,0.00010025334,0.000050435734,0.0006029756,0.000067613604,0.000050994047],"category_scores_gemma":[0.00026315424,0.00013606194,0.000082510756,0.0001959363,0.000049135404,0.00012937596,0.00023790389,0.00024509107,0.000006258663],"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":[0.000008781855,0.000010792934,0.00024175456,0.00033383397,0.00020200333,0.0000024545625,0.000009207525,0.0008356536,0.00002510075,0.0000019377717,0.9965092,0.001819279],"study_design_scores_gemma":[0.0003272851,0.000028001563,0.00023393745,0.000065223736,0.00039541975,0.0000055493915,0.000014550839,0.13241339,0.00010091686,0.000010002519,0.86622494,0.00018077136],"about_ca_topic_score_codex":0.000035988738,"about_ca_topic_score_gemma":0.00043136557,"teacher_disagreement_score":0.13157773,"about_ca_system_score_codex":0.000010111017,"about_ca_system_score_gemma":0.000055819564,"threshold_uncertainty_score":0.55484444},"labels":[],"label_agreement":null},{"id":"W6932050840","doi":"10.5524/102742","title":"Genome assembly of the sea turtle Caretta caretta","year":2025,"lang":"en","type":"dataset","venue":"GigaDB","topic":"Turtle Biology and Conservation","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Subtropics; Mediterranean sea; Temperate climate; Mediterranean climate; Indian ocean; Haplotype; Sequence assembly; Pacific ocean","score_opus":0.0077520250011816364,"score_gpt":0.21905016082157847,"score_spread":0.21129813582039683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6932050840","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":[0.016360475,0.0002377537,0.0000022459856,0.0005378024,0.00066064566,0.00022587218,0.97990406,0.000012373963,0.0020587728],"genre_scores_gemma":[0.012422537,0.000040815932,0.000012898278,0.0010688842,0.00009053514,0.000025478814,0.98320746,0.0000052773617,0.0031261246],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99907506,0.000105614105,0.00019476305,0.00024467058,0.0002020137,0.0001779006],"domain_scores_gemma":[0.9989769,0.00005781534,0.00015783736,0.00076669554,0.000010801686,0.00002995724],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013815866,0.00015945069,0.00018863872,0.000021978014,0.000101445345,0.000009376392,0.0008013761,0.00031494317,0.0008220664],"category_scores_gemma":[0.00006279991,0.00011317917,0.00012866575,0.00020000897,0.00020029338,0.000038942457,0.00047167533,0.0002818969,0.00007322663],"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":[0.0000050584636,0.000013411088,0.0025235824,0.000025220572,0.000023447687,0.0000013801972,0.000024551699,0.000013511317,0.0004699278,0.00000464681,0.996678,0.00021725839],"study_design_scores_gemma":[0.000067375375,0.00001590459,0.065610446,0.000021547065,0.000060262082,0.0000016591955,0.000011791147,0.0000014086202,0.0005083886,0.00002841996,0.93355674,0.00011608073],"about_ca_topic_score_codex":0.0013833409,"about_ca_topic_score_gemma":0.00074339303,"teacher_disagreement_score":0.06312129,"about_ca_system_score_codex":0.000107125146,"about_ca_system_score_gemma":0.00006310396,"threshold_uncertainty_score":0.90010506},"labels":[],"label_agreement":null},{"id":"W6950442593","doi":"10.5524/100649","title":"High-coverage genomes of all extant penguin taxa","year":2019,"lang":"en","type":"dataset","venue":"GigaDB","topic":"","field":"","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"European Research Council; Lundbeckfonden; Carlsbergfondet; Chinese Academy of Sciences; Villum Fonden","keywords":"Extant taxon; Taxon; Adaptation (eye); Southern Hemisphere; Genome; Resource (disambiguation); Tree of life (biology); Climate