{"id":"W4403438134","doi":"10.5194/gchron-6-503-2024","title":"Towards the construction of regional marine radiocarbon calibration curves: an unsupervised machine learning approach","year":2024,"lang":"en","type":"article","venue":"Geochronology","topic":"Geology and Paleoclimatology Research","field":"Earth and Planetary Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Environment Research Council; National Computational Infrastructure; University of Victoria","keywords":"Radiocarbon dating; Calibration; Calibration curve; Unsupervised learning; Geology; Artificial intelligence; Computer science; Environmental science; Remote sensing; Mathematics; Statistics; Paleontology","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"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":[0.0005143714,0.000104669,0.00018159,0.0001169494,0.0001489621,0.00001517153,0.0002116569,0.0001653665,0.00267141],"category_scores_gemma":[0.00004578384,0.00007103702,0.00004729923,0.0002442328,0.0006734111,0.0001426323,0.00002362879,0.0004543788,0.00004262258],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000001708441,"about_ca_system_score_gemma":0.0001408863,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001419109,"about_ca_topic_score_gemma":0.001739775,"domain_scores_codex":[0.9986331,0.0005167133,0.0001954942,0.000269213,0.0001290265,0.0002564714],"domain_scores_gemma":[0.9995253,0.0001772111,0.00004121967,0.0001760868,0.00003210478,0.00004805452],"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":[0.00006058583,0.00001279504,0.9799355,0.0001561126,0.00005367624,0.00001327701,0.0002059209,0.00153808,0.00002048182,0.003495261,0.0001078348,0.01440051],"study_design_scores_gemma":[0.0003304607,0.0005083772,0.4176438,0.00003437714,0.00005058433,0.001355844,0.0002760221,0.5709202,0.0001093189,0.005621406,0.002984934,0.0001646957],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9635624,0.01407497,0.001301498,0.006022975,0.0004664923,0.0002654238,0.00002359813,0.0001069886,0.01417565],"genre_scores_gemma":[0.996376,0.001310382,0.0008409875,0.0001608297,0.00008627101,0.000004131363,0.001088504,0.000003128267,0.0001297041],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5693821,"threshold_uncertainty_score":0.9982403,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02926035893446221,"score_gpt":0.2402085444336813,"score_spread":0.2109481854992191,"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."}}