{"id":"W6906257848","doi":"10.15468/dl.z653b6","title":"Occurrence Download","year":2022,"lang":"en","type":"dataset","venue":"Global Biodiversity Information Facility","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Download; Matching (statistics); Range (aeronautics); Alien; Information system","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0004692601,0.000233084,0.0002039283,0.0001222859,0.0005545826,0.0003725992,0.002034112,0.0001698549,0.01144416],"category_scores_gemma":[0.0001884131,0.0002498356,0.0001111657,0.0005610709,0.00006994735,0.001869622,0.001379246,0.0004819597,0.07811141],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003358572,"about_ca_system_score_gemma":0.0001983213,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005223172,"about_ca_topic_score_gemma":0.000006092241,"domain_scores_codex":[0.9981996,0.0001643644,0.0003490909,0.0003443622,0.0006837717,0.0002587994],"domain_scores_gemma":[0.998116,0.00002937573,0.0003948576,0.001189147,0.0001355729,0.0001350907],"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":[0.000008656377,0.00003076185,0.0003260769,0.00005609813,0.00001148909,0.000001642019,0.00003918844,0.00002436875,1.348459e-8,0.000003423487,0.9916001,0.007898211],"study_design_scores_gemma":[0.0001771377,0.00003721704,0.0001453248,6.188974e-7,0.00001351723,0.000007294295,0.00003675219,0.000005612557,2.877634e-7,0.00000194771,0.9993223,0.0002519947],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.00001318321,0.00001843611,0.0006535181,0.0005864765,0.0007423369,0.0001918153,0.9974072,0.0002232093,0.0001638152],"genre_scores_gemma":[0.000004438269,0.00005153108,0.00001509572,0.0006443514,9.269131e-7,0.000007193703,0.9992763,7.723e-9,1.908777e-7],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.06666725,"threshold_uncertainty_score":0.9999954,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.015963953544511,"score_gpt":0.2283926934335638,"score_spread":0.2124287398890528,"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."}}