{"id":"W4213043896","doi":"10.1016/j.ecoinf.2022.101601","title":"PermaBN: A Bayesian Network framework to help predict permafrost thaw in the Arctic","year":2022,"lang":"en","type":"article","venue":"Ecological Informatics","topic":"Climate change and permafrost","field":"Earth and Planetary Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Texas A and M University; National Science Foundation","keywords":"Permafrost; Environmental science; Arctic; Bayesian network; Snow; Climate change; Cryosphere; Vegetation (pathology); Bayesian inference; Climatology; Physical geography; Bayesian probability; Computer science; Ecology; Meteorology; Machine learning; Sea ice; Geology; Artificial intelligence; Geography","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001078147,0.0001761032,0.0002294798,0.00007211049,0.0006313435,0.0001447852,0.0006948357,0.00009865953,0.04370889],"category_scores_gemma":[0.0001384276,0.0001136165,0.00008128619,0.0007272318,0.00006800696,0.000182447,0.0001307246,0.0007473608,0.0005020041],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002075084,"about_ca_system_score_gemma":0.00003587332,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002430477,"about_ca_topic_score_gemma":0.004780892,"domain_scores_codex":[0.9980797,0.0002127164,0.0004714251,0.0001362175,0.0004590661,0.0006408959],"domain_scores_gemma":[0.9985954,0.0008484703,0.00009402649,0.0002890576,0.00001891993,0.0001541011],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00004362873,0.00005384465,0.932861,0.00002492742,0.000006301992,0.00004524717,0.0105065,0.03723533,2.836521e-7,0.0002709152,0.01803006,0.0009219594],"study_design_scores_gemma":[0.0001631461,0.000589589,0.9182447,0.00001604404,0.000009653377,0.00008577791,0.01378614,0.02660438,1.529794e-7,0.002040834,0.03825143,0.0002081134],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9651436,0.0002082194,0.0002168582,0.004639031,0.00107707,0.00105873,0.004284752,0.00007794415,0.02329383],"genre_scores_gemma":[0.9730753,0.00004870069,0.000709575,0.02415131,0.0003193428,0.00004182205,0.001586055,0.000003663242,0.00006425421],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04320688,"threshold_uncertainty_score":0.9571653,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03120018005630917,"score_gpt":0.2454358500140922,"score_spread":0.214235669957783,"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."}}