{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":13,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":13,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12","author_layer_release":"2026-06-26"},"query_hash":"d0588226f4e4","filters":{"venue":"GigaDB"}},"results":[{"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","authors":[],"retraction":null,"screen_n_in":null,"score":{"opus":0.0539351991770709,"gpt":0.3508133905652442,"spread":0.2968781913881733,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001665267,0.0005931932,0.0008461076,0.0006993391,0.000380477,0.0002096344,0.0009566797,0.0005319546,0.00007046696],"category_scores_gemma":[0.003163373,0.0006612703,0.000154836,0.0005895814,0.0002501303,0.0004800215,0.0007720898,0.000714831,0.00002557646],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001554921,"about_ca_system_score_gemma":0.0005470392,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001165751,"about_ca_topic_score_gemma":0.0005996781,"domain_scores_codex":[0.9959595,0.0002751769,0.001281375,0.001232714,0.0005631182,0.0006881618],"domain_scores_gemma":[0.9947732,0.0006235509,0.00227859,0.001794159,0.000377786,0.0001527245],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0005799013,0.0001670958,0.006214015,0.002960447,0.0004927272,0.000009156273,0.00005367175,0.003487813,0.009766583,0.000001698422,0.9757513,0.0005155212],"study_design_scores_gemma":[0.00163927,0.0001590841,0.001633953,0.0009241995,0.001296693,0.000008171657,0.0001208149,0.1109106,0.0003282363,0.000005696981,0.8824844,0.0004888675],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.01578717,0.0006769793,0.003645066,0.000009572016,0.0002618398,0.001148941,0.9783162,0.0001482774,0.000005961662],"genre_scores_gemma":[0.001894702,0.00003267089,0.00080282,0.0000870581,0.0002454157,0.000053247,0.996662,0.0001108304,0.0001112327],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.1074228,"threshold_uncertainty_score":0.9995838,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"National Science Foundation of Sri Lanka","keywords":"Vole; Subspecies; Genome; Mitochondrial DNA; Montane ecology; Range (aeronautics)","authors":[],"retraction":null,"screen_n_in":null,"score":{"opus":0.06062579880789461,"gpt":0.3029744775442766,"spread":0.242348678736382,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009760622,0.0007289927,0.0008230132,0.0001466677,0.0003939409,0.0003839293,0.006133163,0.0004725478,0.0008718944],"category_scores_gemma":[0.0004848268,0.0005694355,0.0002602704,0.0003356153,0.0001854587,0.0002042729,0.003164391,0.0008734639,0.008966586],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003833124,"about_ca_system_score_gemma":0.0006365013,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003102799,"about_ca_topic_score_gemma":0.009551177,"domain_scores_codex":[0.9961668,0.0001372777,0.0006571502,0.001560633,0.0005532004,0.0009249258],"domain_scores_gemma":[0.9881897,0.0005327179,0.0005101934,0.01041422,0.0001740683,0.0001790821],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001018566,0.00009955772,0.000002775885,0.0001534511,0.0005130817,0.00018894,0.00001331333,0.00001991973,0.001102918,0.000004219981,0.9969952,0.0008047873],"study_design_scores_gemma":[0.0007604941,0.00003967149,0.0001131627,0.00009248994,0.001020275,0.0001539914,0.0001027303,0.0002728289,0.00008457833,0.00002723168,0.9966565,0.000676025],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.00004385567,0.01423278,0.00005201582,0.0003911117,0.001422677,0.001820321,0.9818857,0.0001086702,0.00004282091],"genre_scores_gemma":[0.000008232789,0.0006329626,0.0005001872,0.0004811711,0.001818187,0.000365217,0.9941235,0.000289488,0.001781072],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.01359982,"threshold_uncertainty_score":0.9996757,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"