change","score_opus":0.02564693946101074,"score_gpt":0.27229406130604594,"score_spread":0.2466471218450352,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6950442593","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":[0.0013310739,0.0023011952,0.0000026209984,0.000033407552,0.0012500401,0.0007775776,0.99383515,0.00007771129,0.0003912429],"genre_scores_gemma":[0.0007725723,0.0009465586,0.00015913823,0.00020743873,0.0005318613,0.000039833092,0.9955793,0.00022493744,0.0015383376],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9963096,0.00019139677,0.00083929,0.0008903406,0.0010203989,0.00074900244],"domain_scores_gemma":[0.99540055,0.00016981899,0.0012297264,0.0028585142,0.00015873612,0.00018264013],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0005712056,0.00073960715,0.0013127954,0.00048955734,0.000042333297,0.00007154342,0.0015975356,0.00059927756,0.005360973],"category_scores_gemma":[0.00018463784,0.00071019016,0.000321324,0.000309638,0.00013930099,0.00015317484,0.0005634478,0.000780751,0.06400402],"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":[0.00008781732,0.00017603987,0.00000925161,0.0004992599,0.00033140634,0.00013674378,0.000039483486,0.00006146075,0.001682978,0.000037053273,0.99675083,0.00018765936],"study_design_scores_gemma":[0.00088423985,0.00015094933,0.00032919945,0.00015861036,0.00031663725,0.000018405037,0.000011898065,0.0000025487493,0.00043356942,0.00008911621,0.9968689,0.0007358952],"about_ca_topic_score_codex":0.0010329048,"about_ca_topic_score_gemma":0.00020445777,"teacher_disagreement_score":0.058643047,"about_ca_system_score_codex":0.0002753148,"about_ca_system_score_gemma":0.0003142953,"threshold_uncertainty_score":0.9995349},"labels":[],"label_agreement":null},{"id":"W6950549437","doi":"10.5524/102208","title":"Supporting data for \"Message in a Bottle – Metabarcoding Enables Biodiversity Comparisons Across Ecoregions\"","year":2022,"lang":"en","type":"dataset","venue":"GigaDB","topic":"Diatoms and Algae Research","field":"Materials Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Species richness; Arthropod; Biodiversity; Habitat; Species diversity; Biomass (ecology); Beta diversity; Metacommunity","score_opus":0.12060308358706134,"score_gpt":0.3932097445349342,"score_spread":0.27260666094787284,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6950549437","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":[0.009122529,0.00058142026,0.0000394348,0.00019981827,0.0004959544,0.00054198125,0.9889578,0.000040298295,0.00002072301],"genre_scores_gemma":[0.0006005978,0.00016855543,0.00038573964,0.00008272855,0.00009880205,0.00009327488,0.9983648,0.000014923814,0.00019058188],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99685204,0.00015987991,0.00045662103,0.00094183773,0.00053290295,0.0010567291],"domain_scores_gemma":[0.9976064,0.00039626783,0.00032167186,0.0014828994,0.000045930523,0.00014683344],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0030636298,0.0002640781,0.0005895183,0.00017710896,0.00070106896,0.00038265547,0.0026146758,0.00013130676,0.010897881],"category_scores_gemma":[0.00048235292,0.00026243337,0.00010850551,0.00031335477,0.0001590035,0.00039665413,0.0042239344,0.00045353404,0.0001977516],"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":[0.000030020432,0.0001272534,0.00044165674,0.0002524634,0.00001815376,0.000061294835,0.000043729342,0.000018700395,0.00025263563,0.000010468243,0.99852806,0.00021558191],"study_design_scores_gemma":[0.00046176714,0.000036383295,0.00013584913,0.000043104574,0.00003911436,0.00000526734,0.00093247986,0.000091233625,0.00025676077,0.000011732309,0.99768203,0.00030426556],"about_ca_topic_score_codex":0.003530046,"about_ca_topic_score_gemma":0.0020241777,"teacher_disagreement_score":0.01070013,"about_ca_system_score_codex":0.0001186634,"about_ca_system_score_gemma":0.0002839305,"threshold_uncertainty_score":0.9999828},"labels":[],"label_agreement":null},{"id":"W6950597707","doi":"10.5524/102732","title":"Supporting data for \"WaveSeekerNet: Accurate Prediction of Influenza A Virus Subtypes and Host Source Using Attention-Based Deep Learning\"","year":2025,"lang":"en","type":"dataset","venue":"GigaDB","topic":"","field":"","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Host (biology); Influenza A virus; Pandemic; Transmission (telecommunications); Generalization; Deep