{"id":"W4415431826","doi":"10.1021/acs.jctc.5c01333","title":"Capturing Electron Correlation with Machine Learning through a Data-Driven CASPT2 Framework","year":2025,"lang":"en","type":"article","venue":"Journal of Chemical Theory and Computation","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dairy Farmers of Ontario; University of Toronto","funders":"Division of Chemistry","keywords":"Electronic correlation; Correlation; Perturbation (astronomy); Complete active space; Perturbation theory (quantum mechanics); Set (abstract data type); Space (punctuation); Parameter space","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":[],"consensus_categories":[],"category_scores_codex":[0.001362023,0.0001024577,0.000201432,0.0000528579,0.00011357,0.0001227131,0.0002579692,0.00006158023,0.00004013728],"category_scores_gemma":[0.0006075627,0.00007520374,0.00001927839,0.0001520828,0.0001077207,0.0004469519,0.0001073911,0.0003698361,0.000003584187],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000349907,"about_ca_system_score_gemma":0.00005425823,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008508556,"about_ca_topic_score_gemma":3.927581e-7,"domain_scores_codex":[0.9987999,0.0003276885,0.000312393,0.0001923165,0.000226319,0.000141444],"domain_scores_gemma":[0.9987502,0.0006439908,0.0003606112,0.0001128897,0.00009576216,0.00003662483],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001457952,0.00007301144,0.001759371,0.0001054761,0.00003770914,0.0000210496,0.001737749,0.2059523,0.7463825,0.03923947,0.00005318302,0.003180189],"study_design_scores_gemma":[0.001559856,0.0005632506,0.001203195,0.001056048,0.0002137084,0.0005091992,0.0003619592,0.3564743,0.2485656,0.3884982,0.000551242,0.0004434041],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6023179,0.0001629208,0.3970016,0.0001485495,0.0001319771,0.00003695082,0.000001114302,0.00001796072,0.000181009],"genre_scores_gemma":[0.962322,0.00001131123,0.03742027,0.0001103255,0.00009096163,7.513629e-7,0.000008164026,0.00000654208,0.00002969789],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4978169,"threshold_uncertainty_score":0.306672,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01151249226718793,"score_gpt":0.2942273946020841,"score_spread":0.2827149023348962,"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."}}