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","authors":[],"retraction":null,"screen_n_in":null,"score":{"opus":0.02564693946101074,"gpt":0.2722940613060459,"spread":0.2466471218450352,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0005712056,0.0007396071,0.001312795,0.0004895573,0.0000423333,0.00007154342,0.001597536,0.0005992776,0.005360973],"category_scores_gemma":[0.0001846378,0.0007101902,0.000321324,0.000309638,0.000139301,0.0001531748,0.0005634478,0.000780751,0.06400402],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002753148,"about_ca_system_score_gemma":0.0003142953,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001032905,"about_ca_topic_score_gemma":0.0002044578,"domain_scores_codex":[0.9963096,0.0001913968,0.00083929,0.0008903406,0.001020399,0.0007490024],"domain_scores_gemma":[0.9954005,0.000169819,0.001229726,0.002858514,0.0001587361,0.0001826401],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00008781732,0.0001760399,0.00000925161,0.0004992599,0.0003314063,0.0001367438,0.00003948349,0.00006146075,0.001682978,0.00003705327,0.9967508,0.0001876594],"study_design_scores_gemma":[0.0008842399,0.0001509493,0.0003291995,0.0001586104,0.0003166372,0.00001840504,0.00001189807,0.000002548749,0.0004335694,0.00008911621,0.9968689,0.0007358952],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.001331074,0.002301195,0.000002620998,0.00003340755,0.00125004,0.0007775776,0.9938352,0.00007771129,0.0003912429],"genre_scores_gemma":[0.0007725723,0.0009465586,0.0001591382,0.0002074387,0.0005318613,0.00003983309,0.9955793,0.0002249374,0.001538338],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.05864305,"threshold_uncertainty_score":0.9995349,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Canarie","keywords":"Workflow; Scalability; Flexibility (engineering); Software; Software deployment; Genomics; Server; Metagenomics","authors":[],"retraction":null,"screen_n_in":null,"score":{"opus":0.1265652084631406,"gpt":0.4477554824733593,"spread":0.3211902740102188,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0008088867,0.0003586974,0.0006272708,0.0001252192,0.0003646928,0.001287918,0.00632201,0.000215132,0.00002656327],"category_scores_gemma":[0.0006989029,0.0003380301,0.00006585015,0.0002649553,0.00005435041,0.001581252,0.004284196,0.0003270503,0.00002714701],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005254151,"about_ca_system_score_gemma":0.0002044021,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000562311,"about_ca_topic_score_gemma":0.00001156199,"domain_scores_codex":[0.9970176,0.00005183749,0.0005382447,0.001522429,0.00020623,0.0006636861],"domain_scores_gemma":[0.99471,0.0005260781,0.0005713367,0.003842393,0.0001204388,0.0002296983],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001979502,0.00004446238,0.000007566088,0.0001492888,0.0000398429,0.000002025824,0.00001854295,0.00008048962,0.00008808903,0.0001733888,0.9779053,0.02147118],"study_design_scores_gemma":[0.0004669076,0.0001263718,0.00001756404,0.0001154367,0.0000629705,0.000007702587,0.00004127094,0.1414195,0.00004160231,0.002380046,0.8549157,0.0004049083],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"dataset","genre_scores_codex":[0.000005130654,0.0001802398,0.5064387,0.0001348601,0.0002381001,0.0006495695,0.4923156,0.00003563646,0.000002117653],"genre_scores_gemma":[0.00002115396,0.00004515246,0.324016,0.0006880986,0.0001637077,0.0000477113,0.6748754,0.0000254792,0.000117366],"genre_candidate":"dataset","genre_consensus":null,"teacher_disagreement_score":0.1825597,"threshold_uncertainty_score":0.9999072,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Nova scotia; Contig; Shore; Haplotype; Peninsula; Sea