{"id":"W4399179273","doi":"10.1038/s41597-024-03410-0","title":"Global Spore Sampling Project: A global, standardized dataset of airborne fungal DNA","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Indoor Air Quality and Microbial Exposure","field":"Environmental Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"Center for Northern Studies; Université de Moncton; University of Guelph; Saint Mary's University; MacEwan University","funders":"Biotechnology and Biological Sciences Research Council; Natural Sciences and Engineering Research Council of Canada; Nature; Natural Environment Research Council; Mushroom Research Foundation; Vetenskapsrådet; Eesti Teadusagentuur; Svenska Forskningsrådet Formas; Novo Nordisk Fonden; Norges Forskningsråd; Academy of Finland; National Natural Science Foundation of China; Fundação de Amparo à Pesquisa do Estado de São Paulo; European Commission; Sight Research UK; Hrvatska Zaklada za Znanost; Novo Nordisk; Polar Knowledge Canada; Jane ja Aatos Erkon Säätiö; National Science Foundation","keywords":"Sampling (signal processing); Spore; Biology; Environmental science; Geography; Botany; Computer science","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"}],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002330642,0.0009528238,0.000732982,0.003175818,0.0005795211,0.0008201403,0.0008086479,0.0008270922,0.002669193],"category_scores_gemma":[0.004453719,0.0003959525,0.0006094414,0.004436359,0.0004389907,0.00047598,0.002256447,0.0008859704,0.002123558],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003563729,"about_ca_system_score_gemma":0.001400562,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007976214,"about_ca_topic_score_gemma":0.008873628,"domain_scores_codex":[0.997902,0.0004686077,0.0002547036,0.0007021428,0.0004616104,0.0002109092],"domain_scores_gemma":[0.9975194,0.0004446831,0.0006534355,0.0005497966,0.0005101318,0.0003225047],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001753561,0.0006838766,0.5673607,0.003207912,0.001073744,0.0008920529,0.001594274,0.01257601,0.08505955,0.002452228,0.1986177,0.1247284],"study_design_scores_gemma":[0.0003907833,0.0004206977,0.7757753,0.0001945359,0.0001586552,0.0005734143,0.0006556758,0.005578535,0.01019206,0.001355579,0.2046062,0.0000986158],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.1568672,0.0004408278,0.01428702,0.0001373934,0.00005189866,0.0003844285,0.825135,0.0008706251,0.001825546],"genre_scores_gemma":[0.07465909,0.0001206244,0.0220712,0.0000695736,0.0000240536,0.0007161748,0.9017304,0.0001884354,0.0004204196],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.007976214,"threshold_uncertainty_score":0.01585954,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05739459153731757,"score_gpt":0.339505968732002,"score_spread":0.2821113771946844,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}