{"data":{"id":"10.4121/3c4a5d21-954b-4ba3-b70d-f7f09582bace","type":"dois","attributes":{"doi":"10.4121/3c4a5d21-954b-4ba3-b70d-f7f09582bace","prefix":"10.4121","suffix":"3c4a5d21-954b-4ba3-b70d-f7f09582bace","identifiers":[],"alternateIdentifiers":[],"creators":[{"name":"Alexander Kolganov","nameType":"Personal","nameIdentifiers":[{"nameIdentifier":"0000-0002-0262-8892","nameIdentifierScheme":"https://orcid.org/"}],"affiliation":[]},{"name":"Mas Klein","nameType":"Personal","givenName":"Mas","familyName":"Klein","nameIdentifiers":[{"nameIdentifier":"0009-0003-8245-7919","nameIdentifierScheme":"https://orcid.org/"}],"affiliation":[]},{"name":"Evgeny Pidko","nameType":"Personal","givenName":"Evgeny","familyName":"Pidko","nameIdentifiers":[{"nameIdentifier":"0000-0001-9242-9901","nameIdentifierScheme":"https://orcid.org/"}],"affiliation":[]}],"titles":[{"title":"Dataset underlying the publication \"Foundation interatomic potentials learn the practical chemistry they were never taught\""}],"publisher":"4TU.ResearchData","container":{},"publicationYear":2026,"subjects":[{"subject":"Physical Chemistry (incl. Structural)","subjectScheme":"Australian and New Zealand Standard Research Classification (ANZSRC), 2008","classificationCode":"0306"},{"subject":"Organic Chemistry","subjectScheme":"Australian and New Zealand Standard Research Classification (ANZSRC), 2008","classificationCode":"0305"},{"subject":"Theoretical and Computational Chemistry","subjectScheme":"Australian and New Zealand Standard Research Classification (ANZSRC), 2008","classificationCode":"0307"},{"subject":"Inorganic Chemistry","subjectScheme":"Australian and New Zealand Standard Research Classification (ANZSRC), 2008","classificationCode":"0302"},{"subject":"Chemical Sciences","subjectScheme":"Australian and New Zealand Standard Research Classification (ANZSRC), 2008","classificationCode":"03"},{"subject":"Universal Machine Learning Potentials"},{"subject":"Computational Chemistry"},{"subject":"Machine Learning for Chemistry"},{"subject":"Latent space exploration"}],"contributors":[{"name":"TU