{"id":"W4317614930","doi":"10.22541/essoar.167422960.07359877/v1","title":"Development and application of the Branched and Isoprenoid GDGT Machine learning Classification algorithm (BIGMaC) for paleoenvironmental reconstruction","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Geology and Paleoclimatology Research","field":"Earth and Planetary Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Consejo Nacional de Ciencia y Tecnología; Woods Hole Oceanographic Institution; American Chemical Society Petroleum Research Fund; National Science Foundation","keywords":"Sedimentary depositional environment; Geology; Sedimentary rock; Paleontology; Paleoclimatology; Geologic record; Machine learning; Oceanography; Computer science; Climate change","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.002228299,0.001051978,0.0008319938,0.002003136,0.0009024449,0.00118246,0.00224096,0.001366105,0.001664686],"category_scores_gemma":[0.005334368,0.0004054414,0.0009964306,0.001302522,0.0003926585,0.0009159541,0.001302443,0.001614343,0.0007135406],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001172638,"about_ca_system_score_gemma":0.002161549,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01987369,"about_ca_topic_score_gemma":0.01606947,"domain_scores_codex":[0.9993892,0.0001269365,0.00006014612,0.0002078298,0.0001490604,0.0000667963],"domain_scores_gemma":[0.9980837,0.0007218105,0.0001169105,0.0002455795,0.0007157352,0.0001162067],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000331548,0.0002735077,0.02919103,0.0001169643,0.0002250089,0.0002120643,0.0001903938,0.2025237,0.00738924,0.004055648,0.01124128,0.7442496],"study_design_scores_gemma":[0.00001745468,0.00002507216,0.001261082,0.000008554341,0.000009181199,0.00002116257,0.00003006655,0.9942219,0.001487487,0.001543575,0.00136619,0.000008249114],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.198787,0.00117164,0.7739257,0.0009317798,0.0002866288,0.00040335,0.002074239,0.01925226,0.003167314],"genre_scores_gemma":[0.3313597,0.0001617544,0.6623465,0.00034804,0.00007946777,0.0003529347,0.003455923,0.0002929762,0.001602696],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01987369,"threshold_uncertainty_score":0.03951603,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03430623523477798,"score_gpt":0.2440314492208584,"score_spread":0.2097252139860804,"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."}}