{"id":"W4408873551","doi":"10.1063/5.0263653","title":"Applying the active learning strategy to the construction of full-dimensional neural network potential energy surfaces: Critical tests in H2O–He spectroscopic calculation","year":2025,"lang":"en","type":"article","venue":"The Journal of Chemical Physics","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"National Natural Science Foundation of China","keywords":"Mean squared error; Artificial neural network; Range (aeronautics); Sampling (signal processing); Dimension (graph theory); Algorithm; Mathematics; Energy (signal processing); Root mean square; Computer science; Mathematical optimization; Statistics; Artificial intelligence; Engineering; Detector","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":[0.001803152,0.0004791152,0.0005750665,0.0003888076,0.00048324,0.0004671757,0.00103885,0.0007390094,0.001317639],"category_scores_gemma":[0.003972772,0.0003562767,0.0004238599,0.0005256352,0.0005578596,0.001401319,0.0007310082,0.0009688543,0.0001411419],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003971461,"about_ca_system_score_gemma":0.0005418119,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00201288,"about_ca_topic_score_gemma":0.001419406,"domain_scores_codex":[0.9996964,0.0001037169,0.0000158358,0.00003719967,0.0001158496,0.00003101862],"domain_scores_gemma":[0.9989171,0.0006652848,0.00004177908,0.000140426,0.0002061894,0.00002921198],"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":[0.0001864556,0.0001328869,0.00166948,0.0002529153,0.00003891413,0.0001386248,0.0001823548,0.9269555,0.01330178,0.01839977,0.0004220189,0.03831938],"study_design_scores_gemma":[0.0000038414,0.00003232892,0.0001342337,0.000004270762,0.000001751848,0.000005538839,0.00001280338,0.9954668,0.003085013,0.001096748,0.0001523464,0.000004252367],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7248206,0.0007422412,0.2664607,0.0004455014,0.00005586756,0.0001062506,0.0001772659,0.0004166223,0.006774994],"genre_scores_gemma":[0.9367883,0.0001864302,0.06227816,0.00003225914,0.000006122465,0.0001034622,0.0001026159,0.00004568912,0.0004568071],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00201288,"threshold_uncertainty_score":0.009536028,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009056949236737171,"score_gpt":0.278528151800484,"score_spread":0.2694712025637468,"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."}}