{"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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002546026,0.0001781035,0.0002208214,0.00003439612,0.000250053,0.0004358215,0.001716,0.00008044038,0.001435509],"category_scores_gemma":[0.0001404559,0.0001549242,0.0000605384,0.001412772,0.0008066325,0.0008654597,0.002119974,0.0001096077,0.00060573],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002476263,"about_ca_system_score_gemma":0.0002412899,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009945851,"about_ca_topic_score_gemma":0.001792037,"domain_scores_codex":[0.9972163,0.00007972282,0.0004428303,0.001139635,0.0006918054,0.0004296502],"domain_scores_gemma":[0.997777,0.00002717623,0.00008788548,0.0019911,0.00001794998,0.00009884621],"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":[0.0000546256,0.00008790487,0.0007347236,0.00009877943,0.00002971773,0.00003688853,0.0001684214,0.0000454179,0.003405004,0.0009808913,0.9707643,0.02359333],"study_design_scores_gemma":[0.0002737795,0.00003334528,0.001216269,0.00009080058,0.00005304044,0.00004370059,0.0001764972,0.0006945807,0.0005801779,0.0006920065,0.9959309,0.0002148961],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.103246,0.000530242,0.005943202,0.0003665811,0.003296305,0.000656796,0.8810712,0.0001706625,0.004719094],"genre_scores_gemma":[0.7982858,0.0000357173,0.01904083,0.0003235317,0.0002637943,0.00001374749,0.1802071,0.00003669505,0.001792719],"genre_candidate":"dataset","genre_consensus":null,"teacher_disagreement_score":0.700864,"threshold_uncertainty_score":0.9994773,"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."}}