[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-291029-105":59,"doc-detail-291029-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","overcoming-systematic-softening-in-universal-machine-learning-interatomic-potentials-by-fine-tuning","Overcoming systematic softening in universal machine learning interatomic potentials - by fine-tuning","","Machine learning interatomic potentials (MLIPs) enable large-scale atomic simulations, and universal MLIPs (uMLIPs) offer ready-to-use force fields and a basis for downstream refinement. Their extrapolation to out-of-distribution atomic environments remains unclear. This study identifies a consistent potential energy surface softening across M3GNet, CHGNet, and MACE-MP-0, driven by systematic underprediction of PES curvature. Fine-tuning with one additional data point rectifies the issue, supporting data-efficient correction and motivating improved PES sampling in next-generation foundational models.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/overcoming-systematic-softening-in-universal-machine-learning-interatomic-potentials-by-fine-tuning/291029/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/overcoming-systematic-softening-in-universal-machine-learning-interatomic-potentials-by-fine-tuning/291029.png","ImageObject",300,407,{"name":92,"@type":93},"Theodore","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-09-28","2026-09-17",true,{"@type":102,"interactionType":103,"userInteractionCount":24},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What problem does the paper address in universal machine learning interatomic potentials?","Question",{"text":112,"@type":113},"It examines why universal MLIPs struggle to extrapolate reliably to out-of-distribution complex atomic environments, focusing on a consistent potential energy surface softening effect.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"Which uMLIPs show the potential energy surface softening behavior?",{"text":117,"@type":113},"The paper reports PES softening in three uMLIPs: M3GNet, CHGNet, and MACE-MP-0.",{"name":119,"@type":110,"acceptedAnswer":120},"How is the PES softening issue corrected, and what data is required?",{"text":121,"@type":113},"The study shows the issue can be effectively rectified by fine-tuning with a single additional data point, indicating the error is systematic and efficiently correctable.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},291029,1789643226,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":24,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":139,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":129,"read_time":41},7971461740886,"https://ap-avatar.wpscdn.com/davatar_3d24733baf745e90a7e4bdd5f77d97b2","arXiv :2405 .07105v1 [ cond-mat .mtrl-sci ] 11 May 2024  \nOvercoming systematic softening in universal machine learning interatomic potentials  \nby fine-tuning  \nBowen Deng , 1, 2 Yunyeong Choi , 1, 2 Peichen Zhong , 1, 2 Janosh Riebesell ,3 Shashwat Anand ,2 Zhuohan Li ,2 KyuJung Jun , 1, 2 Kristin A. Persson , 1, 2 and Gerbrand Ceder 1, 2, ∗  \n1 Department of Materials Science and Engineering,  \nUniversity of California, Berkeley, California 94720, United States  \n2 Materials Sciences Division, Lawrence Berkeley National Laboratory, California 94720, United States  \n3 Cavendish Laboratory, University of Cambridge, J. J. Thomson Ave, Cambridge, UK (Dated: May 14, 2024)  \nMachine learning interatomic potentials (MLIPs) have introduced a new paradigm for atomic simulations. Recent advancements have seen the emergence of universal MLIPs (uMLIPs) that are pre-trained on diverse materials datasets, providing opportunities for both ready-to-use universal force fields and robust foundations for downstream machine learning refinements. However, their performance in extrapolating to out-of-distribution complex atomic environments remains unclear. In this study, we highlight a consistent potential energy surface (PES) softening effect in three uMLIPs: M3GNet, CHGNet, and MACE-MP-0, which is characterized by energy and force under-prediction in a series of atomic-modeling benchmarks including surfaces, defects, solid-solution energetics, phonon vibration modes, ion migration barriers, and general high-energy states.  \nWe find that the PES softening behavior originates from a systematic underprediction error of the PES curvature, which derives from the biased sampling of near-equilibrium atomic arrangements in uMLIP pre-training datasets. We demonstrate that the PES softening issue can be effectively rectified by fine-tuning with a single additional data point. Our findings suggest that a considerable fraction of uMLIP errors are highly systematic, and can therefore be efficiently corrected. This result rationalizes the data-efficient fine-tuning performance boost commonly observed with foundational MLIPs. We argue for the importance of a comprehensive materials dataset with improved PES sampling for next-generation foundational MLIPs.  \nI. INTRODUCTION  \nArtificial intelligence (AI) is increasingly shifting the paradigm of scientific discovery to accelerate research and solve real-world scientific challenges [1] . While ab-initio quantum mechanical simulation methods, such as density functional theory (DFT), offer the theoretical foundation to investigate material and chemical science problems atthe atomic scale, their computational demands limit their applicability in both spatial and temporal scales. Recent advancements in machine learning interatomic potentials (MLIPs) [2, 3] have enabled the opportunity to scale up quantum mechanical methods to million atoms simulations such as water, copper [4], and biomolecules [5] .  \nAlongside improvements in atomic environment descriptors and graph neural networks that enhance the expressivity of MLIP models [3, 6], universal machine learning interatomic potentials (uMLIPs) have demonstrated another avenue by taking advantage of pre-training on large and comprehensive material datasets [7–13] . These uMLIPs enable out-of-box atomic modeling covering the entire periodic table as well as providing robust machinelearning foundations for fine-tuning downstream tasks. While uMLIPs hold considerable promise, a critical challenge lies in their ability to reliably generalize to complex and diverse chemical environments, particularly those  \n∗ [gceder@berkeley.edu](gceder@berkeley.edu)  \nthat deviate significantly from the pre-training data distribution. Several recent benchmark efforts have tested the uMLIPs’ ability to identify stable materials [14], surface energies [15], lattice relaxations and vibrational properties [16], etc. A systematic understanding of the ability of uMLIPs to extrapolate to co","cbCaicLWjSbAE8YF","https://ap.wps.com/l/cbCaicLWjSbAE8YF","pdf",11348788,12,"English","# Introduction\n## Universal MLIPs and the challenge of OOD generalization\n## Systematic PES softening across uMLIPs\n## Origin of softening: biased PES curvature underprediction\n## Fine-tuning as a data-efficient correction","[{\"question\":\"What problem does the paper address in universal machine learning interatomic potentials?\",\"answer\":\"It examines why universal MLIPs struggle to extrapolate reliably to out-of-distribution complex atomic environments, focusing on a consistent potential energy surface softening effect.\"},{\"question\":\"Which uMLIPs show the potential energy surface softening behavior?\",\"answer\":\"The paper reports PES softening in three uMLIPs: M3GNet, CHGNet, and MACE-MP-0.\"},{\"question\":\"How is the PES softening issue corrected, and what data is required?\",\"answer\":\"The study shows the issue can be effectively rectified by fine-tuning with a single additional data point, indicating the error is systematic and efficiently correctable.\"}]","Overcoming systematic softening in universal machine learning interatomic potentials - by fine-tuning | PDF"]