Delft, Faculty of Applied Sciences, Department of Chemical Engineering","nameType":"Organizational","contributorType":"Other","affiliation":[],"nameIdentifiers":[]}],"dates":[{"date":"2026-10-29","dateType":"Issued"}],"language":"en","types":{"ris":"DATA","bibtex":"misc","citeproc":"dataset","schemaOrg":"Dataset","resourceType":"Dataset","resourceTypeGeneral":"Dataset"},"relatedIdentifiers":[{"relationType":"IsSupplementTo","relatedIdentifier":"10.26434/chemrxiv.15005743","relatedIdentifierType":"DOI"},{"relationType":"IsVersionOf","relatedIdentifier":"10.4121/3c4a5d21-954b-4ba3-b70d-f7f09582bace.v1","relatedIdentifierType":"DOI"},{"relationType":"IsVersionOf","relatedIdentifier":"10.4121/3c4a5d21-954b-4ba3-b70d-f7f09582bace.v2","relatedIdentifierType":"DOI"},{"relationType":"IsVersionOf","relatedIdentifier":"10.4121/3c4a5d21-954b-4ba3-b70d-f7f09582bace.v3","relatedIdentifierType":"DOI"}],"relatedItems":[],"sizes":[],"formats":[".xyz (molecular geometries), .h5 (data archives), .csv(ground-truth datasets, metrics, predictions, controls), .py (python code)"],"version":"3","rightsList":[{"rights":"Creative Commons Attribution 4.0 International","rightsUri":"https://creativecommons.org/licenses/by/4.0/legalcode","schemeUri":"https://spdx.org/licenses/","rightsIdentifier":"cc-by-4.0","rightsIdentifierScheme":"SPDX"}],"descriptions":[{"description":"This dataset supports a computational study investigating whether the internal atomic representations (embeddings) of universal machine-learning interatomic potentials (MLIPs) implicitly encode established physical-organic and organometallic chemistry, despite never explicitly being trained on such properties. Per-atom embeddings were extracted from three foundation MLIPs (MACE-Omol-0, UMA-s-1p2, ORB-mol) and used as fixed inputs to simple supervised probes (ridge regression and a gated attention-pooling network) trained to recover reference chemical descriptors and observables. The dataset consists of the input molecular geometries (XYZ), the reference label tables and per-atom embedding tensors (HDF5), the