{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001553093,0.0005070207,0.0006689554,0.0007800218,0.0005211192,0.0005020483,0.001162422,0.0009178852,0.001507145],"category_scores_gemma":[0.007697876,0.0003114461,0.0006225909,0.0004576227,0.001181494,0.001143139,0.000487995,0.001169287,0.0002414256],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001014361,"about_ca_system_score_gemma":0.000754712,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005653139,"about_ca_topic_score_gemma":0.006342683,"domain_scores_codex":[0.9996357,0.0001679558,0.00001223042,0.00007743636,0.00006513219,0.00004144277],"domain_scores_gemma":[0.9959275,0.002850458,0.0002775606,0.0005633408,0.000286565,0.00009447955],"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":[0.00005129748,0.00004313876,0.002002205,0.00004798815,0.00002228642,0.00006197188,0.00003265885,0.9773082,0.001062906,0.01233529,0.000901659,0.006130509],"study_design_scores_gemma":[0.0000022756,0.000006376553,0.0001709802,0.000001934692,0.000001405531,0.000005191458,0.000002485689,0.9944528,0.0002243672,0.00506727,0.00006288553,0.000002038218],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6650813,0.0005315904,0.3282786,0.001145895,0.00009243604,0.00006740371,0.0004954906,0.001158379,0.003148966],"genre_scores_gemma":[0.95765,0.0001019841,0.0405223,0.000105054,0.00002106209,0.00005855101,0.0004795371,0.0001468576,0.0009146267],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005653139,"threshold_uncertainty_score":0.01124048,"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."}}