turtle; Genome","authors":[],"retraction":null,"screen_n_in":null,"score":{"opus":0.009610998464547892,"gpt":0.227236339217032,"spread":0.2176253407524841,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001747303,0.0001373907,0.0001684586,0.00001982782,0.00009043294,0.000007357536,0.0006582965,0.0002626146,0.001173893],"category_scores_gemma":[0.00006941687,0.00009525748,0.000121298,0.0001840332,0.0001879109,0.00003802586,0.0004182122,0.0002440497,0.0001707545],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006684729,"about_ca_system_score_gemma":0.00004565966,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005898766,"about_ca_topic_score_gemma":0.0003121847,"domain_scores_codex":[0.9991502,0.0001018081,0.0001873658,0.0002451389,0.0001598485,0.00015561],"domain_scores_gemma":[0.9991347,0.00006320147,0.0001587739,0.0006112375,0.000006672632,0.00002537821],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000005790389,0.00002180626,0.001563543,0.00001966563,0.00002057404,9.111437e-7,0.000007360426,0.00001533313,0.0008207484,0.00000706755,0.997308,0.000209252],"study_design_scores_gemma":[0.00006699295,0.0000140134,0.0639099,0.00001673058,0.00004551661,0.000001260457,0.000004261808,0.000001825454,0.0005432034,0.0000863376,0.9352142,0.00009582529],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.01001969,0.00013749,0.000006785174,0.0007046622,0.0005807369,0.0002187503,0.9851617,0.00001285996,0.003157387],"genre_scores_gemma":[0.006024632,0.00006494682,0.00003644855,0.001299154,0.00009803786,0.00002505291,0.9859206,0.00000451883,0.006526605],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.06234635,"threshold_uncertainty_score":0.9997392,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Species richness; Arthropod; Biodiversity; Habitat; Species diversity; Biomass (ecology); Beta diversity; Metacommunity","authors":[],"retraction":null,"screen_n_in":null,"score":{"opus":0.1206030835870613,"gpt":0.3932097445349342,"spread":0.2726066609478728,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00306363,0.0002640781,0.0005895183,0.000177109,0.000701069,0.0003826555,0.002614676,0.0001313068,0.01089788],"category_scores_gemma":[0.0004823529,0.0002624334,0.0001085055,0.0003133548,0.0001590035,0.0003966541,0.004223934,0.000453534,0.0001977516],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001186634,"about_ca_system_score_gemma":0.0002839305,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003530046,"about_ca_topic_score_gemma":0.002024178,"domain_scores_codex":[0.996852,0.0001598799,0.000456621,0.0009418377,0.000532903,0.001056729],"domain_scores_gemma":[0.9976064,0.0003962678,0.0003216719,0.001482899,0.00004593052,0.0001468334],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003002043,0.0001272534,0.0004416567,0.0002524634,0.00001815376,0.00006129484,0.00004372934,0.0000187004,0.0002526356,0.00001046824,0.9985281,0.0002155819],"study_design_scores_gemma":[0.0004617671,0.0000363833,0.0001358491,0.00004310457,0.00003911436,0.00000526734,0.0009324799,0.00009123363,0.0002567608,0.00001173231,0.997682,0.0003042656],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.009122529,0.0005814203,0.0000394348,0.0001998183,0.0004959544,0.0005419813,0.9889578,0.0000402983,0.00002072301],"genre_scores_gemma":[0.0006005978,0.0001685554,0.0003857396,0.00008272855,0.00009880205,0.00009327488,0.9983648,0.00001492381,0.0001905819],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.01070013,"threshold_uncertainty_score":0.9999828,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Subtropics; Mediterranean sea; Temperate climate; Mediterranean climate; Indian ocean; Haplotype; Sequence assembly; Pacific