{"id":"W4413860404","doi":"10.1016/j.chemolab.2025.105511","title":"Sharpness-aware minimization with physics-informed regularizations for predicting semiconductor material properties in molecular dynamics","year":2025,"lang":"en","type":"article","venue":"Chemometrics and Intelligent Laboratory Systems","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Institute for Information and Communications Technology Promotion; Information Technology Research Centre; Ministry of Science and ICT, South Korea; National Research Foundation of Korea","keywords":"Molecular dynamics; Dynamics (music); Statistical physics; Minification; Semiconductor; Computer science; Physics; Materials science; Mathematics; Quantum mechanics; Mathematical optimization","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":[],"consensus_categories":[],"category_scores_codex":[0.0005795443,0.0002166517,0.0003336699,0.0004107046,0.0001781605,0.0005397452,0.0002814319,0.0001187043,0.00001712064],"category_scores_gemma":[0.0006392341,0.0001775646,0.00002095575,0.001845212,0.0001291404,0.0003644084,0.00009447102,0.00008175344,0.000002736826],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002828277,"about_ca_system_score_gemma":0.0003811665,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006378697,"about_ca_topic_score_gemma":0.00001170157,"domain_scores_codex":[0.9983822,0.00007822478,0.000521,0.0004371255,0.0002705438,0.0003108896],"domain_scores_gemma":[0.9988006,0.0001013074,0.0002571029,0.0002754169,0.0005012043,0.00006438912],"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":[0.0001509999,0.000152192,0.0247661,0.003203798,0.00002839316,0.000004808314,0.001127842,0.04128075,0.9194588,0.009256037,0.0001436247,0.0004266304],"study_design_scores_gemma":[0.0004591727,0.0001495706,0.0003462426,0.0006478337,0.00003184655,0.00000312662,0.001127473,0.3677454,0.6280937,0.00008279979,0.0009443547,0.0003684425],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8886741,0.0002110276,0.108589,0.00005648968,0.00114678,0.0008911472,0.0002342282,0.00009211584,0.0001051732],"genre_scores_gemma":[0.9974221,0.00002282982,0.001755145,0.00005864258,0.00008355361,0.0002141498,0.00008851028,0.00002749759,0.0003275649],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3264647,"threshold_uncertainty_score":0.7240876,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01433154802904162,"score_gpt":0.2499681112843469,"score_spread":0.2356365632553053,"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."}}