cross-validated analysis outputs (metrics, per-point predictions, and control/baseline results as CSV), and the Python data analysis code.","descriptionType":"Abstract"}],"geoLocations":[],"fundingReferences":[{"awardTitle":"The Catalyst Dance: Understanding Ensemble Dynamics for Theory-Guided Catalyst Development (DYNACAT)","funderName":"NWO","awardNumber":"VI.C.242.082"}],"xml":"PD94bWwgdmVyc2lvbj0iMS4wIiBlbmNvZGluZz0iVVRGLTgiPz4KPHJlc291cmNlIHhtbG5zPSJodHRwOi8vZGF0YWNpdGUub3JnL3NjaGVtYS9rZXJuZWwtNCIgeG1sbnM6eHNpPSJodHRwOi8vd3d3LnczLm9yZy8yMDAxL1hNTFNjaGVtYS1pbnN0YW5jZSIgeHNpOnNjaGVtYUxvY2F0aW9uPSJodHRwOi8vZGF0YWNpdGUub3JnL3NjaGVtYS9rZXJuZWwtNCBodHRwOi8vc2NoZW1hLmRhdGFjaXRlLm9yZy9tZXRhL2tlcm5lbC00LjQvbWV0YWRhdGEueHNkIj4KICA8aWRlbnRpZmllciBpZGVudGlmaWVyVHlwZT0iRE9JIj4xMC40MTIxLzNDNEE1RDIxLTk1NEItNEJBMy1CNzBELUY3RjA5NTgyQkFDRTwvaWRlbnRpZmllcj4KICA8Y3JlYXRvcnM+CiAgICA8Y3JlYXRvcj4KICAgICAgPGNyZWF0b3JOYW1lIG5hbWVUeXBlPSJQZXJzb25hbCI+QWxleGFuZGVyIEtvbGdhbm92PC9jcmVhdG9yTmFtZT4KICAgICAgPG5hbWVJZGVudGlmaWVyIG5hbWVJZGVudGlmaWVyU2NoZW1lPSJodHRwczovL29yY2lkLm9yZy8iPjAwMDAtMDAwMi0wMjYyLTg4OTI8L25hbWVJZGVudGlmaWVyPgogICAgPC9jcmVhdG9yPgogICAgPGNyZWF0b3I+CiAgICAgIDxjcmVhdG9yTmFtZSBuYW1lVHlwZT0iUGVyc29uYWwiPk1hcyBLbGVpbjwvY3JlYXRvck5hbWU+CiAgICAgIDxnaXZlbk5hbWU+TWFzPC9naXZlbk5hbWU+CiAgICAgIDxmYW1pbHlOYW1lPktsZWluPC9mYW1pbHlOYW1lPgogICAgICA8bmFtZUlkZW50aWZpZXIgbmFtZUlkZW50aWZpZXJTY2hlbWU9Imh0dHBzOi8vb3JjaWQub3JnLyI+MDAwOS0wMDAzLTgyNDUtNzkxOTwvbmFtZUlkZW50aWZpZXI+CiAgICA8L2NyZWF0b3I+CiAgICA8Y3JlYXRvcj4KICAgICAgPGNyZWF0b3JOYW1lIG5hbWVUeXBlPSJQZXJzb25hbCI+RXZnZW55IFBpZGtvPC9jcmVhdG9yTmFtZT4KICAgICAgPGdpdmVuTmFtZT5Fdmdlbnk8L2dpdmVuTmFtZT4KICAgICAgPGZhbWlseU5hbWU+UGlka288L2ZhbWlseU5hbWU+CiAgICAgIDxuYW1lSWRlbnRpZmllciBuYW1lSWRlbnRpZmllclNjaGVtZT0iaHR0cHM6Ly9vcmNpZC5vcmcvIj4wMDAwLTAwMDEtOTI0Mi05OTAxPC9uYW1lSWRlbnRpZmllcj4KICAgIDwvY3JlYXRvcj4KICA8L2NyZWF0b3JzPgogIDx0aXRsZXM+CiAgICA8dGl0bGU+RGF0YXNldCB1bmRlcmx5aW5nIHRoZSBwdWJsaWNhdGlvbiAiRm91bmRhdGlvbiBpbnRlcmF0b21pYyBwb3RlbnRpYWxzIGxlYXJuIHRoZSBwcmFjdGljYWwgY2hlbWlzdHJ5IHRoZXkgd2VyZSBuZXZlciB0YXVnaHQiPC90aXRsZT4KICA8L3RpdGxlcz4KICA8cHVibGlzaGVyPjRUVS5SZXNlYXJjaERhdGE8L3B1Ymxpc2hlcj4KICA8cHVibGljYXRpb25ZZWFyPjIwMjY8L3B1YmxpY2F0aW9uWWVhcj4KICA8cmVzb3VyY2VUeXBlIHJlc291cmNlVHlwZUdlbmVyYWw9IkRhdGFzZXQiPkRhdGFzZXQ8L3Jlc291cmNlVHlwZT4KICA8c3ViamVjdHM+CiAgICA8c3ViamVjdCBzdWJqZWN0U2NoZW1lPSJBdXN0cmFsaWFuIGFuZCBOZXcgWmVhbGFuZCBTdGFuZGFyZCBSZXNlYXJjaCBDbGFzc2lmaWNhdGlvbiAoQU5aU1JDKSwgMjAwOCIgY2xhc3NpZmljYXRpb25Db2RlPSIwMzA2Ij5QaHlzaWNhbCBDaGVtaXN0cnkgKGluY2wuIFN0cnVjdHVyYWwpPC9zdWJqZWN0PgogICAgPHN1YmplY3Qgc3ViamVjdFNjaGVtZT0iQXVzdHJhbGlhbiBhbmQgTmV3IFplYWxhbmQgU3RhbmRhcmQgUmVzZWFyY2ggQ2xhc3NpZmljYXRpb24gKEFOWlNSQyksIDIwMDgiIGNsYXNzaWZpY2F0aW9uQ29kZT0iMDMwNSI+T3JnYW5pYyBDaGVtaXN0cnk8L3N1YmplY3Q+CiAgICA8c3ViamVjdCBzdWJqZWN0U2NoZW1lPSJBdXN0cmFsaWFuIGFuZCBOZXcgWmVhbGFuZCBTdGFuZGFyZCBSZXNlYXJjaCBDbGFzc2lmaWNhdGlvbiAoQU5aU1JDKSwgMjAwOCIgY2xhc3NpZmljYXRpb25Db2RlPSIwMzA3Ij5UaGVvcmV0aWNhbCBhbmQgQ29tcHV0YXRpb25hbCBDaGVtaXN0cnk8L3N1YmplY3Q+CiAgICA8c3ViamVjdCBzdWJqZWN0U2NoZW1lPSJBdXN0cmFsaWFuIGFuZCBOZXcgWmVhbGFuZCBTdGFuZGFyZCBSZXNlYXJjaCBDbGFzc2lmaWNhdGlvbiAoQU5aU1JDKSwgMjAwOCIgY2xhc3NpZmljYXRpb25Db2RlPSIwMzAyIj5Jbm9yZ2FuaWMgQ2hlbWlzdHJ5PC9zdWJqZWN0PgogICAgPHN1YmplY3Qgc3ViamVjdFNjaGVtZT0iQXVzdHJhbGlhbiBhbmQgTmV3IFplYWxhbmQgU3RhbmRhcmQgUmVzZWFyY2ggQ2xhc3NpZmljYXRpb24gKEFOWlNSQyksIDIwMDgiIGNsYXNzaWZpY2F0aW9uQ29kZT0iMDMiPkNoZW1pY2FsIFNjaWVuY2VzPC9zdWJqZWN0PgogICAgPHN1YmplY3Q+VW5pdmVyc2FsIE1hY2hpbmUgTGVhcm5pbmcgUG90ZW50aWFsczwvc3ViamVjdD4KICAgIDxzdWJqZWN0PkNvbXB1dGF0aW9uYWwgQ2hlbWlzdHJ5PC9zdWJqZWN0PgogICAgPHN1YmplY3Q+TWFjaGluZSBMZWFybmluZyBmb3IgQ2hlbWlzdHJ5PC9zdWJqZWN0PgogICAgPHN1YmplY3Q+TGF0ZW50IHNwYWNlIGV4cGxvcmF0aW9uPC9zdWJqZWN0PgogIDwvc3ViamVjdHM+CiAgPGNvbnRyaWJ1dG9ycz4KICAgIDxjb250cmlidXRvciBjb250cmlidXRvclR5cGU9Ik90aGVyIj4KICAgICAgPGNvbnRyaWJ1dG9yTmFtZSBuYW1lVHlwZT0iT3JnYW5pemF0aW9uYWwiPlRVIERlbGZ0LCBGYWN1bHR5IG9mIEFwcGxpZWQgU2NpZW5jZXMsIERlcGFydG1lbnQgb2YgQ2hlbWljYWwgRW5naW5lZXJpbmc8L2NvbnRyaWJ1dG9yTmFtZT4KICAgIDwvY29udHJpYnV0b3I+CiAgPC9jb250cmlidXRvcnM+CiAgPGRhdGVzPgogICAgPGRhdGUgZGF0ZVR5cGU9Iklzc3VlZCI+MjAyNi0xMC0yOTwvZGF0ZT4KICA8L2RhdGVzPgogIDxsYW5ndWFnZT5lbjwvbGFuZ3VhZ2U+CiAgPHJlbGF0ZWRJZGVudGlmaWVycz