{"id":"W3107929220","doi":"10.1101/2020.11.24.395095","title":"Predicting direct and indirect non-target impacts of biocontrol agents using machine-learning approaches","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Plant and animal studies","field":"Agricultural and Biological Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Generalist and specialist species; Pairwise comparison; Machine learning; Generality; Trait; Ecology; Artificial intelligence; Computer science; Competition (biology); Biology; Host (biology); Ecological network; Habitat; Ecosystem","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002315431,0.000948189,0.0005633101,0.001224952,0.0002880652,0.0007754239,0.0006658743,0.0009059233,0.0008823587],"category_scores_gemma":[0.006238178,0.0002761384,0.0006845724,0.0004529104,0.0003473508,0.0009431271,0.000510333,0.0008102367,0.0002150773],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008004108,"about_ca_system_score_gemma":0.0004569233,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004680629,"about_ca_topic_score_gemma":0.004584347,"domain_scores_codex":[0.9993181,0.0002860971,0.00005260243,0.0001815494,0.0001004398,0.00006113906],"domain_scores_gemma":[0.9922478,0.006117855,0.0007085856,0.0002384484,0.0005251498,0.0001621297],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001695267,0.0002542863,0.06391432,0.00007924834,0.0001799093,0.00005383414,0.0000221902,0.8982671,0.002727936,0.0003493423,0.0003060786,0.03367622],"study_design_scores_gemma":[0.000002727519,0.00002887481,0.002992366,0.000003850033,0.000007907465,0.000006904491,0.000003592135,0.996079,0.0005048151,0.0003299631,0.0000365173,0.000003464014],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8626267,0.0006391825,0.1332879,0.0003119411,0.00003671351,0.00008240114,0.0005716627,0.0005190044,0.00192443],"genre_scores_gemma":[0.9752566,0.00006553884,0.02398099,0.0000468645,0.0000156788,0.00003946966,0.0003069493,0.000009187755,0.0002787403],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004680629,"threshold_uncertainty_score":0.0122453,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05645953717324868,"score_gpt":0.2072265957764625,"score_spread":0.1507670586032138,"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."}}