{"id":"W4408858459","doi":"10.2139/ssrn.5195404","title":"Physics-Guided Transfer Learning for Bayesian Optimization of Chemical Port-Hamiltonian Systems","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Hamiltonian (control theory); Port (circuit theory); Bayesian probability; Bayesian optimization; Physics; Computer science; Mathematical optimization; Engineering; Mathematics; Artificial intelligence; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.005282457,0.0004464689,0.0008687336,0.0001896923,0.0002630948,0.0003171955,0.001213433,0.000376886,0.00009645897],"category_scores_gemma":[0.0004106895,0.0004228848,0.0003198805,0.000215431,0.0001484373,0.0001907788,0.0002457739,0.002590877,0.000005271263],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009034274,"about_ca_system_score_gemma":0.004502323,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002099366,"about_ca_topic_score_gemma":0.00001274254,"domain_scores_codex":[0.9948778,0.0004561507,0.001152939,0.0007211337,0.0006523066,0.002139627],"domain_scores_gemma":[0.9980982,0.00015978,0.0007214486,0.0004430611,0.0004631584,0.0001143466],"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":[0.00007833098,0.00005103493,0.0001342738,0.0004162767,0.00005833805,9.519811e-7,0.0002027963,0.8637077,0.1184964,0.01639527,0.0000302314,0.0004284246],"study_design_scores_gemma":[0.001864285,0.0005215158,0.00002580832,0.001363602,0.0004158325,0.0002764125,0.0005013153,0.8595225,0.08027927,0.05363246,0.0003581233,0.001238823],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1289384,0.000626964,0.8671501,0.0001962107,0.001798702,0.0007115515,0.00004058219,0.0001141169,0.0004234136],"genre_scores_gemma":[0.9852394,0.0004840981,0.01188319,0.00002843269,0.000835632,0.00009009741,0.0000735155,0.00006404647,0.001301577],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.856301,"threshold_uncertainty_score":0.9998223,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01143027647369294,"score_gpt":0.2720658125267212,"score_spread":0.2606355360530283,"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."}}