{"id":"W4407010955","doi":"10.1126/sciadv.adt7769","title":"Adapting hybrid density functionals with machine learning","year":2025,"lang":"en","type":"article","venue":"Science Advances","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"Structural Genomics Consortium; Vector Institute; University of Toronto","funders":"","keywords":"Hybrid functional; Dipole; Density functional theory; Benchmark (surveying); Overhead (engineering); Statistical physics; Constraint (computer-aided design); Quantum; Delocalized electron; Physics; Computer science; Materials science; Molecular physics; Quantum mechanics; Mathematics","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.00292279,0.0002128266,0.0002506534,0.0002646408,0.001604702,0.0004426379,0.0009625105,0.0000222406,0.0005014905],"category_scores_gemma":[0.0011531,0.0001577151,0.00003132286,0.001270928,0.001564764,0.001692275,0.0003214976,0.0002265541,0.0001983517],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001023383,"about_ca_system_score_gemma":0.0003754799,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001067997,"about_ca_topic_score_gemma":0.00005788979,"domain_scores_codex":[0.9971125,0.0001339423,0.0002961307,0.0008762758,0.0009217811,0.000659439],"domain_scores_gemma":[0.9987752,0.0002185759,0.0002217531,0.0003848098,0.0002809076,0.0001187314],"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":[0.00006123911,0.0000252849,0.02401309,0.00003128786,0.000001759066,0.00001054175,0.0000791599,0.03884678,0.9290959,0.002028007,0.0000299296,0.005777008],"study_design_scores_gemma":[0.0003915193,0.0002169178,0.01323221,0.0001806132,0.00001659863,0.00006715266,0.0002472176,0.01380164,0.9505265,0.002643154,0.01822283,0.0004536009],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9541531,0.0004959715,0.03531829,0.0005821674,0.001202076,0.000176752,0.000004774273,0.0003399019,0.007726953],"genre_scores_gemma":[0.9690434,0.00001149242,0.02851711,0.000338596,0.00006365134,0.00001782812,0.000002129635,0.000009249726,0.001996597],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02504514,"threshold_uncertainty_score":0.9996951,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007504357070883157,"score_gpt":0.2663137163954359,"score_spread":0.2588093593245528,"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."}}