{"id":"W4235160088","doi":"10.26434/chemrxiv.6189617.v2","title":"A Bayesian Approach to Predict Solubility Parameters","year":2018,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Canadian Institute for Advanced Research","funders":"Bayerisches Staatsministerium für Umwelt und Verbraucherschutz; Solar Technologies go Hybrid; Deutsche Forschungsgemeinschaft; Departamento Administrativo de Ciencia, Tecnología e Innovación (COLCIENCIAS); U.S. Department of Energy","keywords":"Solubility; Bayesian probability; Computer science; Miscibility; Flexibility (engineering); Toolbox; Probabilistic logic; Set (abstract data type); Consistency (knowledge bases); Biological system; Algorithm; Artificial intelligence; Chemistry; Polymer; Mathematics; Organic chemistry","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":[0.004144927,0.00108857,0.00148513,0.001946271,0.0008236832,0.001722994,0.002433526,0.002022629,0.003422821],"category_scores_gemma":[0.01155656,0.001070802,0.00144355,0.001431275,0.00160849,0.002898513,0.001583843,0.002712189,0.0009881284],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001363835,"about_ca_system_score_gemma":0.002064697,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006744992,"about_ca_topic_score_gemma":0.005331603,"domain_scores_codex":[0.9983576,0.0006666296,0.0000803256,0.0003317202,0.0004417485,0.0001218989],"domain_scores_gemma":[0.9955199,0.003127494,0.000359178,0.0003258874,0.0005454005,0.0001220679],"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":[0.00007371049,0.00006084263,0.001615084,0.00009350006,0.00007232687,0.00007979907,0.00006757453,0.8969127,0.001571383,0.06580383,0.001803429,0.03184586],"study_design_scores_gemma":[0.000007417462,0.00001183758,0.0001623526,0.00001087063,0.000009101873,0.00001681779,0.000004399729,0.9704583,0.0004229407,0.02806527,0.0008180576,0.00001260492],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01280305,0.0003553239,0.9837141,0.0004027108,0.00003477712,0.00004978995,0.0004153397,0.0003612594,0.001863649],"genre_scores_gemma":[0.6110147,0.001623542,0.3759922,0.0006899639,0.0003830298,0.0006034073,0.002419596,0.0003995643,0.006873917],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006744992,"threshold_uncertainty_score":0.02192068,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02712077660177568,"score_gpt":0.2757814230263786,"score_spread":0.248660646424603,"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."}}