{"id":"W4387899421","doi":"10.1088/2632-2153/ad0652","title":"Neural network Gaussian processes as efficient models of potential energy surfaces for polyatomic molecules","year":2023,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Gaussian process; Kernel (algebra); Polyatomic ion; Computer science; Gaussian; Function (biology); Gaussian function; Artificial neural network; Kriging; Generalization; Mathematical optimization; Algorithm; Artificial intelligence; Mathematics; Machine learning; Statistical physics; Computational chemistry; Physics; Chemistry; Molecule; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001337172,0.0005617916,0.001033394,0.0009137201,0.0004430157,0.001081538,0.002104915,0.00144102,0.002378289],"category_scores_gemma":[0.003039693,0.0004999581,0.001051837,0.000815732,0.001561969,0.002350654,0.001036637,0.001781832,0.0003884342],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001221533,"about_ca_system_score_gemma":0.0007797891,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004212715,"about_ca_topic_score_gemma":0.003501591,"domain_scores_codex":[0.9996473,0.0001437013,0.00001402117,0.00005687008,0.00008985158,0.00004826345],"domain_scores_gemma":[0.9988463,0.0006799639,0.0001090207,0.000131613,0.0001600526,0.00007305547],"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":[0.00001558369,0.000018263,0.0002547069,0.00001956818,0.00001325942,0.00001962151,0.00002000748,0.974342,0.0004388506,0.02253208,0.0001626546,0.002163466],"study_design_scores_gemma":[0.000001131155,0.000002374397,0.00002837847,0.000001560441,8.437752e-7,0.000001533359,0.000001433802,0.9948089,0.00005418485,0.005051877,0.00004642475,0.000001447807],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1637467,0.0005300624,0.8292814,0.0007078167,0.00005987507,0.0000694712,0.0002023617,0.0003959012,0.005006348],"genre_scores_gemma":[0.9393743,0.0003853526,0.05533628,0.0001593562,0.00004196032,0.0001898649,0.0002412435,0.0001599301,0.004111631],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004212715,"threshold_uncertainty_score":0.008862913,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00728694705171877,"score_gpt":0.2471794843492509,"score_spread":0.2398925372975321,"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."}}