{"id":"W1859664698","doi":"10.1007/s13202-015-0189-3","title":"Improving the estimation accuracy of titration-based asphaltene precipitation through power-law committee machine (PLCM) model with alternating conditional expectation (ACE) and support vector regression (SVR) elements","year":2015,"lang":"en","type":"article","venue":"Journal of Petroleum Exploration and Production Technology","topic":"Petroleum Processing and Analysis","field":"Chemistry","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Schlumberger (Canada)","funders":"","keywords":"Asphaltene; Support vector machine; Precipitation; Predictive modelling; Predictive power; Computer science; Artificial intelligence; Machine learning; Chemistry; Meteorology","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":[0.0005670815,0.0001725843,0.0002615219,0.0002390227,0.0002483981,0.00007058134,0.0001202126,0.0001119791,0.00001700897],"category_scores_gemma":[0.0005389823,0.0001221641,0.00004070746,0.0002327011,0.0001849153,0.001202927,0.00002285529,0.0002956542,6.482683e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008494232,"about_ca_system_score_gemma":0.0001796312,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001537402,"about_ca_topic_score_gemma":0.00001658069,"domain_scores_codex":[0.9983994,0.00005696023,0.0007049172,0.0002381292,0.0004688877,0.0001316807],"domain_scores_gemma":[0.997292,0.00006971494,0.001671181,0.0001805159,0.0007336255,0.00005290122],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001533528,0.0006069394,0.005786447,0.0005119354,0.0003337354,0.000009740708,0.005728796,0.2864664,0.6203175,0.004319739,0.000411292,0.07397395],"study_design_scores_gemma":[0.003025335,0.00082554,0.00009537601,0.0002916552,0.0002668684,0.0001638567,0.005706995,0.5308236,0.4474295,0.0108222,0.0002592021,0.0002898388],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7384897,0.0005906806,0.2504075,0.01000448,0.000124276,0.0000567049,0.00001395346,0.00006915222,0.0002435094],"genre_scores_gemma":[0.9818056,0.00006356173,0.0177216,0.00005508724,0.00009019251,0.00002312817,0.00008678274,0.00001639095,0.0001377249],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2443573,"threshold_uncertainty_score":0.4981709,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02466400957461221,"score_gpt":0.2833201988854355,"score_spread":0.2586561893108233,"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."}}