{"status":"OK","data":{"id":606784,"identifier":"RNPTDS","persistentUrl":"https://doi.org/10.34894/RNPTDS","protocol":"doi","authority":"10.34894","separator":"/","publisher":"DataverseNL","publicationDate":"2026-05-04","storageIdentifier":"surf://10.34894/RNPTDS","effectiveDatasetFileCountLimit":10000,"datasetFileUploadsAvailable":9998,"datasetType":"dataset","locks":[],"latestVersion":{"id":33988,"datasetId":606784,"datasetPersistentId":"doi:10.34894/RNPTDS","datasetType":"dataset","storageIdentifier":"surf://10.34894/RNPTDS","versionNumber":1,"internalVersionNumber":23,"versionMinorNumber":0,"versionState":"RELEASED","latestVersionPublishingState":"RELEASED","lastUpdateTime":"2026-05-04T07:46:48Z","releaseTime":"2026-05-04T07:46:48Z","createTime":"2026-02-09T16:39:56Z","publicationDate":"2026-05-04","citationDate":"2026-05-04","effectiveDatasetFileCountLimit":10000,"datasetFileUploadsAvailable":9998,"license":{"name":"CC-BY-4.0","uri":"http://creativecommons.org/licenses/by/4.0","iconUri":"https://i.creativecommons.org/l/by/4.0/88x31.png"},"fileAccessRequest":true,"metadataBlocks":{"citation":{"displayName":"Citation Metadata","name":"citation","fields":[{"typeName":"title","multiple":false,"typeClass":"primitive","value":"Dataset: Molecular Simulations Assisted by an Artificial Intelligence Agent"},{"typeName":"author","multiple":true,"typeClass":"compound","value":[{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"Chanmungkalakul, Supphachok"},"authorAffiliation":{"typeName":"authorAffiliation","multiple":false,"typeClass":"primitive","value":"https://ror.org/012p63287","expandedvalue":{"scheme":"http://www.grid.ac/ontology/","termName":"University of Groningen","@type":"https://schema.org/Organization"}},"authorIdentifierScheme":{"typeName":"authorIdentifierScheme","multiple":false,"typeClass":"controlledVocabulary","value":"ORCID"},"authorIdentifier":{"typeName":"authorIdentifier","multiple":false,"typeClass":"primitive","value":"0000-0002-8287-5040"}},{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"van der Ree, Michiel"},"authorAffiliation":{"typeName":"authorAffiliation","multiple":false,"typeClass":"primitive","value":"https://ror.org/012p63287","expandedvalue":{"scheme":"http://www.grid.ac/ontology/","termName":"University of Groningen","@type":"https://schema.org/Organization"}},"authorIdentifierScheme":{"typeName":"authorIdentifierScheme","multiple":false,"typeClass":"controlledVocabulary","value":"ORCID"},"authorIdentifier":{"typeName":"authorIdentifier","multiple":false,"typeClass":"primitive","value":"0009-0005-0442-936X"}},{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"Giuntoli, Andrea"},"authorAffiliation":{"typeName":"authorAffiliation","multiple":false,"typeClass":"primitive","value":"https://ror.org/012p63287","expandedvalue":{"scheme":"http://www.grid.ac/ontology/","termName":"University of Groningen","@type":"https://schema.org/Organization"}},"authorIdentifierScheme":{"typeName":"authorIdentifierScheme","multiple":false,"typeClass":"controlledVocabulary","value":"ORCID"},"authorIdentifier":{"typeName":"authorIdentifier","multiple":false,"typeClass":"primitive","value":"0000-0002-5676-5614"}},{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"Pollice, Robert"},"authorAffiliation":{"typeName":"authorAffiliation","multiple":false,"typeClass":"primitive","value":"https://ror.org/012p63287","expandedvalue":{"scheme":"http://www.grid.ac/ontology/","termName":"University of Groningen","@type":"https://schema.org/Organization"}},"authorIdentifierScheme":{"typeName":"authorIdentifierScheme","multiple":false,"typeClass":"controlledVocabulary","value":"ORCID"},"authorIdentifier":{"typeName":"authorIdentifier","multiple":false,"typeClass":"primitive","value":"0000-0001-8836-6266"}}]},{"typeName":"datasetContact","multiple":true,"typeClass":"compound","value":[{"datasetContactName":{"typeName":"datasetContactName","multiple":false,"typeClass":"primitive","value":"Groningen Digital Competence Centre"},"datasetContactAffiliation":{"typeName":"datasetContactAffiliation","multiple":false,"typeClass":"primitive","value":"University of Groningen"}}]},{"typeName":"dsDescription","multiple":true,"typeClass":"compound","value":[{"dsDescriptionValue":{"typeName":"dsDescriptionValue","multiple":false,"typeClass":"primitive","value":"This Dataset is for the paper Molecular Simulations Assisted by an Artificial Intelligence Agent (ArIA). This set contains codes and full datasets used to reproduce the results shown in the paper.<br><br>\n\nDataset Structure<br>\nThis set contains three main directories:\nAll the scripts require uv (https://docs.astral.sh/uv/getting-started/installation/)\nAll the test scripts were tested in our local cluster with L40S GPU.<br><br>\n\nApp_deployment<br>\nThis directory is used for deploying the ArIA chatbot. LoRA adapters trained in the `Model_development` directory are transferred here for use within the LangGraph framework.