{"id":"https://openalex.org/W7225731367","doi":"https://doi.org/10.1088/1402-4896/aec009","title":"Crystal-scaffold: deterministic scaffold compilation for text-conditioned CIF generation","display_name":"Crystal-scaffold: deterministic scaffold compilation for text-conditioned CIF generation","publication_year":2026,"publication_date":"2026-11-10","ids":{"openalex":"https://openalex.org/W7225731367","doi":"https://doi.org/10.1088/1402-4896/aec009"},"language":"en","primary_location":{"id":"doi:10.1088/1402-4896/aec009","doi":"https://doi.org/10.1088/1402-4896/aec009","is_oa":false,"landing_page_url":"https://doi.org/10.1088/1402-4896/aec009","pdf_url":null,"source":{"id":"https://openalex.org/S59012888","display_name":"Physica Scripta","issn_l":"0031-8949","issn":["0031-8949","1402-4896"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","dongbi-d","jufo-1","ki-jl-1","norway-1","poland-40","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320083","host_organization_name":"IOP Publishing","host_organization_lineage":["https://openalex.org/P4310320083","https://openalex.org/P4310311669"],"host_organization_lineage_names":["IOP Publishing","Institute of Physics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Physica Scripta","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049125725","display_name":"Senlin Wang","orcid":"https://orcid.org/0000-0002-7557-6237","observed_orcids":["https://orcid.org/0000-0002-7557-6237"]},"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/I4210119098","display_name":"Fujian Institute of Research on the Structure of Matter","ror":"https://ror.org/02j89k719","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210119098"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Senlin Wang","raw_affiliation_strings":["Chinese Academy of Sciences Fujian Institute of Research on the Structure of Matter"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences Fujian Institute of Research on the Structure of Matter","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210119098"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5161363058","display_name":"Haotian Zhang","orcid":"https://orcid.org/0009-0006-4421-7289","observed_orcids":["https://orcid.org/0009-0006-4421-7289"]},"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/I4210119098","display_name":"Fujian Institute of Research on the Structure of Matter","ror":"https://ror.org/02j89k719","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210119098"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haotian Zhang","raw_affiliation_strings":["Chinese Academy of Sciences Fujian Institute of Research on the Structure of Matter"],"raw_orcid":"https://orcid.org/0009-0006-4421-7289","affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences Fujian Institute of Research on the Structure of Matter","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210119098"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5161416549","display_name":"Hao Chen","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/I4210119098","display_name":"Fujian Institute of Research on the Structure of Matter","ror":"https://ror.org/02j89k719","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210119098"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Chen","raw_affiliation_strings":["Chinese Academy of Sciences Fujian Institute of Research on the Structure of Matter"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences Fujian Institute of Research on the Structure of Matter","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210119098"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070235642","display_name":"Wei Hua Luo","orcid":"https://orcid.org/0000-0003-4016-765X","observed_orcids":["https://orcid.org/0000-0003-4016-765X"]},"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/I4210119098","display_name":"Fujian Institute of Research on the Structure of Matter","ror":"https://ror.org/02j89k719","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210119098"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Luo","raw_affiliation_strings":["Chinese Academy of Sciences Fujian Institute of Research on the Structure of Matter"],"raw_orcid":"https://orcid.org/0000-0003-4016-765X","affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences Fujian Institute of Research on the Structure of Matter","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210119098"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5161378484","display_name":"Wei Wang","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/I4210119098","display_name":"Fujian Institute of Research on the Structure of Matter","ror":"https://ror.org/02j89k719","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210119098"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Wang","raw_affiliation_strings":["Chinese Academy of Sciences Fujian Institute of Research on the Structure of Matter"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences Fujian Institute of Research on the Structure of Matter","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210119098"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101735762","display_name":"Renhao Fan","orcid":"https://orcid.org/0009-0002-9136-1831","observed_orcids":["https://orcid.org/0009-0002-9136-1831"]},"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/I4210119098","display_name":"Fujian Institute of Research on the Structure of Matter","ror":"https://ror.org/02j89k719","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210119098"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Renhao Fan","raw_affiliation_strings":["Chinese Academy of Sciences Fujian Institute of Research on the Structure of Matter"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences Fujian Institute of Research on the Structure of Matter","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210119098"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2400,"currency":"USD","value_usd":2400},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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":0.9955999851226807,"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":0.9955999851226807,"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/T10464","display_name":"Crystal structures of chemical compounds","score":0.0013000000035390258,"subfield":{"id":"https://openalex.org/subfields/1604","display_name":"Inorganic Chemistry"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10939","display_name":"Crystal Structures and