{"id":"https://openalex.org/W7204775318","doi":"https://doi.org/10.48550/arxiv.2608.27629","title":"LitCurate: A Configuration-Driven AI-Assisted Framework for Scientific Database Construction with an Application to Lower-Mantle Equation-of-State Data","display_name":"LitCurate: A Configuration-Driven AI-Assisted Framework for Scientific Database Construction with an Application to Lower-Mantle Equation-of-State Data","publication_year":2026,"publication_date":"2026-08-27","ids":{"openalex":"https://openalex.org/W7204775318","doi":"https://doi.org/10.48550/arxiv.2608.27629"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.27629","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.27629","pdf_url":"https://arxiv.org/pdf/2608.27629","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","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.27629","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5106437037","display_name":"Abin Shakya","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I152304114","display_name":"Lamont-Doherty Earth Observatory","ror":"https://ror.org/02e2tgs60","country_code":"US","type":"facility","lineage":["https://openalex.org/I152304114","https://openalex.org/I78577930"]},{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shakya, Abin","raw_affiliation_strings":["Lamont-Doherty Earth Observatory , Columbia University , Palisades , NY , 10964 , United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lamont-Doherty Earth Observatory , Columbia University , Palisades , NY , 10964 , United States","institution_ids":["https://openalex.org/I152304114","https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148027148","display_name":"Wilson Samuels","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I6026837","display_name":"Tuskegee University","ror":"https://ror.org/0137n4m74","country_code":"US","type":"education","lineage":["https://openalex.org/I6026837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Samuels, Wilson","raw_affiliation_strings":["Department of Electrical and Computer Engineering , Tuskegee University , Tuskegee , AL , 36088 , United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering , Tuskegee University , Tuskegee , AL , 36088 , United States","institution_ids":["https://openalex.org/I6026837"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147986330","display_name":"Dominica Wilson","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I6026837","display_name":"Tuskegee University","ror":"https://ror.org/0137n4m74","country_code":"US","type":"education","lineage":["https://openalex.org/I6026837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wilson, Dominica","raw_affiliation_strings":["Department of Electrical and Computer Engineering , Tuskegee University , Tuskegee , AL , 36088 , United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering , Tuskegee University , Tuskegee , AL , 36088 , United States","institution_ids":["https://openalex.org/I6026837"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147933060","display_name":"Gioia Marchi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marchi, Gioia A.","raw_affiliation_strings":["Department of Industrial Engineering and Operations Research , Columbia University , New York , NY , 10027 , United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Industrial Engineering and Operations Research , Columbia University , New York , NY , 10027 , United States","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010174378","display_name":"Israa Draz","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Draz, Israa","raw_affiliation_strings":["Department of Applied Physics and Applied Mathematics , Columbia University , New York , NY , 10027 , United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Applied Physics and Applied Mathematics , Columbia University , New York , NY , 10027 , United States","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029610652","display_name":"Chenxing Luo","orcid":"https://orcid.org/0000-0003-4116-6851","observed_orcids":["https://orcid.org/0000-0003-4116-6851"]},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Luo, Chenxing","raw_affiliation_strings":["Department of Applied Physics and Applied Mathematics , Columbia University , New York , NY , 10027 , United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Applied Physics and Applied Mathematics , Columbia University , New York , NY , 10027 , United States","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020910604","display_name":"Renata M. M. Wentzcovitch","orcid":"https://orcid.org/0000-0001-5663-9426","observed_orcids":["https://orcid.org/0000-0001-5663-9426"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wentzcovitch, Renata M.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":0.6074000000953674,"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":0.6074000000953674,"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":0.1120000034570694,"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":0.07620000094175339,"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/literature-curation","display_name":"literature curation","score":0.7900000214576721},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9309999942779541},{"id":"https://openalex.org/keywords/equation-of-state","display_name":"equation of state","score":0.746999979019165},{"id":"https://openalex.org/keywords/lower-mantle","display_name":"lower mantle","score":0.9919999837875366},{"id":"https://openalex.org/keywords/high-pressure-mineral-phases","display_name":"high-pressure mineral phases","score":0.8790000081062317},{"id":"https://openalex.org/keywords/information-extraction","display_name":"information extraction","score":0.7390000224113464},{"id":"https://openalex.org/keywords/provenance-tracking","display_name":"provenance tracking","score":0.8539999723434448},{"id":"https://openalex.org/keywords/literature-discovery","display_name":"literature discovery","score":0.5139999985694885}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.732699990272522},{"id":"https://openalex.org/C2780615836","wikidata":"https://www.wikidata.org/wiki/Q2471869","display_name":"USable","level":2,"score":0.711899995803833},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.6485999822616577},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5879999995231628},{"id":"https://openalex.org/C2781083858","wikidata":"https://www.wikidata.org/wiki/Q17327049","display_name":"Scientific