{"id":"W2071161986","doi":"10.1002/cjce.20212","title":"A neural network approach to predict activity coefficients","year":2009,"lang":"en","type":"article","venue":"The Canadian Journal of Chemical Engineering","topic":"Process Optimization and Integration","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"UNIFAC; Artificial neural network; Group contribution method; Binary number; Activity coefficient; Representation (politics); Computer science; Mathematics; Phase (matter); Artificial intelligence; Phase equilibrium; Chemistry; Organic chemistry; Arithmetic","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001170147,0.00009221564,0.0001151491,0.00007459673,0.0000353839,0.00005476812,0.0002034871,0.00004894642,0.000006272122],"category_scores_gemma":[0.00006416866,0.00007189074,0.00004346182,0.0002622807,0.000009667334,0.0001016112,0.000002963665,0.0002729011,0.000001631515],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001362336,"about_ca_system_score_gemma":0.00005827081,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002199884,"about_ca_topic_score_gemma":0.00000935172,"domain_scores_codex":[0.999458,0.000004689742,0.0001500652,0.00004750265,0.0001115436,0.0002282014],"domain_scores_gemma":[0.9994943,0.0000137828,0.0000226225,0.00007857555,0.00005760012,0.000333095],"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":[0.000003387896,0.000003173154,0.000005843806,0.000004735898,0.000008272565,0.000001323959,0.000087213,0.9919395,0.004591091,0.0001476317,0.001578002,0.001629815],"study_design_scores_gemma":[0.0001063326,0.00002055601,0.0001696935,0.00002817128,0.000008613668,0.0000411893,0.000002856506,0.9901913,0.008427278,0.00001924604,0.0008942056,0.00009055062],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6693298,0.0004231283,0.3244755,0.00076115,0.0007037717,0.0001887841,0.000005855645,0.0001209536,0.003991102],"genre_scores_gemma":[0.9980376,9.674976e-7,0.001554122,0.0001436967,0.0002409686,0.000001246898,0.000001307116,0.00001199309,0.000008082782],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3287078,"threshold_uncertainty_score":0.2931619,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007308879783958363,"score_gpt":0.1795097424207537,"score_spread":0.1722008626367953,"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."}}