{"id":"W4405360772","doi":"10.1115/ipc2024-131852","title":"Knowledge-Informed Semi-Supervised Robust Modeling for Mixed Oil Length Prediction in Multi-Product Pipelines Based on Student’s-T Mixture Model","year":2024,"lang":"en","type":"article","venue":"Volume 3: Operations, Monitoring, and Maintenance; Materials and Joining","topic":"Petroleum Processing and Analysis","field":"Chemistry","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Pipeline transport; Product (mathematics); Computer science; Data modeling; Petroleum engineering; Artificial intelligence; Machine learning; Engineering; Mathematics; Database; Mechanical engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001409968,0.001013414,0.001388339,0.0007050084,0.0003518935,0.001031636,0.001627708,0.0009825948,0.0009374853],"category_scores_gemma":[0.003156463,0.0006709727,0.00148604,0.0006291928,0.0009284738,0.001166856,0.0009611606,0.001417372,0.0003011373],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007250212,"about_ca_system_score_gemma":0.001056032,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0106946,"about_ca_topic_score_gemma":0.008022343,"domain_scores_codex":[0.9994056,0.0001856289,0.000032812,0.000198944,0.0001178241,0.00005926671],"domain_scores_gemma":[0.9982222,0.001098117,0.0002671179,0.0001025612,0.0002528229,0.00005711298],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006590176,0.00003193777,0.0009988629,0.0000388349,0.00005353168,0.00003011203,0.00002960066,0.9793953,0.001227444,0.002122293,0.0002622642,0.01574391],"study_design_scores_gemma":[8.067168e-7,0.000003860144,0.0000501943,8.765878e-7,0.00000170497,0.000001206794,0.000001079187,0.9994236,0.0001229866,0.0003709539,0.0000210436,0.0000017391],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04708407,0.0002244117,0.9513834,0.0001653369,0.00002328003,0.00002439049,0.0001080069,0.000418358,0.0005688572],"genre_scores_gemma":[0.9317896,0.000197587,0.06515161,0.0001094436,0.00004610506,0.0000924301,0.0004661214,0.00007727996,0.00206987],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0106946,"threshold_uncertainty_score":0.02126467,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03660236648895963,"score_gpt":0.2944162497518111,"score_spread":0.2578138832628515,"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."}}