4KICAgIDxyZWxhdGVkSWRlbnRpZmllciByZWxhdGVkSWRlbnRpZmllclR5cGU9IkRPSSIgcmVsYXRpb25UeXBlPSJJc1N1cHBsZW1lbnRUbyI+MTAuMjY0MzQvY2hlbXJ4aXYuMTUwMDU3NDM8L3JlbGF0ZWRJZGVudGlmaWVyPgogICAgPHJlbGF0ZWRJZGVudGlmaWVyIHJlbGF0ZWRJZGVudGlmaWVyVHlwZT0iRE9JIiByZWxhdGlvblR5cGU9IklzVmVyc2lvbk9mIj4xMC40MTIxLzNjNGE1ZDIxLTk1NGItNGJhMy1iNzBkLWY3ZjA5NTgyYmFjZS52MTwvcmVsYXRlZElkZW50aWZpZXI+CiAgICA8cmVsYXRlZElkZW50aWZpZXIgcmVsYXRlZElkZW50aWZpZXJUeXBlPSJET0kiIHJlbGF0aW9uVHlwZT0iSXNWZXJzaW9uT2YiPjEwLjQxMjEvM2M0YTVkMjEtOTU0Yi00YmEzLWI3MGQtZjdmMDk1ODJiYWNlLnYyPC9yZWxhdGVkSWRlbnRpZmllcj4KICAgIDxyZWxhdGVkSWRlbnRpZmllciByZWxhdGVkSWRlbnRpZmllclR5cGU9IkRPSSIgcmVsYXRpb25UeXBlPSJJc1ZlcnNpb25PZiI+MTAuNDEyMS8zYzRhNWQyMS05NTRiLTRiYTMtYjcwZC1mN2YwOTU4MmJhY2UudjM8L3JlbGF0ZWRJZGVudGlmaWVyPgogIDwvcmVsYXRlZElkZW50aWZpZXJzPgogIDxmb3JtYXRzPgogICAgPGZvcm1hdD4ueHl6IChtb2xlY3VsYXIgZ2VvbWV0cmllcyksIC5oNSAoZGF0YSBhcmNoaXZlcyksIC5jc3YoZ3JvdW5kLXRydXRoIGRhdGFzZXRzLCBtZXRyaWNzLCBwcmVkaWN0aW9ucywgY29udHJvbHMpLCAgLnB5IChweXRob24gY29kZSk8L2Zvcm1hdD4KICA8L2Zvcm1hdHM+CiAgPHZlcnNpb24+MzwvdmVyc2lvbj4KICA8cmlnaHRzTGlzdD4KICAgIDxyaWdodHMgcmlnaHRzVVJJPSJodHRwczovL2NyZWF0aXZlY29tbW9ucy5vcmcvbGljZW5zZXMvYnkvNC4wLyI+Q0MgQlkgNC4wPC9yaWdodHM+CiAgPC9yaWdodHNMaXN0PgogIDxkZXNjcmlwdGlvbnM+CiAgICA8ZGVzY3JpcHRpb24gZGVzY3JpcHRpb25UeXBlPSJBYnN0cmFjdCI+Jmx0O3AmZ3Q7VGhpcyBkYXRhc2V0IHN1cHBvcnRzIGEgY29tcHV0YXRpb25hbCBzdHVkeSBpbnZlc3RpZ2F0aW5nIHdoZXRoZXIgdGhlIGludGVybmFsIGF0b21pYyByZXByZXNlbnRhdGlvbnMgKGVtYmVkZGluZ3MpIG9mIHVuaXZlcnNhbCBtYWNoaW5lLWxlYXJuaW5nIGludGVyYXRvbWljIHBvdGVudGlhbHMgKE1MSVBzKSBpbXBsaWNpdGx5IGVuY29kZSBlc3RhYmxpc2hlZCBwaHlzaWNhbC1vcmdhbmljIGFuZCBvcmdhbm9tZXRhbGxpYyBjaGVtaXN0cnksIGRlc3BpdGUgbmV2ZXIgZXhwbGljaXRseSBiZWluZyB0cmFpbmVkIG9uIHN1Y2ggcHJvcGVydGllcy4gUGVyLWF0b20gZW1iZWRkaW5ncyB3ZXJlIGV4dHJhY3RlZCBmcm9tIHRocmVlIGZvdW5kYXRpb24gTUxJUHMgKE1BQ0UtT21vbC0wLCBVTUEtcy0xcDIsIE9SQi1tb2wpIGFuZCB1c2VkIGFzIGZpeGVkIGlucHV0cyB0byBzaW1wbGUgc3VwZXJ2aXNlZCBwcm9iZXMgKHJpZGdlIHJlZ3Jlc3Npb24gYW5kIGEgZ2F0ZWQgYXR0ZW50aW9uLXBvb2xpbmcgbmV0d29yaykgdHJhaW5lZCB0byByZWNvdmVyIHJlZmVyZW5jZSBjaGVtaWNhbCBkZXNjcmlwdG9ycyBhbmQgb2JzZXJ2YWJsZXMuIFRoZSBkYXRhc2V0IGNvbnNpc3RzIG9mIHRoZSBpbnB1dCBtb2xlY3VsYXIgZ2VvbWV0cmllcyAoWFlaKSwgdGhlIHJlZmVyZW5jZSBsYWJlbCB0YWJsZXMgYW5kIHBlci1hdG9tIGVtYmVkZGluZyB0ZW5zb3JzIChIREY1KSwgdGhlIGNyb3NzLXZhbGlkYXRlZCBhbmFseXNpcyBvdXRwdXRzIChtZXRyaWNzLCBwZXItcG9pbnQgcHJlZGljdGlvbnMsIGFuZCBjb250cm9sL2Jhc2VsaW5lIHJlc3VsdHMgYXMgQ1NWKSwgYW5kIHRoZSBQeXRob24gZGF0YSBhbmFseXNpcyBjb2RlLiZsdDsvcCZndDs8L2Rlc2NyaXB0aW9uPgogIDwvZGVzY3JpcHRpb25zPgogIDxmdW5kaW5nUmVmZXJlbmNlcz4KICAgIDxmdW5kaW5nUmVmZXJlbmNlPgogICAgICA8ZnVuZGVyTmFtZT5OV088L2Z1bmRlck5hbWU+CiAgICAgIDxhd2FyZE51bWJlcj5WSS5DLjI0Mi4wODI8L2F3YXJkTnVtYmVyPgogICAgICA8YXdhcmRUaXRsZT5UaGUgQ2F0YWx5c3QgRGFuY2U6IFVuZGVyc3RhbmRpbmcgRW5zZW1ibGUgRHluYW1pY3MgZm9yIFRoZW9yeS1HdWlkZWQgQ2F0YWx5c3QgRGV2ZWxvcG1lbnQgKERZTkFDQVQpPC9hd2FyZFRpdGxlPgogICAgPC9mdW5kaW5nUmVmZXJlbmNlPgogIDwvZnVuZGluZ1JlZmVyZW5jZXM+CjwvcmVzb3VyY2U+","url":"https://data.4tu.nl/datasets/3c4a5d21-954b-4ba3-b70d-f7f09582bace","contentUrl":null,"metadataVersion":2,"schemaVersion":"http://datacite.org/schema/kernel-4","source":"api","isActive":true,"state":"findable","reason":null,"viewCount":0,"viewsOverTime":[],"downloadCount":0,"downloadsOverTime":[],"referenceCount":0,"citationCount":2,"citationsOverTime":[{"year":"2026","total":2}],"partCount":0,"partOfCount":0,"versionCount":0,"versionOfCount":3,"created":"2026-06-22T12:49:20.000Z","registered":"2026-06-22T12:49:21.000Z","published":"2026","updated":"2026-10-29T09:24:17.000Z"},"relationships":{"client":{"data":{"id":"delft.data4tu","type":"clients"}},"provider":{"data":{"id":"scpr","type":"providers"}},"media":{"data":{"id":"10.4121/3c4a5d21-954b-4ba3-b70d-f7f09582bace","type":"media"}},"references":{"data":[]},"citations":{"data":[{"id":"10.26434/chemrxiv.15005743","type":"dois"},{"id":"10.26434/chemrxiv.15005743/v2","type":"dois"}]},"parts":{"data":[]},"partOf":{"data":[]},"versions":{"data":[]},"versionOf":{"data":[{"id":"10.4121/3c4a5d21-954b-4ba3-b70d-f7f09582bace.v2","type":"dois"},{"id":"10.4121/3c4a5d21-954b-4ba3-b70d-f7f09582bace.v1","type":"dois"},{"id":"10.4121/3c4a5d21-954b-4ba3-b70d-f7f09582bace.v3","type":"dois"}]}}}}