{"id":"W4387229410","doi":"10.1007/s00214-023-03047-z","title":"Something for nothing: improved solvation free energy prediction with $${\\Delta }$$-learning","year":2023,"lang":"en","type":"article","venue":"Theoretical Chemistry Accounts","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University","funders":"Shared Hierarchical Academic Research Computing Network; Canada Research Chairs","keywords":"Solvation; Linear regression; Gaussian; Solubility; Gaussian process; Regression; Kriging; Chemistry; Statistical physics; Artificial intelligence; Computer science; Machine learning; Computational chemistry; Mathematics; Molecule; Physics; Statistics; Physical chemistry; Organic chemistry","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001085562,0.0001970738,0.0001844207,0.00007040268,0.0002474294,0.0002894122,0.0008570655,0.0001353524,0.00003089045],"category_scores_gemma":[0.001156704,0.0001792843,0.00007304284,0.000638996,0.0001667646,0.0006467961,0.0003818747,0.0002545881,0.000006842054],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008877509,"about_ca_system_score_gemma":0.0001231696,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005359687,"about_ca_topic_score_gemma":3.553004e-7,"domain_scores_codex":[0.9982475,0.00006708472,0.0002805517,0.0005459536,0.0004627267,0.0003962028],"domain_scores_gemma":[0.9978852,0.001157723,0.0001260556,0.0005015708,0.0002264867,0.0001030136],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001988257,0.00007099052,0.0001383825,0.0001877103,0.00008060667,0.000006653282,0.001015432,0.04183378,0.09301991,0.8502015,0.000417285,0.01282893],"study_design_scores_gemma":[0.0005299957,0.00004831044,0.0001251572,0.00003550001,0.0000127171,0.000008859585,0.00004271544,0.7532889,0.04573276,0.1994268,0.0005673583,0.0001809058],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06556412,0.000007792535,0.9300196,0.001344424,0.0001487407,0.0001244133,0.00002547634,0.000606948,0.002158532],"genre_scores_gemma":[0.9572898,0.000003928912,0.04173001,0.0001998294,0.0002998728,0.00009911536,0.000113055,0.00003245888,0.0002319311],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8917257,"threshold_uncertainty_score":0.7311,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0102707934810247,"score_gpt":0.255692505584878,"score_spread":0.2454217121038533,"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."}}