{"id":"W4408509457","doi":"10.1016/j.ecoser.2025.101717","title":"Revealing driver-mediated indirect interactions between ecosystem services using Bayesian Belief Networks","year":2025,"lang":"en","type":"article","venue":"Ecosystem Services","topic":"Land Use and Ecosystem Services","field":"Environmental Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University Health Centre; McGill University; Centre For Cold Ocean Resources Engineering; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; CRC Health Group","keywords":"Ecosystem services; Bayesian network; Ecosystem; Bayesian probability; Computer science; Environmental resource management; Ecology; Economics; Artificial intelligence; Biology","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"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":[0.0008924421,0.0006372623,0.0009819049,0.0003141562,0.0009506975,0.0004332065,0.001304093,0.0003597053,0.0009580191],"category_scores_gemma":[0.00000562297,0.0005682657,0.0002436963,0.001437132,0.00001235415,0.001358307,0.0007361272,0.0003943115,0.001050875],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005910553,"about_ca_system_score_gemma":0.00003815192,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004106779,"about_ca_topic_score_gemma":0.101182,"domain_scores_codex":[0.9956914,0.0004182561,0.001302745,0.001080863,0.0005264655,0.0009803013],"domain_scores_gemma":[0.9976063,0.0003536171,0.0007408104,0.0009086144,0.00006169754,0.0003289707],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004451808,0.0001241512,0.9571405,0.003525498,0.0005515104,0.00003757547,0.001282474,0.03527538,0.0008039318,0.00002065753,0.000213708,0.0009800829],"study_design_scores_gemma":[0.001426381,0.00009214961,0.07792923,0.00652476,0.0006169438,0.00004864459,0.002633274,0.8551263,0.00118921,0.0001299484,0.05277133,0.001511838],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9888248,0.0005357313,0.0006959445,0.0002122284,0.001645944,0.0008517014,0.0002168731,0.0004566626,0.006560079],"genre_scores_gemma":[0.9981066,0.00006703395,0.000319584,0.0004228115,0.0005471213,0.00007228734,0.0002626493,0.00006885752,0.0001330746],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8792113,"threshold_uncertainty_score":0.9999552,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008381654024163592,"score_gpt":0.2322205886374132,"score_spread":0.2238389346132496,"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."}}