{"id":"https://openalex.org/W7214392264","doi":"https://doi.org/10.48550/arxiv.2609.29595","title":"Building Atomic Structures from Natural Language","display_name":"Building Atomic Structures from Natural Language","publication_year":2026,"publication_date":"2026-08-27","ids":{"openalex":"https://openalex.org/W7214392264","doi":"https://doi.org/10.48550/arxiv.2609.29595"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.29595","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.29595","pdf_url":"https://arxiv.org/pdf/2609.29595","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.29595","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134800279","display_name":"Pai Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210147322","display_name":"Shanghai Institute of Microsystem and Information Technology","ror":"https://ror.org/04nytyj38","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210147322"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Li, Pai","raw_affiliation_strings":["Chinese Academy of Sciences , 865 Changning Road , Shanghai 200050 , China","State Key Laboratory of Materials for Integrated Circuits , Shanghai Institute of Microsystem and Information Technology ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences , 865 Changning Road , Shanghai 200050 , China","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"State Key Laboratory of Materials for Integrated Circuits , Shanghai Institute of Microsystem and Information Technology ,","institution_ids":["https://openalex.org/I4210147322"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5134800279"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210147322"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10002","display_name":"Advanced Chemical Physics Studies","score":0.0003000000142492354,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12044","display_name":"Advanced Physical and Chemical Molecular Interactions","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1606","display_name":"Physical and Theoretical Chemistry"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/natural-language-prompts","display_name":"natural language prompts","score":0.4690000116825104},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9399999976158142},{"id":"https://openalex.org/keywords/periodicity-constraints","display_name":"periodicity constraints","score":0.6620000004768372},{"id":"https://openalex.org/keywords/nanoparticle-structure","display_name":"nanoparticle structure","score":0.5289999842643738},{"id":"https://openalex.org/keywords/surface-slabs","display_name":"surface slabs","score":0.6669999957084656},{"id":"https://openalex.org/keywords/interfaces","display_name":"interfaces","score":0.5360000133514404},{"id":"https://openalex.org/keywords/amorphous-network","display_name":"amorphous network","score":0.8379999995231628},{"id":"https://openalex.org/keywords/liquid-structure","display_name":"liquid structure","score":0.578000009059906}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7804999947547913},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.6941999793052673},{"id":"https://openalex.org/C78023250","wikidata":"https://www.wikidata.org/wiki/Q657596","display_name":"Unary operation","level":2,"score":0.5863000154495239},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.5080000162124634},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.4970000088214874},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.49059998989105225},{"id":"https://openalex.org/C35292069","wikidata":"https://www.wikidata.org/wiki/Q1575458","display_name":"Validator","level":2,"score":0.45239999890327454},{"id":"https://openalex.org/C151552104","wikidata":"https://www.wikidata.org/wiki/Q7705809","display_name":"Test suite","level":4,"score":0.42320001125335693},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.41290000081062317},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.3853999972343445},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.38420000672340393},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.3698999881744385},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.3587000072002411},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3540000021457672},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.3529999852180481},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3492000102996826},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.3483000099658966},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33889999985694885},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.32989999651908875},{"id":"https://openalex.org/C2781020372","wikidata":"https://www.wikidata.org/wiki/Q533093","display_name":"On the fly","level":2,"score":0.32339999079704285},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.3165999948978424},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.26759999990463257},{"id":"https://openalex.org/C164155591","wikidata":"https://www.wikidata.org/wiki/Q2067766","display_name":"Satisfiability modulo theories","level":2,"score":0.2605000138282776},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2567000091075897}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.29595","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.29595","pdf_url":"https://arxiv.org/pdf/2609.29595","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.29595","doi":"https://doi.org/10.48550/arxiv.2609.29595","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.29595","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.29595","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.29595","pdf_url":"https://arxiv.org/pdf/2609.29595","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214392264.pdf","grobid_xml":"https://content.openalex.org/works/W7214392264.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W4320854289"],"related_works":["https://openalex.org/W7165656070","https://openalex.org/W7222760228","https://openalex.org/W7220474145","https://openalex.org/W7133211127","https://openalex.org/W4407238013","https://openalex.org/W7135389302","https://openalex.org/W4405114187","https://openalex.org/W4415798112","https://openalex.org/W4391670863","https://openalex.org/W7133979686"],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"can":[3],"write":[4],"the":[5,19,67,114,127,135,138,146,159,166,198],"input":[6],"parameters":[7,23],"of":[8,59,97],"a":[9,13,27,31,41,45,55,62,72,94,105,109,155],"materials":[10],"simulation":[11],"from":[12,120,180],"prompt,":[14],"but":[15],"they":[16],"cannot":[17],"build":[18,85,110],"atomic":[20],"structure":[21],"those":[22],"describe.":[24],"A":[25],"crystal,":[26],"surface":[28],"slab":[29],"or":[30],"mismatched":[32],"interface":[33],"must":[34],"satisfy":[35],"global":[36],"constraints-periodicity":[37],"along":[38],"specific":[39],"axes,":[40],"given":[42],"vacuum":[43],"thickness,":[44],"commensurate":[46],"registry,":[47],"sensible":[48],"bond":[49],"lengths.":[50],"Generation":[51],"one":[52,147],"token":[53],"at":[54],"time":[56],"enforces":[57],"none":[58],"them,":[60],"and":[61,89,100,122,134,150,183,188,193],"violation":[63],"is":[64,111,145,152,163],"invisible":[65],"in":[66],"output.":[68],"We":[69,195],"present":[70],"ATLAS,":[71],"framework":[73],"that":[74,140],"makes":[75,165],"structural":[76,176],"construction":[77],"scriptable.":[78],"Seven":[79],"components-analyzer,":[80],"LLM":[81],"skill,":[82],"JSON":[83],"format,":[84],"engine,":[86],"validator,":[87],"scorer":[88],"web":[90],"interface-are":[91],"organized":[92],"around":[93],"component":[95],"algebra":[96],"named":[98],"structures":[99],"spaces.":[101],"Every":[102],"specification":[103],"carries":[104],"check":[106],"list,":[107],"so":[108,154],"verified":[112],"against":[113,126],"request":[115],"rather":[116,171],"than":[117,172],"merely":[118,173],"parsed":[119],"it,":[121],"builds":[123],"are":[124,178],"scored":[125],"user's":[128],"intent.":[129],"Requests":[130],"state":[131],"physical":[132],"sizes,":[133],"engine":[136],"computes":[137],"replication":[139],"reaches":[141],"them.":[142],"The":[143],"translation":[144],"stochastic":[148],"stage,":[149],"it":[151],"recorded,":[153],"run":[156],"replays":[157],"with":[158],"model":[160],"held":[161],"fixed-which":[162],"what":[164],"framework's":[167],"own":[168],"behaviour":[169],"measurable":[170],"observed.":[174],"Fourteen":[175],"classes":[177],"demonstrated,":[179],"bulk":[181],"cells":[182],"nanoparticles":[184],"through":[185],"surfaces,":[186],"defects":[187],"interfaces":[189],"to":[190],"amorphous":[191],"networks":[192],"liquids.":[194],"outline":[196],"how":[197],"same":[199],"loop":[200],"generates":[201],"training":[202],"sets":[203],"for":[204],"machine-learning":[205],"force":[206],"fields.":[207]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-09-26T00:00:00"}
