{"id":"W3181308313","doi":"10.1038/s41598-021-93854-w","title":"Regularized machine learning on molecular graph model explains systematic error in DFT enthalpies","year":2021,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"University of Delaware; U.S. Department of Energy","keywords":"Thermochemistry; Density functional theory; NIST; Computer science; Statistical physics; Graph; Graph theory; Molecule; Thermodynamics; Computational chemistry; Chemistry; Mathematics; Theoretical computer science; Physics; Quantum mechanics","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","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.007297556,0.0003403469,0.0006559403,0.0004337233,0.0005464527,0.001057683,0.000494039,0.0001142674,0.0004936679],"category_scores_gemma":[0.00328416,0.0003006911,0.0001614798,0.001062233,0.0003634818,0.0002900751,0.0003415733,0.0003065589,0.0001432551],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001108366,"about_ca_system_score_gemma":0.0002980219,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006282951,"about_ca_topic_score_gemma":0.00008284004,"domain_scores_codex":[0.9939372,0.0009226989,0.001187934,0.001683618,0.00154471,0.0007238271],"domain_scores_gemma":[0.9971001,0.0001170884,0.0006867358,0.001673398,0.0002362496,0.0001864105],"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":[0.0000119548,0.00008829217,0.0006595919,0.0008012956,0.000004005062,0.001509137,0.0006341137,0.1967885,0.7987537,0.0006326457,0.0001106233,0.000006205608],"study_design_scores_gemma":[0.0004469998,0.00007286575,0.0002224654,0.002518873,0.0000410271,0.0008426949,0.00037422,0.2250871,0.7555851,0.01383603,0.0002483617,0.0007243548],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9869429,0.0002856611,0.005746488,0.0002295068,0.004733339,0.0005463361,0.000005317651,0.0002115119,0.001298872],"genre_scores_gemma":[0.9838194,0.000003526822,0.01107437,0.00009273887,0.00002492361,0.0001036107,0.0000585479,0.00004101703,0.004781883],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04316863,"threshold_uncertainty_score":0.9999793,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01567091199213221,"score_gpt":0.258180193862229,"score_spread":0.2425092818700967,"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."}}