{"id":"https://openalex.org/W7213495232","doi":"https://doi.org/10.48550/arxiv.2609.18583","title":"ERAF4XRD: A multimodal agentic framework for constructing validated experimental X-ray diffraction databases from scientific literature","display_name":"ERAF4XRD: A multimodal agentic framework for constructing validated experimental X-ray diffraction databases from scientific literature","publication_year":2026,"publication_date":"2026-09-16","ids":{"openalex":"https://openalex.org/W7213495232","doi":"https://doi.org/10.48550/arxiv.2609.18583"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.18583","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.18583","pdf_url":"https://arxiv.org/pdf/2609.18583","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","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/2609.18583","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089006665","display_name":"Afnan Mostafa","orcid":"https://orcid.org/0000-0002-0371-926X","observed_orcids":["https://orcid.org/0000-0002-0371-926X"]},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mostafa, Afnan","raw_affiliation_strings":["Department of Mechanical Engineering , University of Rochester , NY 14627 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering , University of Rochester , NY 14627 , USA","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085468170","display_name":"William Ratcliff","orcid":"https://orcid.org/0000-0001-8956-3851","observed_orcids":["https://orcid.org/0000-0001-8956-3851"]},"institutions":[{"id":"https://openalex.org/I1321296531","display_name":"National Institute of Standards and Technology","ror":"https://ror.org/05xpvk416","country_code":"US","type":"government","lineage":["https://openalex.org/I1321296531","https://openalex.org/I1343035065"]},{"id":"https://openalex.org/I4210159838","display_name":"NIST Center for Neutron Research","ror":"https://ror.org/05qgcra83","country_code":"US","type":"government","lineage":["https://openalex.org/I1321296531","https://openalex.org/I1343035065","https://openalex.org/I4210159838"]},{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ratcliff, William","raw_affiliation_strings":["Department of Physics , Department of Materials Science and Engineering , University of Maryland , College Park , MD 20742 , USA","NIST Center for Neutron Research , National Institute of Standards and Technology , Gaithersburg , MD 20899 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Physics , Department of Materials Science and Engineering , University of Maryland , College Park , MD 20742 , USA","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"NIST Center for Neutron Research , National Institute of Standards and Technology , Gaithersburg , MD 20899 , USA","institution_ids":["https://openalex.org/I1321296531","https://openalex.org/I4210159838"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065794019","display_name":"Simon J. L. Billinge","orcid":"https://orcid.org/0000-0002-9734-4998","observed_orcids":["https://orcid.org/0000-0002-9734-4998"]},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Billinge, Simon J. L.","raw_affiliation_strings":["Department of Materials , University of California , Santa Barbara , CA 93106 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Materials , University of California , Santa Barbara , CA 93106 , USA","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057731721","display_name":"Niaz Abdolrahim","orcid":"https://orcid.org/0000-0002-9333-8179","observed_orcids":["https://orcid.org/0000-0002-9333-8179"]},"institutions":[{"id":"https://openalex.org/I4405262925","display_name":"Laboratory for Laser Energetics","ror":"https://ror.org/006rjbv46","country_code":"US","type":"facility","lineage":["https://openalex.org/I4405262925","https://openalex.org/I5388228"]},{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abdolrahim, Niaz","raw_affiliation_strings":["Department of Mechanical Engineering , University of Rochester , NY 14627 , USA","Laboratory for Laser Energetics , University of Rochester , NY 14623 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering , University of Rochester , NY 14627 , USA","institution_ids":["https://openalex.org/I5388228"]},{"raw_affiliation_string":"Laboratory for Laser Energetics , University of Rochester , NY 14623 , USA","institution_ids":["https://openalex.org/I4405262925","https://openalex.org/I5388228"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"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":0.7148000001907349,"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":0.7148000001907349,"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/T11937","display_name":"Research Data Management Practices","score":0.10970000177621841,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.02449999935925007,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/x-ray-diffraction","display_name":"X-ray diffraction","score":0.9359999895095825},{"id":"https://openalex.org/keywords/scientific-text-mining","display_name":"scientific literature mining","score":0.5960000157356262},{"id":"https://openalex.org/keywords/multimodal-information-extraction","display_name":"multimodal information extraction","score":0.7289999723434448},{"id":"https://openalex.org/keywords/multi-agent-systems","display_name":"multi-agent systems","score":0.9120000004768372},{"id":"https://openalex.org/keywords/data-validation","display_name":"data validation","score":0.6620000004768372}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.8930000066757202},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.722000002861023},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6891000270843506},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6653000116348267},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6320000290870667},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5313000082969666},{"id":"https://openalex.org/C2781083858","wikidata":"https://www.wikidata.org/wiki/Q17327049","display_name":"Scientific