ocean","authors":[],"retraction":null,"screen_n_in":null,"score":{"opus":0.007752025001181636,"gpt":0.2190501608215785,"spread":0.2112981358203968,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001381587,0.0001594507,0.0001886387,0.00002197801,0.0001014453,0.000009376392,0.0008013761,0.0003149432,0.0008220664],"category_scores_gemma":[0.00006279991,0.0001131792,0.0001286657,0.000200009,0.0002002934,0.00003894246,0.0004716753,0.0002818969,0.00007322663],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001071251,"about_ca_system_score_gemma":0.00006310396,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001383341,"about_ca_topic_score_gemma":0.000743393,"domain_scores_codex":[0.9990751,0.0001056141,0.0001947631,0.0002446706,0.0002020137,0.0001779006],"domain_scores_gemma":[0.9989769,0.00005781534,0.0001578374,0.0007666955,0.00001080169,0.00002995724],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000005058464,0.00001341109,0.002523582,0.00002522057,0.00002344769,0.000001380197,0.0000245517,0.00001351132,0.0004699278,0.00000464681,0.996678,0.0002172584],"study_design_scores_gemma":[0.00006737537,0.00001590459,0.06561045,0.00002154706,0.00006026208,0.000001659196,0.00001179115,0.00000140862,0.0005083886,0.00002841996,0.9335567,0.0001160807],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.01636047,0.0002377537,0.000002245986,0.0005378024,0.0006606457,0.0002258722,0.9799041,0.00001237396,0.002058773],"genre_scores_gemma":[0.01242254,0.00004081593,0.00001289828,0.001068884,0.00009053514,0.00002547881,0.9832075,0.000005277362,0.003126125],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.06312129,"threshold_uncertainty_score":0.9001051,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","authors":[],"retraction":null,"screen_n_in":null,"score":{"opus":0.06032147925947912,"gpt":0.3745358988320427,"spread":0.3142144195725636,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003928843,0.0001826942,0.0003733944,0.00009241143,0.0001002533,0.00005043573,0.0006029756,0.0000676136,0.00005099405],"category_scores_gemma":[0.0002631542,0.0001360619,0.00008251076,0.0001959363,0.0000491354,0.000129376,0.0002379039,0.0002450911,0.000006258663],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001011102,"about_ca_system_score_gemma":0.00005581956,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003598874,"about_ca_topic_score_gemma":0.0004313656,"domain_scores_codex":[0.9985808,0.00002653112,0.0006676462,0.0003382381,0.0001359802,0.0002508358],"domain_scores_gemma":[0.9984026,0.000260519,0.0002388934,0.0009169439,0.00009540198,0.00008562651],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000008781855,0.00001079293,0.0002417546,0.000333834,0.0002020033,0.000002454562,0.000009207525,0.0008356536,0.00002510075,0.000001937772,0.9965092,0.001819279],"study_design_scores_gemma":[0.0003272851,0.00002800156,0.0002339374,0.00006522374,0.0003954197,0.000005549392,0.00001455084,0.1324134,0.0001009169,0.00001000252,0.8662249,0.0001807714],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0009606052,0.002212917,0.0004499823,0.0008951778,0.000424642,0.0004498633,0.9945461,0.00004780251,0.00001286613],"genre_scores_gemma":[0.01865088,0.01189279,0.00006556893,0.00009803632,0.0007328715,0.0001354096,0.9682595,0.00003939631,0.0001256171],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.1315777,"threshold_uncertainty_score":0.5548444,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","authors":[],"retraction":null,"screen_n_in":null,"score":{"opus":0.04601337461542012,"gpt":0.3625341177756394,"spread":0.3165207431602193,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002931913,0.0007153688,0.001357985,0.000413491,0.0005400487,0.001304811,0.001018711,0.0006541625,0.0001765775],"category_scores_gemma":[0.00209115,0.0006981514,0.0002286367,0.00008450345,0.0001406876,0.0005717648,0.0004053843,0.0002436432,0.0008326777],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002346881,"about_ca_system_score_gemma":0.0003956863,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000421017,"about_ca_topic_score_gemma":0.0001132722,"domain_scores_codex":[0.9963018,0.00003891519,0.00154279,0.0004787046,0.0004666672,0.001171087],"domain_scores_gemma":[0.9942786,0.0003339675,0.003004981,0