{"id":"W4402273081","doi":"10.26434/chemrxiv-2024-m2h4h","title":"A comprehensive approach to analyzing environmental data with non-detects","year":2024,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Water Quality Monitoring and Analysis","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Environmental data; Data science; Data mining; Political science","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":[0.01760767,0.001900693,0.002141699,0.004953396,0.001660661,0.005773619,0.004454002,0.002700511,0.003756936],"category_scores_gemma":[0.04643001,0.001801807,0.004410963,0.008167934,0.002292323,0.004826363,0.005221963,0.006099285,0.002802395],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001174695,"about_ca_system_score_gemma":0.004378105,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003805452,"about_ca_topic_score_gemma":0.006621446,"domain_scores_codex":[0.9847231,0.005333965,0.001514606,0.002677219,0.005457445,0.0002935453],"domain_scores_gemma":[0.9718502,0.01289322,0.002350091,0.009569434,0.002896389,0.0004406295],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001488445,0.0004447894,0.02416459,0.001809533,0.001772375,0.0005662188,0.00131121,0.06232528,0.01577174,0.3442521,0.04576119,0.501672],"study_design_scores_gemma":[0.00005677048,0.000125078,0.01175361,0.0003450998,0.0002399814,0.001062046,0.0002502391,0.2077743,0.009348688,0.593251,0.1755265,0.0002667211],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0006101851,0.0001535965,0.9962287,0.0002977396,0.00005038236,0.00006527366,0.001085599,0.001049119,0.0004594595],"genre_scores_gemma":[0.01220951,0.0005153086,0.981842,0.0004101497,0.0001899203,0.0005366125,0.002424347,0.0005694614,0.001302632],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01760767,"threshold_uncertainty_score":0.09311938,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04530110944337658,"score_gpt":0.2649662705815363,"score_spread":0.2196651611381597,"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."}}