{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00128854,0.0006173057,0.0005918338,0.001241369,0.0005462124,0.0005466435,0.002207785,0.0008923222,0.004224752],"category_scores_gemma":[0.004299984,0.00043974,0.0005499427,0.0009769659,0.0003815102,0.0009822925,0.001075656,0.001084143,0.000854901],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000628819,"about_ca_system_score_gemma":0.0006796365,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008571143,"about_ca_topic_score_gemma":0.001434967,"domain_scores_codex":[0.9995432,0.0001599948,0.00002797699,0.00006732871,0.0001693296,0.00003224378],"domain_scores_gemma":[0.9984766,0.0005630913,0.00006853285,0.0005283774,0.0003243101,0.00003905625],"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":[0.0003907493,0.000421583,0.007244884,0.0006608795,0.0001358507,0.000317826,0.0001743253,0.7325107,0.05371244,0.05002765,0.01519874,0.1392044],"study_design_scores_gemma":[0.0000415087,0.00006447185,0.0005375128,0.0000138295,0.000005362665,0.00003651885,0.00002641377,0.9616107,0.02472617,0.009572132,0.003354366,0.00001107695],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5828655,0.0005285947,0.3843815,0.0006412795,0.0001600347,0.0003500798,0.00908666,0.008196565,0.01378976],"genre_scores_gemma":[0.7690436,0.0001536044,0.2151199,0.00009404346,0.00002392189,0.0004731807,0.01353149,0.0006867482,0.0008734747],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004224752,"threshold_uncertainty_score":0.01413321,"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."}}