{"id":"W4252056807","doi":"10.26434/chemrxiv.13551629.v2","title":"Modeling LiF and FLiBe Molten Salts with Robust Neural Network Interatomic Potentials","year":2021,"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":"Natural Sciences and Engineering Research Council of Canada; Office of Nuclear Energy; Nuclear Energy University Program; U.S. Department of Energy","keywords":"Molecular dynamics; Melting point; Materials science; Lithium (medication); Chemical physics; Interatomic potential; Atom (system on chip); Work (physics); Absorption (acoustics); Molten salt; Thermodynamics; Chemistry; Computational chemistry","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","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001227983,0.0005803236,0.0008305522,0.00008487049,0.0002868848,0.001645574,0.000967304,0.0003111795,0.0005544176],"category_scores_gemma":[0.0001780921,0.0004920592,0.0001019053,0.0001917457,0.0002601596,0.0003072073,0.002293139,0.0007257054,0.00005191758],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007475493,"about_ca_system_score_gemma":0.0002263019,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002741405,"about_ca_topic_score_gemma":0.00004959559,"domain_scores_codex":[0.9962383,0.0003099871,0.0006408016,0.001518329,0.0005166157,0.00077597],"domain_scores_gemma":[0.9981004,0.0000780547,0.0003567104,0.001013887,0.0002062589,0.0002446815],"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":[0.00005012274,0.00002082885,0.0003390856,0.0002459525,0.0000155019,0.00006108476,0.0003340367,0.8726371,0.1260948,0.00002369851,0.0001178878,0.00005990665],"study_design_scores_gemma":[0.0003076953,0.00004534849,0.0003539282,0.0008971689,0.0000675099,0.0001115205,0.00008694764,0.979895,0.01718895,0.0003257359,0.00002236089,0.0006978365],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9725165,0.0007712035,0.02361145,0.000359693,0.001785834,0.0003658214,0.000006389043,0.0002979224,0.0002851732],"genre_scores_gemma":[0.9566345,0.00006620348,0.04185328,0.000299011,0.0007806299,0.00006227554,0.00006734041,0.00008597522,0.0001508046],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1089058,"threshold_uncertainty_score":0.9997531,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01956359525752548,"score_gpt":0.2432499642665238,"score_spread":0.2236863690089983,"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."}}