{"id":"W2968906595","doi":"10.1007/s11707-019-0748-x","title":"An unsupervised learning approach to study synchroneity of past events in the South China Sea","year":2019,"lang":"en","type":"article","venue":"Frontiers of Earth Science","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Unsupervised learning; Geology; Cluster analysis; Proxy (statistics); Hindcast; Drilling; Paleontology; Artificial intelligence; Oceanography; Computer science; Machine learning; Climatology","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":[0.002818004,0.0001042665,0.0001988771,0.0001321151,0.0001278676,0.00003341148,0.002438713,0.00002828688,0.000004046512],"category_scores_gemma":[0.0001429572,0.00007652257,0.00003407486,0.001356679,0.0001397485,0.0004049851,0.000277091,0.000168834,0.000004216109],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006737367,"about_ca_system_score_gemma":0.00008558224,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005727115,"about_ca_topic_score_gemma":0.000002432464,"domain_scores_codex":[0.9981866,0.0001927992,0.0002207556,0.000482008,0.0006090403,0.0003087521],"domain_scores_gemma":[0.9989416,0.00002114803,0.0001196864,0.000743003,0.00009633685,0.00007820252],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000009969912,0.0003129776,0.9585694,0.00001505258,0.000003804615,7.845044e-7,0.01668985,0.02112073,0.002196995,0.000139446,0.00001339032,0.0009275675],"study_design_scores_gemma":[0.0002805015,0.0003245505,0.9148774,0.00001043696,0.000002173322,0.000001754409,0.004719801,0.07793595,0.001591725,0.0001184434,0.00003550067,0.0001017979],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9509208,0.00001715121,0.04522125,0.0001054389,0.0001260466,0.0003961922,7.604028e-7,0.00001612196,0.003196261],"genre_scores_gemma":[0.9813417,3.119117e-7,0.01852192,0.00002715165,0.00001003104,0.000006316425,7.04936e-7,0.000001198923,0.00009064533],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05681521,"threshold_uncertainty_score":0.4531777,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01041119280444441,"score_gpt":0.2190985077170798,"score_spread":0.2086873149126353,"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."}}