<br><br>\n\nMake_prompt <br>\nThis directory contains scripts for generating synthetic prompts from ORCA input files, as well as synthetic reasoning texts (CoT, CoVe, ToT, GoT, and intrinsic reasoning) used for model fine-tuning.\nORCA input files were generated with the method used in this paper: https://doi.org/10.1039/D4DD00366G.\nThe scripts for calculating F1, classifying errors are also included in this directory.<br><br>\n\nModel_development<br>\nThis directory is dedicated to LoRA adapter development. It includes ORCA input file execution to ensure runnability, along with validation and feedback agents.<br>\n\nEach directory is separated. Enter a directory to load and use the corresponding module."},"dsDescriptionDate":{"typeName":"dsDescriptionDate","multiple":false,"typeClass":"primitive","value":"2026"}}]},{"typeName":"subject","multiple":true,"typeClass":"controlledVocabulary","value":["Chemistry"]},{"typeName":"keyword","multiple":true,"typeClass":"compound","value":[{"keywordValue":{"typeName":"keywordValue","multiple":false,"typeClass":"primitive","value":"AI-assisted computational chemistry"}},{"keywordValue":{"typeName":"keywordValue","multiple":false,"typeClass":"primitive","value":"computational chemistry"}},{"keywordValue":{"typeName":"keywordValue","multiple":false,"typeClass":"primitive","value":"quantum chemistry"}},{"keywordValue":{"typeName":"keywordValue","multiple":false,"typeClass":"primitive","value":"DFT"}}]},{"typeName":"topicClassification","multiple":true,"typeClass":"compound","value":[{"topicClassValue":{"typeName":"topicClassValue","multiple":false,"typeClass":"primitive","value":"AI-assisted computational chemistry"}}]},{"typeName":"publication","multiple":true,"typeClass":"compound","value":[{"publicationRelationType":{"typeName":"publicationRelationType","multiple":false,"typeClass":"controlledVocabulary","value":"IsSupplementTo"},"publicationCitation":{"typeName":"publicationCitation","multiple":false,"typeClass":"primitive","value":"Molecular Simulations Assisted by an Artificial Intelligence Agent (ArIA) (submitted)"}}]},{"typeName":"notesText","multiple":false,"typeClass":"primitive","value":"DOI of the preprint: https://chemrxiv.org/doi/full/10.26434/chemrxiv.15002344/v1"},{"typeName":"language","multiple":true,"typeClass":"controlledVocabulary","value":["English"]},{"typeName":"distributor","multiple":true,"typeClass":"compound","value":[{"distributorName":{"typeName":"distributorName","multiple":false,"typeClass":"primitive","value":"DataverseNL Network"},"distributorAffiliation":{"typeName":"distributorAffiliation","multiple":false,"typeClass":"primitive","value":"DANS"},"distributorAbbreviation":{"typeName":"distributorAbbreviation","multiple":false,"typeClass":"primitive","value":"DVNL"},"distributorURL":{"typeName":"distributorURL","multiple":false,"typeClass":"primitive","value":"https://dataverse.nl"}}]},{"typeName":"depositor","multiple":false,"typeClass":"primitive","value":"Elsenga, Christina"},{"typeName":"dateOfDeposit","multiple":false,"typeClass":"primitive","value":"2026-02-09"}]},"dansDataVaultMetadata":{"displayName":"Data Vault Metadata","name":"dansDataVaultMetadata","fields":[{"typeName":"dansDataversePid","multiple":false,"typeClass":"primitive","value":"doi:10.34894/RNPTDS"},{"typeName":"dansDataversePidVersion","multiple":false,"typeClass":"primitive","value":"1.0"},{"typeName":"dansBagId","multiple":false,"typeClass":"primitive","value":"urn:uuid:a65c9232-7fbb-479f-ae70-4c51d94f9576"},{"typeName":"dansNbn","multiple":false,"typeClass":"primitive","value":"urn:nbn:nl:ui:13-053c0d57-0f05-4010-99c1-7ab5e04b1893"}]}},"files":[{"label":"ArIA_v1.zip","restricted":false,"version":4,"datasetVersionId":33988,"dataFile":{"id":607599,"persistentId":"","filename":"ArIA_v1.zip","contentType":"application/zip","friendlyType":"ZIP Archive","filesize":3550691608,"storageIdentifier":"surf://store:19c56706e3e-b63c4fd33608","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"dfdd6088b9d6db77ca4f3cdf50e931980b5cae7d"},"tabularData":false,"creationDate":"2026-02-13","publicationDate":"2026-05-04","lastUpdateTime":"2026-05-04T07:46:48Z","fileAccessRequest":true}},{"description":"Documentation","label":"README.md","restricted":false,"version":1,"datasetVersionId":33988,"dataFile":{"id":614488,"persistentId":"","filename":"README.md","contentType":"text/markdown","friendlyType":"Markdown Text","filesize":1125,"description":"Documentation","storageIdentifier":"surf://store:19cc3f61f35-7b571caf6f1c","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"0a7866c9c47bf3a83ee96ef132ec830b8132460e"},"tabularData":false,"creationDate":"2026-03-06","publicationDate":"2026-05-04","lastUpdateTime":"2026-05-04T07:46:48Z","fileAccessRequest":true}}]}}}