.001667458,0.0004483667,0.0002666341],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001507034,0.00003445846,0.000009791707,0.002625681,0.0003366304,0.000004199337,0.00008379298,0.00001068144,0.0005404643,0.000009018641,0.9958873,0.0003072927],"study_design_scores_gemma":[0.001366914,0.0001604035,0.0001121512,0.0003070665,0.0008890739,0.00001675861,0.0000666223,0.0001687171,0.000277998,0.0003664412,0.9954413,0.0008265356],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.001167345,0.0001158529,0.0005951888,0.00003218702,0.0006860154,0.002908964,0.9943669,0.00008488004,0.00004270947],"genre_scores_gemma":[0.0001962381,0.00005693542,0.008190875,0.0001346439,0.001028787,0.0007266906,0.9889753,0.0001994277,0.000491064],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.007595686,"threshold_uncertainty_score":0.9999453,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Genome; Bovine genome; Genomics; Whole genome sequencing; DNA sequencing; Selection (genetic algorithm)","authors":[],"retraction":null,"screen_n_in":null,"score":{"opus":0.03095607748547605,"gpt":0.2695145841201383,"spread":0.2385585066346623,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002939256,0.00007313535,0.0001177007,0.00001724208,0.00005725853,0.000005067467,0.0001355538,0.00006316043,0.00003188881],"category_scores_gemma":[0.00013495,0.0000541746,0.00002927297,0.00008097611,0.0001035841,0.000001935271,0.00005095149,0.00004443611,0.000002073712],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001496568,"about_ca_system_score_gemma":0.0004370033,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.02911006,"about_ca_topic_score_gemma":0.03759301,"domain_scores_codex":[0.9993942,0.00004907313,0.0001397088,0.0001434303,0.0001531872,0.0001204506],"domain_scores_gemma":[0.9993815,0.000008068055,0.00007608508,0.0001959029,0.0002639751,0.00007443451],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0008001578,0.0006931559,0.1770044,0.004457855,0.001845823,0.000009290392,0.02611268,0.0003973007,0.2920646,0.0113903,0.4769398,0.008284635],"study_design_scores_gemma":[0.0008667955,0.0008918376,0.3911154,0.000201236,0.0001414763,0.00001370016,0.001140547,0.000004063937,0.004712698,0.0008197048,0.5998073,0.0002852763],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9401214,0.04944539,0.0002338701,0.001876517,0.0002004243,0.0005644463,0.0009099381,0.000004675621,0.006643365],"genre_scores_gemma":[0.9942945,0.0009925033,0.001945645,0.000436332,0.0001273075,0.00001113173,0.0003226268,0.00000781386,0.001862185],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2873519,"threshold_uncertainty_score":0.9799684,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","authors":[],"retraction":null,"screen_n_in":null,"score":{"opus":0.2391469643514842,"gpt":0.4007605994116636,"spread":0.1616136350601794,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.01452773,0.000750861,0.001118613,0.0001831405,0.001208768,0.0006567592,0.01192209,0.0002477106,0.0008320768],"category_scores_gemma":[0.003903697,0.0004978807,0.0001505213,0.0006210323,0.000737752,0.002061904,0.0111095,0.001443423,0.00003797023],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008951875,"about_ca_system_score_gemma":0.0004146601,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008590318,"about_ca_topic_score_gemma":0.001838856,"domain_scores_codex":[0.9927531,0.001029151,0.001748363,0.002332789,0.001237731,0.0008988155],"domain_scores_gemma":[0.9764266,0.001970293,0.002943001,0.01838632,0.0001994609,0.00007430273],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002310237,0.000112199,0.00001663354,0.0003782817,0.0004897079,0.000008446376,0.0001573706,2.130982e-7,0.001618259,0.0001265573,0.991926,0.004935297],"study_design_scores_gemma":[0.0007444226,0.00004214783,0.0001991699,0.00005313845,0.001343402,0.00004882685,0.002845003,0.0009339714,0.0009384977