{"id":"W4408808955","doi":"10.1080/10256016.2025.2467863","title":"Reimagining the Kendall plot: using <i>δ</i> <sup>15</sup> N and <i>δ</i> <sup>18</sup> O of nitrate and advanced machine learning to improve N pollutant source classification","year":2025,"lang":"en","type":"article","venue":"Isotopes in Environmental and Health Studies","topic":"Groundwater and Isotope Geochemistry","field":"Earth and Planetary Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Nitrate; Context (archaeology); Environmental science; Pollution; Water quality; Nonpoint source pollution; Eutrophication; Pollutant; Stable isotope ratio; Water pollution; Environmental engineering; Environmental chemistry; Chemistry; Geography; Ecology; Nutrient","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004567181,0.0002141978,0.0003558599,0.00006865479,0.0005031178,0.00004000344,0.0001019965,0.00004406173,0.00002377713],"category_scores_gemma":[0.0000195345,0.0001447918,0.00002384686,0.000106159,0.0003483701,0.0001526325,0.0001333264,0.0002787507,0.000002182664],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002580019,"about_ca_system_score_gemma":0.00002546869,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001203388,"about_ca_topic_score_gemma":0.000243871,"domain_scores_codex":[0.9985995,0.00009500088,0.0003990544,0.0004126617,0.0001457496,0.0003479926],"domain_scores_gemma":[0.9995325,0.0001241622,0.0001161843,0.0001351504,0.000006299171,0.00008568173],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001126362,0.00003157416,0.863821,0.0003642818,0.00005199808,0.000002583448,0.008480031,0.006242861,0.002940161,0.000008516113,0.00004697289,0.1178974],"study_design_scores_gemma":[0.002100381,0.0006527806,0.8144169,0.0005892595,0.00007485618,0.00004584309,0.05840504,0.1023918,0.001290494,0.0004794599,0.01896632,0.0005868769],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9768652,0.01952543,0.00005606375,0.002705232,0.00003658041,0.0004257694,0.00007890751,0.00001535145,0.0002914642],"genre_scores_gemma":[0.9891235,0.008589247,0.0005795816,0.001305265,0.00003024945,0.000009308157,0.00001896893,0.000006122889,0.0003377632],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1173106,"threshold_uncertainty_score":0.5904438,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02447896273147124,"score_gpt":0.2673063319788547,"score_spread":0.2428273692473834,"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."}}