literature","level":2,"score":0.5636000037193298},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4941999912261963},{"id":"https://openalex.org/C91632574","wikidata":"https://www.wikidata.org/wiki/Q15088675","display_name":"Data curation","level":2,"score":0.48260000348091125},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4348999857902527},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.42080000042915344},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.3522000014781952},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.3319999873638153},{"id":"https://openalex.org/C3020774429","wikidata":"https://www.wikidata.org/wiki/Q1201886","display_name":"Web of science","level":3,"score":0.33180001378059387},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30970001220703125},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.30559998750686646},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3027999997138977},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.29429998993873596},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.2847999930381775},{"id":"https://openalex.org/C189708586","wikidata":"https://www.wikidata.org/wiki/Q1504425","display_name":"Systematic review","level":3,"score":0.28290000557899475},{"id":"https://openalex.org/C5968703","wikidata":"https://www.wikidata.org/wiki/Q267136","display_name":"Database model","level":3,"score":0.28130000829696655},{"id":"https://openalex.org/C138379479","wikidata":"https://www.wikidata.org/wiki/Q1116876","display_name":"Scientific modelling","level":2,"score":0.2700999975204468},{"id":"https://openalex.org/C148840519","wikidata":"https://www.wikidata.org/wiki/Q1049878","display_name":"Database design","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2619999945163727}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.27629","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.27629","pdf_url":"https://arxiv.org/pdf/2608.27629","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.2608.27629","doi":"https://doi.org/10.48550/arxiv.2608.27629","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.27629","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:2608.27629","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.27629","pdf_url":"https://arxiv.org/pdf/2608.27629","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/G5268743511","display_name":"Machine Learning Serpentines","funder_award_id":"2506448","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5363092874","display_name":null,"funder_award_id":"10.37807","funder_id":"https://openalex.org/F4320306202","funder_display_name":"Gordon and Betty Moore Foundation"},{"id":"https://openalex.org/G7661743722","display_name":"Modeling Earth from the Atomic to Global Scale","funder_award_id":"GBMF12801","funder_id":"https://openalex.org/F4320306202","funder_display_name":"Gordon and Betty Moore Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306202","display_name":"Gordon and Betty Moore Foundation","ror":"https://ror.org/006wxqw41"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204775318.pdf","grobid_xml":"https://content.openalex.org/works/W7204775318.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7106318670","https://openalex.org/W7153300043","https://openalex.org/W7203923425","https://openalex.org/W2975643040","https://openalex.org/W4416619891","https://openalex.org/W7171543239","https://openalex.org/W7164684257","https://openalex.org/W4411081845","https://openalex.org/W7221755834","https://openalex.org/W4417192129"],"abstract_inverted_index":{"The":[0,141,171],"growing":[1],"scientific":[2,56,69,182,201],"literature":[3,45,73,183,197],"contains":[4],"decades":[5],"of":[6,20,123],"experimental":[7,131],"and":[8,15,28,95,101,125,132,156,159,203],"computational":[9,204],"results":[10,94],"that":[11],"could":[12],"support":[13],"data-driven":[14],"physics-based":[16],"modeling,":[17],"yet":[18],"much":[19],"this":[21],"infor-":[22],"mation":[23,89],"remains":[24],"locked":[25],"in":[26],"publications":[27],"is":[29,46],"not":[30],"readily":[31],"usable":[32],"for":[33,67,194,200],"large-scale":[34],"analysis":[35,202],"or":[36,164],"sci-":[37],"entific":[38],"software.":[39],"Building":[40],"structured":[41],"databases":[42,70],"from":[43,71,130,138],"the":[44,72],"particularly":[47],"challenging":[48],"whenrelevantstudiesmustfirstbediscoveredamonglargecollectionsofpapersandreported":[49],"quantities":[50],"must":[51],"be":[52,169],"extracted":[53],"with":[54],"enough":[55],"context":[57],"to":[58,99,118,148,184],"remain":[59],"usable.":[60],"We":[61,115],"present":[62],"LitCurate,":[63],"an":[64,79,120],"open-source":[65],"framework":[66],"building":[68],"using":[74],"large":[75],"language":[76],"models":[77],"within":[78],"auditable,":[80],"stage-wise":[81],"curation":[82,109],"workflow.":[83],"LitCurate":[84,117],"integratesliteraturediscovery,":[85],"relevancescreening,":[86],"full-textprocessing,":[87],"andstructuredinfor-":[88],"extraction":[90],"while":[91],"retaining":[92],"intermediate":[93],"provenance,":[96],"allowing":[97],"researchers":[98],"inspect":[100],"revise":[102],"individual":[103],"stages":[104],"rather":[105],"than":[106],"treating":[107],"automated":[108],"as":[110,162],"a":[111,176,191],"black-":[112],"box":[113],"process.":[114],"apply":[116],"construct":[119],"equation-of-state":[121,146],"database":[122],"lower-mantle":[124],"lower-mantle-relevant":[126],"high-pressure":[127],"mineral":[128,149],"phases":[129],"theoretical":[133],"studies,":[134],"comprising":[135],"1,334":[136],"entries":[137],"205":[139],"papers.":[140],"resulting":[142],"dataset":[143],"links":[144],"reported":[145],"parameters":[147],"phases,":[150],"compositions,":[151],"equation":[152],"formulations,":[153],"meth-":[154],"ods,":[155],"parameter":[157],"constraints,":[158],"labels":[160],"values":[161],"source-reported":[163],"citation-reported":[165],"when":[166],"provenance":[167],"can":[168],"determined.":[170],"records":[172],"are":[173],"available":[174],"through":[175],"searchable":[177],"web":[178],"application.":[179],"By":[180],"connecting":[181],"traceable,":[185],"machine-readable":[186],"data,":[187],"LitCu-":[188],"rate":[189],"provides":[190],"reusable":[192],"approach":[193],"transforming":[195],"accumulated":[196],"into":[198],"resources":[199],"modeling.":[205]},"counts_by_year":[],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2026-09-01T00:00:00"}