{"id":"W4386293285","doi":"10.26434/chemrxiv-2023-v72j0","title":"Extraction Yield Prediction for the Large-Scale Recovery of Botanicals","year":2023,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Phase Equilibria and Thermodynamics","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Chemical space; Computer science; Extraction (chemistry); Process (computing); Machine learning; Scale (ratio); Artificial intelligence; Information extraction; Limiting; Supercritical fluid extraction; Yield (engineering); Process engineering; Data mining; Chemistry; Engineering; Materials science; Drug discovery; Chromatography; Mechanical engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001205594,0.001392653,0.0007871099,0.001673289,0.0004009515,0.001019448,0.000824298,0.001315301,0.0009158624],"category_scores_gemma":[0.002810709,0.0003589227,0.001243234,0.001710562,0.0005296678,0.001058801,0.000580778,0.000949806,0.00104531],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001342087,"about_ca_system_score_gemma":0.0008107561,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005621015,"about_ca_topic_score_gemma":0.008960322,"domain_scores_codex":[0.9993553,0.00008159034,0.00004257117,0.0002628805,0.0001994699,0.00005827919],"domain_scores_gemma":[0.9987237,0.0006369987,0.0001750643,0.0002024869,0.0002235069,0.00003831353],"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":[0.0007219803,0.0006171862,0.03078877,0.0008105051,0.0002604532,0.0002393047,0.0000528432,0.7626437,0.1103436,0.002586385,0.01185567,0.0790795],"study_design_scores_gemma":[0.00003325252,0.0000941303,0.01205987,0.00001644682,0.00003936168,0.00006722879,0.00001981364,0.8832847,0.0937526,0.002889976,0.007699364,0.00004317296],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7201338,0.00307544,0.2114232,0.0008923485,0.0001316685,0.0001800962,0.05175343,0.00791723,0.004492741],"genre_scores_gemma":[0.7856123,0.001187792,0.1272653,0.0001906466,0.00005570729,0.0002385995,0.08239955,0.0004717525,0.002578296],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005621015,"threshold_uncertainty_score":0.01117659,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03174808772752181,"score_gpt":0.2636799409993386,"score_spread":0.2319318532718168,"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."}}