{"id":"W4387821381","doi":"10.1038/s41598-023-44875-0","title":"Bayesian regression versus machine learning for rapid age estimation of archaeological features identified with lidar at Angkor","year":2023,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Archaeological Research and Protection","field":"Earth and Planetary Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Max-Planck-Gesellschaft","keywords":"Lidar; Documentation; Population; Bayesian probability; Regression; Geography; Archaeology; Artificial intelligence; Machine learning; Computer science; Physical geography; Remote sensing; Cartography; Statistics; Mathematics","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":[0.001770669,0.0001256407,0.0001855272,0.0002295147,0.0006480387,0.00006195882,0.0001326656,0.00008843084,0.00061213],"category_scores_gemma":[0.0008989049,0.00007670405,0.00007876043,0.0006817734,0.0006384804,0.0001507339,0.00005667411,0.000185891,0.00002790786],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009989811,"about_ca_system_score_gemma":0.00004653351,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001945868,"about_ca_topic_score_gemma":0.001253443,"domain_scores_codex":[0.9980749,0.0001257041,0.0002753109,0.0004963198,0.0006283442,0.0003993676],"domain_scores_gemma":[0.9989786,0.0003359627,0.0001747045,0.0002643425,0.00007928401,0.0001671754],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.005472837,0.00003695348,0.1190074,0.0004171341,0.00009810756,0.002249446,0.001764707,0.1143493,0.009900184,0.0000903402,0.007577865,0.7390357],"study_design_scores_gemma":[0.002023154,0.004753612,0.5596146,0.000265289,0.00006201897,0.0004283509,0.0003828378,0.2440653,0.05773159,0.1050361,0.02480744,0.0008296852],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9878914,0.0004543446,0.007370295,0.000246107,0.001749862,0.0007741954,0.0000194483,0.0002185912,0.001275743],"genre_scores_gemma":[0.9919576,0.00004007775,0.003776896,0.000003952174,0.00003622947,0.00001397243,0.001059398,0.00000447862,0.003107402],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.738206,"threshold_uncertainty_score":0.6702394,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0362213024637873,"score_gpt":0.2870639471151875,"score_spread":0.2508426446514002,"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."}}