{"id":"W4386743595","doi":"10.26434/chemrxiv-2023-v9841","title":"DELFI: A computer oracle for recommending the best density functional for excited states calculations","year":2023,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Canada First Research Excellence Fund; Natural Resources Canada; University of Toronto; Alliance de recherche numérique du Canada; Government of Ontario","keywords":"Oracle; Density functional theory; Excited state; Computer science; Inference; Estimator; Manifold (fluid mechanics); Ranking (information retrieval); Theoretical computer science; Algorithm; Statistical physics; Artificial intelligence; Computational chemistry; Mathematics; Chemistry; Quantum mechanics; Physics","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":[0.002050901,0.0003046,0.0003766008,0.0001017876,0.0008472792,0.0005672293,0.0007153488,0.000190645,0.0001941234],"category_scores_gemma":[0.0005967295,0.0002359554,0.000199066,0.0001687385,0.000190026,0.0001136858,0.0008337834,0.0002568233,0.000188837],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001276409,"about_ca_system_score_gemma":0.0001333137,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001842334,"about_ca_topic_score_gemma":0.00005906607,"domain_scores_codex":[0.997762,0.0001246637,0.0004866455,0.0008346932,0.0003002733,0.0004917585],"domain_scores_gemma":[0.9970898,0.001436523,0.0003892611,0.0006331783,0.0003598343,0.00009140452],"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":[0.000380203,0.0003164827,0.005080106,0.001797863,0.0001598446,0.000006560007,0.001902588,0.5996128,0.2568993,0.004848318,0.1271416,0.001854333],"study_design_scores_gemma":[0.0006792061,0.000103604,0.006971254,0.0002524497,0.000136092,0.00001082726,0.000146778,0.9196959,0.03234113,0.02550188,0.01342086,0.0007400453],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4227594,0.00001884965,0.5675911,0.003293009,0.004691897,0.001169639,0.0001435757,0.0003085205,0.00002404999],"genre_scores_gemma":[0.7053174,0.00003031067,0.2801787,0.001357303,0.004241118,0.00326129,0.002158933,0.0002470448,0.003207888],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.3200831,"threshold_uncertainty_score":0.9621982,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09240764828611062,"score_gpt":0.3300769762529266,"score_spread":0.237669327966816,"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."}}