learning","score_opus":0.0539351991770709,"score_gpt":0.35081339056524424,"score_spread":0.29687819138817334,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6950597707","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":[0.01578717,0.0006769793,0.0036450664,0.000009572016,0.00026183983,0.0011489408,0.9783162,0.00014827738,0.000005961662],"genre_scores_gemma":[0.0018947022,0.000032670887,0.00080281997,0.0000870581,0.0002454157,0.000053247004,0.996662,0.000110830384,0.000111232715],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99595946,0.00027517692,0.0012813751,0.0012327143,0.0005631182,0.00068816176],"domain_scores_gemma":[0.9947732,0.0006235509,0.0022785903,0.0017941588,0.00037778597,0.00015272452],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0016652673,0.00059319317,0.0008461076,0.0006993391,0.00038047702,0.00020963443,0.0009566797,0.0005319546,0.00007046696],"category_scores_gemma":[0.003163373,0.00066127034,0.00015483603,0.0005895814,0.00025013034,0.00048002152,0.00077208976,0.000714831,0.00002557646],"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":[0.0005799013,0.00016709583,0.006214015,0.002960447,0.0004927272,0.000009156273,0.00005367175,0.0034878128,0.009766583,0.0000016984218,0.97575134,0.00051552115],"study_design_scores_gemma":[0.0016392701,0.0001590841,0.0016339534,0.00092419947,0.0012966933,0.000008171657,0.00012081488,0.1109106,0.0003282363,0.000005696981,0.88248444,0.00048886746],"about_ca_topic_score_codex":0.0011657513,"about_ca_topic_score_gemma":0.00059967814,"teacher_disagreement_score":0.10742279,"about_ca_system_score_codex":0.00015549215,"about_ca_system_score_gemma":0.0005470392,"threshold_uncertainty_score":0.99958384},"labels":[],"label_agreement":null},{"id":"W6950629448","doi":"10.5524/100575","title":"Supporting data for \"GenPipes: an open-source framework for distributed and scalable genomic analyses\"","year":2019,"lang":"en","type":"dataset","venue":"GigaDB","topic":"Advanced Vision and Imaging","field":"Computer Science","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":"Canarie","keywords":"Workflow; Scalability; Flexibility (engineering); Software; Software deployment; Genomics; Server; Metagenomics","score_opus":0.12656520846314057,"score_gpt":0.44775548247335933,"score_spread":0.32119027401021877,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6950629448","genre_codex":"methods","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000005130654,0.00018023979,0.50643873,0.00013486012,0.00023810007,0.0006495695,0.49231562,0.00003563646,0.000002117653],"genre_scores_gemma":[0.000021153955,0.00004515246,0.32401597,0.0006880986,0.0001637077,0.000047711303,0.6748754,0.000025479198,0.00011736601],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99701756,0.000051837495,0.00053824467,0.0015224287,0.00020622998,0.00066368614],"domain_scores_gemma":[0.99471,0.0005260781,0.0005713367,0.0038423932,0.0001204388,0.00022969827],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.00080888666,0.00035869738,0.00062727084,0.0001252192,0.0003646928,0.0012879178,0.00632201,0.00021513201,0.000026563266],"category_scores_gemma":[0.00069890294,0.00033803014,0.00006585015,0.00026495528,0.000054350414,0.0015812523,0.004284196,0.0003270503,0.000027147013],"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":[0.000019795018,0.000044462377,0.000007566088,0.00014928878,0.000039842897,0.0000020258237,0.00001854295,0.00008048962,0.00008808903,0.00017338878,0.97790533,0.021471176],"study_design_scores_gemma":[0.00046690763,0.0001263718,0.000017564043,0.000115436706,0.000062970495,0.000007702587,0.000041270938,0.14141946,0.000041602314,0.0023800463,0.85491574,0.00040490826],"about_ca_topic_score_codex":0.0000562311,"about_ca_topic_score_gemma":0.000011561986,"teacher_disagreement_score":0.18255974,"about_ca_system_score_codex":0.00005254151,"about_ca_system_score_gemma":0.00020440207,"threshold_uncertainty_score":0.9999072},"labels":[],"label_agreement":null},{"id":"W6969435139","doi":"10.5524/100725","title":"Supporting data for \"Metagenomic analysis of planktonic riverine microbial consortia using nanopore sequencing reveals insight into river microbe taxonomy and function\"","year":2020,"lang":"en","type":"dataset","venue":"GigaDB","topic":"Scientific Computing and Data Management","field":"Decision Sciences","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":"Division of Environmental Biology; Canadian Institutes of Health