Machine-learned exchange\u2013correlation (XC) functionals offer a route to improve Kohn\u2013Sham density
functional theory without incurring the cost of explicitly correlated electronic-structure methods. Their use
in production simulation codes, however, requires a well-defined mapping between the learned model and the
host-code density representation. We formulate and implement a Skala-1.1 interface in CP2K through the
external GauXC library. CP2K supplies the geometry, Gaussian basis, spin-resolved atomic-orbital density
matrix, and communicator, while GauXC evaluates the XC energy, atomic-orbital potential matrix, and avail
able nuclear derivatives. The interface accepts both all-electron and valence-only density matrices. The latter
may arise from separable dual-space pseudopotentials or molecular effective-core potentials. Implementation
errors are isolated from functional differences by comparing the Perdew\u2013Burke\u2013Ernzerhof (PBE) functional
evaluated through GauXC with native CP2K PBE. The resulting interface gives consistent energies, forces
validated against finite-difference total-energy checks, and force-based molecular-virial diagnostics for repre
sentative molecular cases. The dietGMTKN55 benchmark suite is evaluated with an all-electron Gaussian
augmented plane-wave treatment for elements up to bromine and def2 effective-core potentials for the heavier
elements. The resulting aggregate mean absolute deviation of 1.255 kcalmol\u22121 is within 0.020 kcalmol\u22121 of
the corresponding Skala reference value of 1.235 kcalmol\u22121. This work establishes a validated molecular
implementation of Skala in CP2K through GauXC.<\/p>\n","protected":false},"excerpt":{"rendered":"
Machine-learned exchange\u2013correlation (XC) functionals offer a route to improve Kohn\u2013Sham densityfunctional theory without incurring the cost of explicitly correlated electronic-structure methods. Their usein production simulation codes, however, requires a well-defined mapping between the learned model and thehost-code density representation. We formulate and implement a Skala-1.1 interface in CP2K through theexternal GauXC library. CP2K supplies the […]<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","msr-author-ordering":[{"type":"text","value":"Franz Poschel","user_id":0},{"type":"text","value":"Johann Pototschnig","user_id":0},{"type":"text","value":"Frederick Stein","user_id":0},{"type":"text","value":"Andreas Knupfer","user_id":0},{"type":"user_nicename","value":"Thijs Vogels","user_id":"43464"},{"type":"user_nicename","value":"Stefano Battaglia","user_id":"44283"},{"type":"user_nicename","value":"Sebastian Ehlert","user_id":"42804"},{"type":"text","value":" Jurg Hutter","user_id":0},{"type":"text","value":"Thomas D. Kuhne","user_id":0}],"msr_publishername":"","msr_publisher_other":"","msr_booktitle":"","msr_chapter":"","msr_edition":"","msr_editors":"","msr_how_published":"","msr_isbn":"","msr_issue":"","msr_journal":"","msr_number":"","msr_organization":"","msr_pages_string":"","msr_page_range_start":"","msr_page_range_end":"","msr_series":"","msr_volume":"","msr_copyright":"","msr_conference_name":"","msr_doi":"","msr_arxiv_id":"","msr_mag_id":"","msr_other_authors":"","msr_other_contributors":"","msr_speaker":"","msr_award":"","msr_affiliation":"","msr_institution":"","msr_host":"","msr_version":"","msr_duration":"","msr_release_tracker_id":"","msr_highlight_type":"","msr_date_display_format":"","msr_main_download_label":"","msr_external_link_label":"","msr_doi_label":"","msr_published_date":"2026-08","msr_startdate":"","msr_presentation_date":"","msr_highlight_text":"","msr_notes":"","msr_longbiography":"","msr_publicationurl":"","msr_external_url":"","msr_secondary_video_url":"","msr_conference_url":"","msr_journal_url":"","msr_year":2026,"msr_month":8,"msr_day":0,"msr_microsoftintellectualproperty":false,"msr_pub_id":"","msr_publication_uploader":[],"msr_related_uploader":[{"type":"url","title":"https:\/\/arxiv.org\/pdf\/2608.19033","label_id":270375,"id":false,"viewUrl":false},{"type":"file","title":"Molecular-Implementation-of-the-Machine-Learned-Skala.pdf","label_id":243112,"id":1184310,"viewUrl":"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2026\/08\/Molecular-Implementation-of-the-Machine-Learned-Skala.pdf"}],"msr_original_fields_of_study":[],"msr_s2_paper_id":"","msr_s2_pdf_url":"","msr_citation_count_updated":"","msr_citation_count":0,"msr_influential_citations":0,"msr_reference_count":0,"msr_s2_open_access":false,"msr_s2_author_ids":[],"msr_pub_ids":[],"msr_hide_image_in_river":0,"footnotes":""},"msr-research-highlight":[],"research-area":[13556],"msr-publication-type":[193726],"msr-publisher":[],"msr-publication-cta":[],"msr-focus-area":[],"msr-locale":[268875],"msr-post-option":[],"msr-field-of-study":[270234,270531,265824],"msr-conference":[],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-1184309","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-artificial-intelligence","msr-locale-en_us","msr-field-of-study-artificial-intelligence-1024","msr-field-of-study-density-functional-theory","msr-field-of-study-machine-learning-299"],"msr_publishername":"","msr_edition":"","msr_affiliation":"","msr_published_date":"2026-08","msr_host":"","msr_duration":"","msr_version":"","msr_speaker":"","msr_other_contributors":"","msr_booktitle":"","msr_pages_string":"","msr_chapter":"","msr_isbn":"","msr_journal":"","msr_volume":"","msr_number":"","msr_editors":"","msr_series":"","msr_issue":"","msr_organization":"","msr_how_published":"","msr_notes":"","msr_highlight_text":"","msr_release_tracker_id":"","msr_original_fields_of_study":"","msr_download_urls":"","msr_external_url":"","msr_secondary_video_url":"","msr_longbiography":"","msr_microsoftintellectualproperty":0,"msr_main_download":"","msr_publicationurl":"","msr_doi":"","msr_publication_uploader":[],"msr_related_uploader":[{"type":"url","title":"https:\/\/arxiv.org\/pdf\/2608.19033","label_id":270375,"id":false,"viewUrl":false},{"type":"file","title":"Molecular-Implementation-of-the-Machine-Learned-Skala.pdf","label_id":243112,"id":1184310,"viewUrl":"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2026\/08\/Molecular-Implementation-of-the-Machine-Learned-Skala.pdf"}],"msr_citation_count":0,"msr_citation_count_updated":"","msr_s2_paper_id":"","msr_influential_citations":0,"msr_reference_count":0,"msr_arxiv_id":"","msr_s2_author_ids":[],"msr_s2_open_access":false,"msr_s2_pdf_url":null,"msr_attachments":[{"id":1184310,"url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2026\/08\/Molecular-Implementation-of-the-Machine-Learned-Skala.pdf"}],"msr-author-ordering":[{"type":"text","value":"Franz Poschel","user_id":0,"rest_url":false},{"type":"text","value":"Johann Pototschnig","user_id":0,"rest_url":false},{"type":"text","value":"Frederick Stein","user_id":0,"rest_url":false},{"type":"text","value":"Andreas Knupfer","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Thijs Vogels","user_id":43464,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Thijs Vogels"},{"type":"user_nicename","value":"Stefano Battaglia","user_id":44283,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Stefano Battaglia"},{"type":"user_nicename","value":"Sebastian Ehlert","user_id":42804,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Sebastian Ehlert"},{"type":"text","value":"Jurg Hutter","user_id":0,"rest_url":false},{"type":"text","value":"Thomas D. Kuhne","user_id":0,"rest_url":false}],"msr_impact_theme":[],"msr_research_lab":[851467],"msr_event":[],"msr_group":[],"msr_project":[1149500],"publication":[],"video":[],"msr-tool":[],"msr_publication_type":"unpublished","related_content":{"projects":[{"ID":1149500,"post_title":"Density Functional Theory","post_name":"dft","post_type":"msr-project","post_date":"2025-10-08 08:00:00","post_modified":"2026-08-18 09:45:09","post_status":"publish","permalink":"https:\/\/www.microsoft.com\/en-us\/research\/project\/dft\/","post_excerpt":"Advancing the frontier of quantum chemistry by combining deep learning with Density Functional Theory (DFT) to unlock unprecedented accuracy and scalability in electronic structure simulations. Our mission is to enable predictive modeling of laboratory experiments by achieving chemically accurate electronic structure predictions with deep learning powered DFT, targeting errors below 1 kcal\/mol, while retaining the computational efficiency of scalable semi-local DFT. At the heart of our efforts is Skala, a deep learning-based exchange-correlation (XC) functional…","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/1149500"}]}}]},"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/1184309","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-research-item"}],"version-history":[{"count":4,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/1184309\/revisions"}],"predecessor-version":[{"id":1184314,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/1184309\/revisions\/1184314"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=1184309"}],"wp:term":[{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=1184309"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=1184309"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=1184309"},{"taxonomy":"msr-publisher","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publisher?post=1184309"},{"taxonomy":"msr-publication-cta","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-cta?post=1184309"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=1184309"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=1184309"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=1184309"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=1184309"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=1184309"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=1184309"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=1184309"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=1184309"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}