{"id":"W3165382591","doi":"10.1371/journal.pone.0252448","title":"Predicting direct and indirect non-target impacts of biocontrol agents using machine-learning approaches","year":2021,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Plant and animal studies","field":"Agricultural and Biological Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Marsden Fund; Royal Society Te Apārangi; Royal Society; New Zealand Government; New Zealand Institute for Plant and Food Research Limited","keywords":"Generality; Pairwise comparison; Generalist and specialist species; Biology; Machine learning; Ecology; Trait; Artificial intelligence; Random forest; Abundance (ecology); Computer science; Habitat","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":[0.001748441,0.0008418105,0.0005329839,0.0008883431,0.0002369554,0.000583122,0.0006064215,0.0007420177,0.0006045186],"category_scores_gemma":[0.00509474,0.0002806251,0.0006102305,0.0003870506,0.0002912617,0.0009381956,0.0003996477,0.0007108644,0.0001768277],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006474973,"about_ca_system_score_gemma":0.0004346666,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004777725,"about_ca_topic_score_gemma":0.005147168,"domain_scores_codex":[0.9995723,0.0001786846,0.00002970064,0.0001230891,0.00005319741,0.00004309525],"domain_scores_gemma":[0.9950303,0.004056528,0.0004260592,0.000136374,0.0002562341,0.00009453605],"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":[0.00008726667,0.0001139397,0.02632087,0.00005571692,0.0001061007,0.00004901289,0.00002151076,0.9431784,0.001923609,0.0004132587,0.0001932762,0.02753699],"study_design_scores_gemma":[0.000002520689,0.00001970897,0.001913305,0.000002519463,0.000006975294,0.000008978014,0.00000324227,0.9971712,0.0003184539,0.0005116457,0.00003834323,0.000003142132],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7897421,0.0009039548,0.2065907,0.0002623203,0.00002955311,0.00006004746,0.0003998728,0.0005250685,0.001486486],"genre_scores_gemma":[0.968794,0.0001077073,0.03045695,0.00004394611,0.00001300755,0.00003582305,0.0002792262,0.00001126926,0.0002580168],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004777725,"threshold_uncertainty_score":0.009499848,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1386021903129929,"score_gpt":0.2100622131820115,"score_spread":0.07146002286901854,"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."}}