{"id":"W4306765005","doi":"10.26434/chemrxiv-2022-fdh5d","title":"MLRNet: Combining physics-motivated potential model with neural network for intermolecular potential energy surface construction","year":2022,"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":"","funders":"University of Waterloo; National Natural Science Foundation of China","keywords":"Extrapolation; Artificial neural network; Range (aeronautics); Function (biology); Benchmark (surveying); Statistical physics; Representation (politics); Physics; Computer science; Applied mathematics; Algorithm; Mathematics; Artificial intelligence; Mathematical analysis; Engineering; Aerospace engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008305403,0.0006658359,0.0007854344,0.00006446,0.000667206,0.0005770251,0.001331252,0.0002706908,0.0006411931],"category_scores_gemma":[0.00005959481,0.0006499243,0.0002472461,0.0002510751,0.0004999049,0.0002203988,0.001716629,0.0006793951,0.000009044922],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001690292,"about_ca_system_score_gemma":0.0003122611,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001872155,"about_ca_topic_score_gemma":0.000003521919,"domain_scores_codex":[0.9957966,0.0003440572,0.0006482737,0.001538303,0.0007588079,0.000914],"domain_scores_gemma":[0.9976788,0.00006477071,0.0008955847,0.0009457959,0.0002435154,0.0001715356],"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":[0.0002158262,0.00003836369,0.00006808411,0.0000919251,0.00002635925,0.00001846234,0.0000706236,0.6383334,0.359892,0.0008544752,0.0003028467,0.00008768535],"study_design_scores_gemma":[0.0007930146,0.000165429,0.00005279234,0.0001126884,0.0001218506,0.00005426824,0.00004301021,0.8959883,0.0949494,0.006883866,0.00009002788,0.0007453559],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6142507,0.00005108976,0.3818768,0.0001301981,0.002804033,0.0003947386,0.00004282192,0.0002941422,0.0001554716],"genre_scores_gemma":[0.9118567,0.000006993507,0.08630861,0.0001780381,0.0006339027,0.0001587501,0.0004375723,0.0001300808,0.0002893865],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2976059,"threshold_uncertainty_score":0.9995952,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0114384924116789,"score_gpt":0.2358234543279317,"score_spread":0.2243849619162528,"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."}}