,0.0001380688,0.9922179,0.0004954275],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0002466888,0.004063546,0.0006638939,0.0008400097,0.0009325907,0.002992408,0.9901428,0.00007748609,0.00004063787],"genre_scores_gemma":[0.001605072,0.0003658462,0.0006255066,0.0003289342,0.001191808,0.0001880937,0.9954941,0.0001647966,0.00003586664],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.01632653,"threshold_uncertainty_score":0.9997473,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","authors":[],"retraction":null,"screen_n_in":null,"score":{"opus":0.01179402195255434,"gpt":0.3006095792707699,"spread":0.2888155573182156,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009141932,0.0005764048,0.0005021922,0.0002805714,0.0007925731,0.0008129943,0.0006099686,0.0002351761,0.0001166555],"category_scores_gemma":[0.0002683706,0.0004359051,0.00003619332,0.0002156971,0.001049955,0.001324433,0.0003970737,0.0004770864,0.00002977278],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001021125,"about_ca_system_score_gemma":0.0001217474,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002793395,"about_ca_topic_score_gemma":0.0009694938,"domain_scores_codex":[0.9971061,0.0001400905,0.0005701648,0.001260282,0.0003568095,0.0005665864],"domain_scores_gemma":[0.9964225,0.0002711042,0.001262106,0.001635454,0.0002701718,0.0001387175],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001393734,0.00001673915,0.0001216136,0.000301868,0.00009968257,0.000006771564,0.0001303432,2.035671e-7,0.01871004,0.000001695911,0.9724126,0.008058996],"study_design_scores_gemma":[0.001102836,0.0001382697,0.0006432426,0.0002494948,0.0008744896,0.0006607967,0.0009313985,0.001207426,0.008490562,0.0003254231,0.9846194,0.0007566884],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.005051296,0.000312839,0.00064815,0.0002532852,0.0007066119,0.001371026,0.9915504,0.00008615113,0.00002021263],"genre_scores_gemma":[0.0008504774,0.0001593543,0.01933806,0.0001102147,0.0008548468,0.00005808021,0.9783942,0.0001516545,0.00008317498],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.01868991,"threshold_uncertainty_score":0.9998093,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","authors":[],"retraction":null,"screen_n_in":null,"score":{"opus":0.217182795868465,"gpt":0.3813144855678104,"spread":0.1641316896993455,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.005341697,0.0004254081,0.001383346,0.001480523,0.0004235922,0.0006028351,0.002729297,0.0001818282,0.0003674498],"category_scores_gemma":[0.002281814,0.0003785556,0.0002941635,0.002129247,0.0003932156,0.0004418108,0.004013407,0.0002632108,0.0000592512],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001428569,"about_ca_system_score_gemma":0.0004272547,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008570008,"about_ca_topic_score_gemma":0.0004806989,"domain_scores_codex":[0.9941605,0.0002298069,0.00204419,0.002330323,0.0007518667,0.0004833206],"domain_scores_gemma":[0.9927735,0.0009405772,0.002323149,0.003449118,0.0003208563,0.000192785],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00006014855,0.00002203906,0.0002845262,0.000147827,0.001125088,0.0000187804,0.0001565922,0.0004682228,0.003594612,0.000008119492,0.9907295,0.003384528],"study_design_scores_gemma":[0.0003980095,0.00004911243,0.0002106143,0.00006629411,0.003328733,0.000007589058,0.0002709945,0.01087543,0.0001176615,0.00011871,0.9841697,0.000387218],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.01634075,0.0003314237,0.02353014,0.00005921186,0.001064725,0.0007625232,0.957871,0.00002652297,0.00001366102],"genre_scores_gemma":[0.003976507,0.00003184099,0.02196309,0.0002679486,0.0002009197,0.00001163614,0.9733563,0.00001950653,0.0001722701],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.01548524,"threshold_uncertainty_score":0.9998667,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}