{"id":"W4411176514","doi":"10.1021/acs.jctc.5c00414","title":"Multiproperty Deep Learning of the Correlation Energy of Electrons and the Physicochemical Properties of Molecules","year":2025,"lang":"en","type":"article","venue":"Journal of Chemical Theory and Computation","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"Alliance de recherche numérique du Canada; China Scholarship Council; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China; Canada Research Chairs","keywords":"Chemical physics; Correlation; Electron; Molecule; Energy (signal processing); Computer science; Data science; Nanotechnology; Chemistry; Materials science; Physics; Nuclear physics; Mathematics; Quantum mechanics","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":[0.001031232,0.00005818221,0.0002006355,0.00002684038,0.0000471386,0.00001472853,0.0001468843,0.00003200849,0.000004225265],"category_scores_gemma":[0.000681486,0.00002802248,0.00004583925,0.00009839691,0.000594315,0.00007315032,0.00007417764,0.0001093492,5.025236e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007655199,"about_ca_system_score_gemma":0.00002987667,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007901766,"about_ca_topic_score_gemma":9.574065e-8,"domain_scores_codex":[0.9988974,0.0004522559,0.0003510883,0.00007064675,0.0001677712,0.00006083647],"domain_scores_gemma":[0.998886,0.0003876471,0.00050427,0.00005421646,0.0001551494,0.00001273467],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005452101,0.00002416599,0.0001277295,0.00005575393,0.000008975329,4.777963e-8,0.0005211208,0.007537012,0.9676024,0.02172079,0.000001791501,0.001855019],"study_design_scores_gemma":[0.0004273134,0.0000373764,0.0002914749,0.0001510359,0.00003051726,0.000007497995,0.0001083879,0.05360965,0.9212641,0.02404154,0.000003232396,0.00002785619],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9501437,0.0004579609,0.04909665,0.0001207961,0.00006031586,0.0000415953,2.860442e-7,0.000002580883,0.0000761142],"genre_scores_gemma":[0.9992311,0.00001782881,0.0006926353,0.00002636069,0.00001632679,9.305943e-7,2.092981e-7,0.000002498947,0.00001211994],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04908739,"threshold_uncertainty_score":0.2189778,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004675662213398228,"score_gpt":0.2221492747348154,"score_spread":0.2174736125214172,"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."}}