{"id":"W4416332491","doi":"10.1038/s41598-025-24236-9","title":"Enhancing soil organic carbon estimation with generative AI and Nix color sensor","year":2025,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Soil Geostatistics and Mapping","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"Indian Institute of Technology Kharagpur","keywords":"Mean squared error; Random forest; Calibration; Soil carbon; Artificial neural network; Boosting (machine learning); Partial least squares regression; Data set; Regression; Soil test","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":[0.0004699402,0.00009360944,0.0001026764,0.00005126907,0.000309787,0.0001828376,0.00003936992,0.00003057824,0.0001061341],"category_scores_gemma":[0.0001204044,0.00007745733,0.00001054872,0.0003928511,0.0002473545,0.00009512148,0.00009295347,0.00006150854,0.00001061108],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008618244,"about_ca_system_score_gemma":0.00006184287,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002523462,"about_ca_topic_score_gemma":0.001036916,"domain_scores_codex":[0.9988533,0.00002153648,0.0002057916,0.0004930299,0.0002451758,0.0001811286],"domain_scores_gemma":[0.9995157,0.0000250193,0.0001081331,0.0002658865,0.00002778927,0.00005749056],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0000177837,0.00007762945,0.05261308,0.00006385555,0.00004072364,0.0004558795,0.00261151,0.01250389,0.9078341,0.0002588252,0.007714876,0.01580792],"study_design_scores_gemma":[0.0004681807,0.0001138577,0.04257943,0.0001938282,0.0001139655,0.0003241527,0.0006941796,0.3144489,0.6160496,0.01728471,0.007096575,0.0006325397],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9774157,0.00002256657,0.01626325,0.0002303114,0.001010333,0.0001963562,6.81593e-7,0.00003232892,0.004828483],"genre_scores_gemma":[0.9864563,0.000001317142,0.00671944,0.0001206074,0.0000101086,0.00001292048,0.00001073072,0.000006099332,0.006662485],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.301945,"threshold_uncertainty_score":0.3158619,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004886922566827325,"score_gpt":0.2186571633630497,"score_spread":0.2137702407962224,"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."}}