Research; Biotechnology and Biological Sciences Research Council; Canada Foundation for Innovation; Compute Canada; National Institute of General Medical Sciences; Aarhus Universitet","keywords":"Metagenomics; Biodiversity; Plankton; Minion; Ecosystem; Biogeochemical cycle; Nanopore sequencing; Functional ecology","score_opus":0.21718279586846498,"score_gpt":0.38131448556781045,"score_spread":0.16413168969934547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6969435139","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":[0.016340753,0.00033142374,0.02353014,0.00005921186,0.0010647251,0.00076252315,0.957871,0.00002652297,0.000013661017],"genre_scores_gemma":[0.0039765066,0.00003184099,0.02196309,0.00026794864,0.00020091972,0.000011636139,0.9733563,0.00001950653,0.00017227013],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9941605,0.00022980694,0.00204419,0.0023303232,0.00075186667,0.0004833206],"domain_scores_gemma":[0.99277353,0.00094057724,0.0023231485,0.0034491185,0.0003208563,0.00019278502],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.005341697,0.0004254081,0.0013833456,0.0014805231,0.00042359222,0.00060283515,0.0027292974,0.00018182822,0.00036744977],"category_scores_gemma":[0.002281814,0.00037855562,0.0002941635,0.0021292472,0.00039321563,0.0004418108,0.0040134066,0.00026321082,0.000059251197],"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":[0.000060148548,0.000022039065,0.00028452624,0.00014782704,0.0011250877,0.0000187804,0.00015659221,0.00046822277,0.0035946125,0.000008119492,0.9907295,0.0033845278],"study_design_scores_gemma":[0.00039800955,0.000049112426,0.00021061434,0.00006629411,0.0033287334,0.000007589058,0.00027099447,0.010875431,0.00011766148,0.00011870996,0.98416966,0.000387218],"about_ca_topic_score_codex":0.00085700076,"about_ca_topic_score_gemma":0.00048069895,"teacher_disagreement_score":0.015485243,"about_ca_system_score_codex":0.0001428569,"about_ca_system_score_gemma":0.00042725474,"threshold_uncertainty_score":0.99986666},"labels":[],"label_agreement":null},{"id":"W6969552464","doi":"10.5524/102744","title":"Genome assembly of the sea turtle Lepidochelys kempii","year":2025,"lang":"en","type":"dataset","venue":"GigaDB","topic":"Turtle Biology and Conservation","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Nova scotia; Contig; Shore; Haplotype; Peninsula; Sea turtle; Genome","score_opus":0.009610998464547892,"score_gpt":0.22723633921703199,"score_spread":0.2176253407524841,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6969552464","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":[0.010019692,0.00013749002,0.0000067851743,0.00070466223,0.0005807369,0.0002187503,0.98516166,0.0000128599595,0.0031573875],"genre_scores_gemma":[0.0060246317,0.00006494682,0.000036448553,0.0012991544,0.00009803786,0.00002505291,0.9859206,0.00000451883,0.006526605],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991502,0.000101808066,0.00018736576,0.00024513886,0.00015984845,0.00015561003],"domain_scores_gemma":[0.9991347,0.00006320147,0.00015877388,0.0006112375,0.000006672632,0.000025378205],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00017473033,0.0001373907,0.00016845863,0.000019827818,0.00009043294,0.000007357536,0.00065829646,0.00026261457,0.0011738926],"category_scores_gemma":[0.00006941687,0.000095257485,0.000121297955,0.0001840332,0.00018791089,0.000038025857,0.0004182122,0.00024404975,0.00017075452],"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":[0.0000057903894,0.000021806258,0.0015635432,0.000019665635,0.00002057404,9.1114373e-7,0.000007360426,0.000015333128,0.00082074845,0.00000706755,0.99730796,0.00020925203],"study_design_scores_gemma":[0.00006699295,0.000014013397,0.063909896,0.000016730579,0.00004551661,0.0000012604571,0.0000042618085,0.0000018254544,0.00054320344,0.0000863376,0.93521416,0.00009582529],"about_ca_topic_score_codex":0.00058987655,"about_ca_topic_score_gemma":0.00031218474,"teacher_disagreement_score":0.06234635,"about_ca_system_score_codex":0.00006684729,"about_ca_system_score_gemma":0.000045659657,"threshold_uncertainty_score":0.99973917},"labels":[],"label_agreement":null}]}