Properties","score":0.0006000000284984708,"subfield":{"id":"https://openalex.org/subfields/2504","display_name":"Electronic, Optical and Magnetic Materials"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8248999714851379},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.6317999958992004},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.6295999884605408},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5252000093460083},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5138999819755554},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.48579999804496765},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.45590001344680786},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.4449999928474426},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4172999858856201},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.39309999346733093},{"id":"https://openalex.org/C146834321","wikidata":"https://www.wikidata.org/wiki/Q2979672","display_name":"Closure (psychology)","level":2,"score":0.38850000500679016},{"id":"https://openalex.org/C2779886137","wikidata":"https://www.wikidata.org/wiki/Q21030012","display_name":"Symmetry (geometry)","level":2,"score":0.37709999084472656},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.3752000033855438},{"id":"https://openalex.org/C2778844933","wikidata":"https://www.wikidata.org/wiki/Q630950","display_name":"Interlocking","level":2,"score":0.35010001063346863},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.3393000066280365},{"id":"https://openalex.org/C89429830","wikidata":"https://www.wikidata.org/wiki/Q735710","display_name":"Scaffold","level":2,"score":0.32429999113082886},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.31040000915527344},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3021000027656555},{"id":"https://openalex.org/C2779696439","wikidata":"https://www.wikidata.org/wiki/Q7512811","display_name":"Signature (topology)","level":2,"score":0.2962999939918518},{"id":"https://openalex.org/C131584629","wikidata":"https://www.wikidata.org/wiki/Q4308705","display_name":"Coupling (piping)","level":2,"score":0.29339998960494995},{"id":"https://openalex.org/C204495577","wikidata":"https://www.wikidata.org/wiki/Q1205349","display_name":"Callback","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C148730421","wikidata":"https://www.wikidata.org/wiki/Q141090","display_name":"Encryption","level":2,"score":0.27090001106262207},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C2777655017","wikidata":"https://www.wikidata.org/wiki/Q1501161","display_name":"Toolbox","level":2,"score":0.2669999897480011},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2513999938964844},{"id":"https://openalex.org/C184720557","wikidata":"https://www.wikidata.org/wiki/Q7825049","display_name":"Topology (electrical circuits)","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1088/1402-4896/aec009","doi":"https://doi.org/10.1088/1402-4896/aec009","is_oa":false,"landing_page_url":"https://doi.org/10.1088/1402-4896/aec009","pdf_url":null,"source":{"id":"https://openalex.org/S59012888","display_name":"Physica Scripta","issn_l":"0031-8949","issn":["0031-8949","1402-4896"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","dongbi-d","jufo-1","ki-jl-1","norway-1","poland-40","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320083","host_organization_name":"IOP Publishing","host_organization_lineage":["https://openalex.org/P4310320083","https://openalex.org/P4310311669"],"host_organization_lineage_names":["IOP Publishing","Institute of Physics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Physica Scripta","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Large":[1],"language":[2],"models":[3],"can":[4],"generate":[5],"crystal":[6],"structures":[7],"as":[8,199],"text,":[9],"but":[10],"direct":[11],"generation":[12],"of":[13,33,143,149,180,184,189],"complete,":[14],"valid":[15,31],"CIFs":[16,20,52],"remains":[17],"difficult,":[18],"since":[19],"combine":[21],"strict":[22],"syntax,":[23],"symmetry":[24,67],"constraints,":[25,74],"deterministic":[26,54],"closure":[27,88],"relations,":[28],"and":[29,65,71,75,83,119,122,145,172,186,196],"multiple":[30],"serializations":[32],"the":[34,99,129,213],"same":[35],"structure.":[36],"Here,":[37],"we":[38],"introduce":[39,109],"Crystal-Scaffold,":[40],"a":[41,58,77,94,111,126,177,200],"canonicalized":[42],"compiled-scaffold":[43,197],"framework":[44],"for":[45,203],"text-conditioned":[46],"full-CIF":[47,205],"generation.":[48],"Crystal-Scaffold":[49,133],"converts":[50],"raw":[51],"into":[53,93],"canonical":[55],"targets,":[56],"uses":[57],"multi-task":[59],"parsing":[60],"warm-up":[61],"to":[62,160],"supervise":[63],"file-level":[64],"target-level":[66],"descriptors,":[68],"stoichiometric":[69],"closure,":[70],"lattice--site":[72],"structural":[73,136,187],"predicts":[76],"compact":[78],"scaffold-core":[79],"representation":[80],"from":[81,158],"composition":[82],"space-group":[84],"conditions.":[85],"The":[86],"remaining":[87],"fields":[89],"are":[90],"deterministically":[91],"compiled":[92,170],"scaffold-full":[95],"conditioning":[96,198],"context,":[97],"while":[98],"final":[100,214],"complete":[101],"CIF":[102,120],"is":[103],"still":[104],"generated":[105],"autoregressively.":[106],"We":[107],"further":[108,211],"Crystal-Scaffold-HBoN,":[110],"hierarchical":[112,208],"Best-of-N":[113],"decoding":[114],"extension":[115],"that":[116],"samples":[117],"scaffold":[118,168],"candidates":[121],"reranks":[123],"them":[124],"with":[125,207],"verifier.":[127],"On":[128],"MP-20":[130],"benchmark,":[131],"Base":[132,165],"achieves":[134,176],"93.2%":[135],"validity,":[137,140],"89.3%":[138],"compositional":[139,182],"first-candidate":[141],"MR@1":[142,157,179],"63.2%,":[144],"oracle":[146],"any-of-20":[147],"MR@20":[148],"78.7%":[150],"on":[151],"9,046":[152],"targets.":[153],"Direct-generation":[154],"controls":[155],"improve":[156],"56.9%":[159],"58.5%":[161],"through":[162],"target":[163,194],"canonicalization;":[164],"additionally":[166],"combines":[167],"planning,":[169],"conditioning,":[171],"staged":[173],"training.":[174],"HBoN":[175],"selected-output":[178],"66.5%,":[181],"validity":[183,188],"91.2%,":[185],"100%.":[190],"These":[191],"results":[192],"support":[193],"canonicalization":[195],"practical":[201],"formulation":[202],"reliable":[204],"generation,":[206],"candidate":[209],"selection":[210],"improving":[212],"selected":[215],"output.":[216]},"counts_by_year":[],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2026-11-11T00:00:00"}
