{"id":"W4409308497","doi":"10.26434/chemrxiv-2025-3h5p5","title":"Constructing Accurate Potential Energy Surfaces with Limited High-Level Data Using Atom-Centered Potentials and Density Functional Theory","year":2025,"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":"University of British Columbia","funders":"Agencia Estatal de Investigación; Alliance de recherche numérique du Canada; Natural Sciences and Engineering Research Council of Canada; University of British Columbia; Ministerio de Ciencia e Innovación; Compute Canada","keywords":"Density functional theory; Atom (system on chip); Energy (signal processing); Physics; Atomic physics; Computer science; Quantum mechanics; Embedded system","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":[0.002142198,0.0006048137,0.000807043,0.0001938051,0.000541998,0.0009653601,0.001489195,0.0003581798,0.0006540813],"category_scores_gemma":[0.0004072509,0.0005243346,0.00006418084,0.0002301948,0.0008423932,0.0004884909,0.005583494,0.0004737353,0.00001117913],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001174405,"about_ca_system_score_gemma":0.0005723395,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001074963,"about_ca_topic_score_gemma":0.00009046092,"domain_scores_codex":[0.995434,0.000689794,0.0006917253,0.001900859,0.0006700156,0.0006135622],"domain_scores_gemma":[0.996653,0.0003048588,0.0009067126,0.001621707,0.0003427295,0.0001709694],"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":[0.0006715248,0.00009541042,0.004694131,0.0006014534,0.0001833658,0.00008206933,0.000105926,0.02888099,0.9579866,0.00565276,0.0002310912,0.0008146666],"study_design_scores_gemma":[0.00297652,0.00009235588,0.02043173,0.002251138,0.00112358,0.0006918104,0.0005938885,0.2149968,0.7404308,0.01319686,0.0002722873,0.002942236],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8235245,0.0001481871,0.1726057,0.000146241,0.002636028,0.0002167372,0.0004083582,0.0002006547,0.0001136358],"genre_scores_gemma":[0.9380413,0.0000304287,0.06051055,0.0001381014,0.0003246305,0.00001010187,0.0005839071,0.00003850245,0.0003224674],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2175558,"threshold_uncertainty_score":0.9997208,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06469069335511336,"score_gpt":0.2804520537348001,"score_spread":0.2157613603796867,"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."}}