literature","level":2,"score":0.4975000023841858},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.46320000290870667},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42410001158714294},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.41359999775886536},{"id":"https://openalex.org/C55037315","wikidata":"https://www.wikidata.org/wiki/Q5421151","display_name":"Experimental data","level":2,"score":0.3628000020980835},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3400000035762787},{"id":"https://openalex.org/C138379479","wikidata":"https://www.wikidata.org/wiki/Q1116876","display_name":"Scientific modelling","level":2,"score":0.2992999851703644},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2924000024795532},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.27149999141693115},{"id":"https://openalex.org/C2983685735","wikidata":"https://www.wikidata.org/wiki/Q5227355","display_name":"Data source","level":2,"score":0.25859999656677246},{"id":"https://openalex.org/C56666940","wikidata":"https://www.wikidata.org/wiki/Q788790","display_name":"Documentation","level":2,"score":0.25760000944137573},{"id":"https://openalex.org/C33326189","wikidata":"https://www.wikidata.org/wiki/Q17092450","display_name":"Information integration","level":2,"score":0.25200000405311584}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.18583","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.18583","pdf_url":"https://arxiv.org/pdf/2609.18583","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.18583","doi":"https://doi.org/10.48550/arxiv.2609.18583","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.18583","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.18583","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.18583","pdf_url":"https://arxiv.org/pdf/2609.18583","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G9000379508","display_name":"Collaborative Research: Elements: DiffAI: Diffraction Database and Intelligent Analysis","funder_award_id":"2625202","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G9000384945","display_name":"Collaborative Research: Elements: DiffAI: Diffraction Database and Intelligent Analysis","funder_award_id":"2513797","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332178","display_name":"National Institute of Standards and Technology","ror":"https://ror.org/05xpvk416"},{"id":"https://openalex.org/F4320337377","display_name":"Office of Advanced Cyberinfrastructure","ror":"https://ror.org/04nh1dc89"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7213495232.pdf","grobid_xml":"https://content.openalex.org/works/W7213495232.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W4304195432","https://openalex.org/W4407185785","https://openalex.org/W4415238177","https://openalex.org/W6910589802","https://openalex.org/W7124132862","https://openalex.org/W7126239966","https://openalex.org/W7127510601","https://openalex.org/W7153300043","https://openalex.org/W7172535593"],"related_works":["https://openalex.org/W6893965243","https://openalex.org/W7160146045","https://openalex.org/W7172513663","https://openalex.org/W7125421550","https://openalex.org/W4321434949","https://openalex.org/W7220472404","https://openalex.org/W7027030587","https://openalex.org/W7211987361","https://openalex.org/W2894224563","https://openalex.org/W2398590682"],"abstract_inverted_index":{"The":[0],"scientific":[1,80,117,186],"literature":[2],"contains":[3],"decades":[4],"of":[5,23,115,144,174],"experimental":[6,35,97,176,190],"measurements":[7],"that":[8,72],"remain":[9],"difficult":[10],"to":[11,40,94,126,169],"access":[12],"as":[13],"structured":[14],"data":[15,36],"for":[16,59,129,183,192],"modern":[17],"AI":[18,193],"and":[19,32,37,44,68,84,91,99,133,152,172,194],"data-driven":[20,195],"research.":[21],"Much":[22],"this":[24],"information":[25,167,187],"is":[26],"distributed":[27],"across":[28,138],"figures,":[29,89,122],"captions,":[30],"text,":[31],"tables,":[33],"requiring":[34],"their":[38],"context":[39],"be":[41,49],"identified,":[42],"connected,":[43],"verified":[45],"before":[46],"they":[47],"can":[48],"reused.":[50],"Here":[51],"we":[52],"introduce":[53],"ERAF4XRD":[54,82,123,178],"(Experiment":[55],"Reader":[56],"Agentic":[57],"Framework":[58],"X-Ray":[60],"Diffraction),":[61],"a":[62,111],"fully":[63],"automated":[64,181],"multimodal":[65],"(i.e.,":[66],"image":[67],"text),":[69],"multi-agent":[70],"framework":[71],"reconstructs":[73],"validated":[74,147],"X-ray":[75],"diffraction":[76],"(XRD)":[77],"records":[78,148],"from":[79],"publications.":[81],"downloads":[83],"screens":[85],"documents,":[86],"identifies":[87],"XRD":[88,130],"extracts":[90],"links":[92],"metadata":[93,136,158],"the":[95,145,170],"corresponding":[96],"data,":[98],"validates":[100],"outputs":[101],"against":[102],"source":[103],"evidence":[104],"using":[105],"an":[106,180],"independent":[107],"validation":[108,173],"agent.":[109],"On":[110],"manually":[112],"curated":[113],"benchmark":[114],"273":[116],"publications":[118],"containing":[119],"3,150":[120],"candidate":[121],"achieved":[124],"up":[125],"98.7%":[127],"accuracy":[128],"figure":[131],"identification":[132],"generated":[134],"1,400":[135],"values":[137],"22":[139],"fields.":[140,163],"Independent":[141],"manual":[142],"assessment":[143],"final":[146],"yielded":[149],"98.5%":[150],"precision":[151],"90.7%":[153],"recall,":[154],"with":[155],"no":[156],"unsupported":[157],"observed":[159],"among":[160],"443":[161],"evaluated":[162],"By":[164],"moving":[165],"beyond":[166],"extraction":[168],"reconstruction":[171],"linked":[175],"records,":[177],"establishes":[179],"approach":[182],"transforming":[184],"published":[185],"into":[188],"machine-readable":[189],"datasets":[191],"science.":[196]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-18T00:00:00"}
