{"id":"W2963501253","doi":"10.48550/arxiv.1907.08717","title":"Interpolation and extrapolation of global potential energy surfaces for polyatomic systems by Gaussian processes with composite kernels","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Extrapolation; Kriging; Gaussian process; Gaussian; Interpolation (computer graphics); Kernel (algebra); Potential energy; Energy (signal processing); Range (aeronautics); Mathematics; Computer science; Mathematical optimization; Applied mathematics; Algorithm; Artificial intelligence; Statistics; Physics; Materials science","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000313821,0.0002825583,0.0004224838,0.00007807252,0.0001227453,0.0002141983,0.0005054328,0.0001976142,0.00002632288],"category_scores_gemma":[0.00003329567,0.0002688408,0.00004622883,0.0002110441,0.0002407874,0.0003600956,0.0003106881,0.00009273649,0.000004702672],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000113731,"about_ca_system_score_gemma":0.0002493172,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001901079,"about_ca_topic_score_gemma":0.00008794014,"domain_scores_codex":[0.9983208,0.0001730044,0.0002864942,0.0008110923,0.0001401763,0.0002684531],"domain_scores_gemma":[0.9985042,0.00009970164,0.0007336171,0.00035448,0.0002214629,0.00008654189],"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":[0.0006448176,0.00006421928,0.04112432,0.001603776,0.00004231069,0.000005908437,0.0001263132,0.7152929,0.2322274,0.008788901,0.0000641027,0.00001492932],"study_design_scores_gemma":[0.001002081,0.000286484,0.005886992,0.0007096496,0.0001879662,0.0000184443,0.0001839244,0.9769383,0.01179091,0.002308704,0.0000634332,0.0006231238],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6953299,0.0001521226,0.3032674,0.00001465208,0.0003993534,0.0003221779,0.000306815,0.00005785174,0.0001496591],"genre_scores_gemma":[0.9985666,0.00004192181,0.0009697625,0.000008670221,0.0000404405,0.000002379504,0.00007969555,0.00001907331,0.0002714038],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3032367,"threshold_uncertainty_score":0.9999764,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01767670260300219,"score_gpt":0.1882167265493725,"score_spread":0.1705400239463703,"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."}}