{"id":"W4411116460","doi":"10.1038/s41524-025-01669-4","title":"Automated generation of structure datasets for machine learning potentials and alloys","year":2025,"lang":"en","type":"article","venue":"npj Computational Materials","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Pacific Institute for Climate Solutions","funders":"Deutsche Forschungsgemeinschaft","keywords":"Computer science; Artificial intelligence; Machine learning","routes":{"ca_aff":true,"ca_fund":false,"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":[],"consensus_categories":[],"category_scores_codex":[0.001042692,0.0001942591,0.0003866711,0.0001573628,0.0002796417,0.0002605487,0.0002654255,0.0000932616,0.0006932093],"category_scores_gemma":[0.0005530759,0.0001768815,0.00002823644,0.0001449826,0.0001427642,0.0002329881,0.0001713676,0.00005129311,0.00001002065],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002598647,"about_ca_system_score_gemma":0.00009120518,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001067569,"about_ca_topic_score_gemma":0.000008244341,"domain_scores_codex":[0.9980872,0.0003265319,0.0006205178,0.0004434173,0.0002879185,0.0002343861],"domain_scores_gemma":[0.9989365,0.0002773058,0.0003674715,0.0001769347,0.0001954839,0.00004626668],"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":[0.00005801142,0.00001837606,0.0001658414,0.0001730328,0.00001158958,6.868486e-7,0.00005107818,0.09112713,0.9025297,0.004826369,0.0008895832,0.0001486588],"study_design_scores_gemma":[0.0007472605,0.00009444244,0.004737915,0.00006607459,0.00004052676,0.00001200919,0.000009293941,0.2502169,0.7360873,0.007036532,0.000744078,0.0002076911],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9586357,0.00008176077,0.03683086,0.0002817096,0.001092113,0.0004674345,0.002357889,0.0002280069,0.00002454664],"genre_scores_gemma":[0.9254318,0.000004157984,0.07224808,0.0001609489,0.0001061137,0.00002592592,0.001945823,0.00001541677,0.00006166224],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1664423,"threshold_uncertainty_score":0.7590156,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01445675374799952,"score_gpt":0.295425338163994,"score_spread":0.2809685844159944,"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."}}