{"id":"W1998860313","doi":"10.1021/jp055253z","title":"A Nested Molecule-Independent Neural Network Approach for High-Quality Potential Fits","year":2005,"lang":"en","type":"article","venue":"The Journal of Physical Chemistry A","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":196,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Mean squared error; Simple (philosophy); Artificial neural network; Function (biology); Basis (linear algebra); Chemistry; Surface (topology); Potential energy; Energy (signal processing); Algorithm; Square (algebra); Potential energy surface; Statistical physics; Molecule; Computer science; Mathematics; Physics; Artificial intelligence; Quantum mechanics; Statistics; Geometry","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":[],"consensus_categories":[],"category_scores_codex":[0.001909624,0.0001884628,0.0003636112,0.000009831759,0.0002159371,0.0001160912,0.0009634985,0.00005979276,0.0001399238],"category_scores_gemma":[0.0002437687,0.0001193861,0.0001617271,0.0001243992,0.0001730492,0.0002033155,0.0001507146,0.0003117913,0.00001209915],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005408816,"about_ca_system_score_gemma":0.00006531491,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001185348,"about_ca_topic_score_gemma":2.885893e-7,"domain_scores_codex":[0.9979785,0.000264993,0.0005004527,0.000206476,0.0006437164,0.0004058306],"domain_scores_gemma":[0.998472,0.0002329419,0.0006608415,0.0003127804,0.0001846032,0.0001367943],"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":[0.000187737,0.00009326403,0.000002889567,0.00003321192,0.000005823123,0.000001545854,0.00008838068,0.3857717,0.6134706,0.00006094193,0.0001921152,0.00009184046],"study_design_scores_gemma":[0.0008333967,0.0001442116,0.000585188,0.00002431632,0.00008290137,0.0001728821,0.00004936553,0.1656335,0.8313722,0.0007884902,0.00009303668,0.0002205771],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.965052,0.00003307695,0.03378118,0.0006106624,0.0001136144,0.0001382757,0.00001054634,0.0000284556,0.0002322035],"genre_scores_gemma":[0.9908091,0.000001011703,0.005413439,0.0001590103,0.003427793,0.000006616542,0.000003608465,0.00001680607,0.0001625441],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2201382,"threshold_uncertainty_score":0.4868423,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01316314854971842,"score_gpt":0.2817688155195605,"score_spread":0.2686056669698421,"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."}}