{"id":"https://openalex.org/W7130544725","doi":"https://doi.org/10.48550/arxiv.2602.16650","title":"Retrieval Augmented Generation of Literature-derived Polymer Knowledge: The Example of a Biodegradable Polymer Expert System","display_name":"Retrieval Augmented Generation of Literature-derived Polymer Knowledge: The Example of a Biodegradable Polymer Expert System","publication_year":2026,"publication_date":"2026-02-18","ids":{"openalex":"https://openalex.org/W7130544725","doi":"https://doi.org/10.48550/arxiv.2602.16650"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2602.16650","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126404252","display_name":"Sonakshi Gupta","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Gupta, Sonakshi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124074621","display_name":"Akhlak Mahmood","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mahmood, Akhlak","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126388650","display_name":"Wei Xiong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiong, Wei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5126415910","display_name":"Rampi Ramprasad","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ramprasad, Rampi","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5126404252"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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":0.7750999927520752,"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":0.7750999927520752,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.0738999992609024,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.050700001418590546,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5472000241279602},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5103999972343445},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.44350001215934753},{"id":"https://openalex.org/keywords/subject-matter-expert","display_name":"Subject-matter expert","score":0.37299999594688416},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.36239999532699585},{"id":"https://openalex.org/keywords/statement","display_name":"Statement (logic)","score":0.3492000102996826},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.3328999876976013}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7455000281333923},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5472000241279602},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5103999972343445},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.44350001215934753},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4399999976158142},{"id":"https://openalex.org/C105002631","wikidata":"https://www.wikidata.org/wiki/Q4833645","display_name":"Subject-matter expert","level":3,"score":0.37299999594688416},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.36239999532699585},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3614000082015991},{"id":"https://openalex.org/C2777026412","wikidata":"https://www.wikidata.org/wiki/Q2684591","display_name":"Statement (logic)","level":2,"score":0.3492000102996826},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.3328999876976013},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3296000063419342},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.3158999979496002},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3091000020503998},{"id":"https://openalex.org/C153701036","wikidata":"https://www.wikidata.org/wiki/Q659974","display_name":"Trustworthiness","level":2,"score":0.30880001187324524},{"id":"https://openalex.org/C2777206241","wikidata":"https://www.wikidata.org/wiki/Q194431","display_name":"Paragraph","level":2,"score":0.2948000133037567},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.2639999985694885},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.25760000944137573},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2565000057220459}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2602.16650","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Article"},{"id":"doi:10.48550/arxiv.2602.16650","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.16650","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:doi:10.48550/arxiv.2602.16650","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Polymer":[0],"literature":[1,238],"contains":[2],"a":[3,54,89,96,112,145,216],"large":[4,63],"and":[5,20,26,95,111,120,139,141,156,202,227],"growing":[6],"body":[7],"of":[8,13],"experimental":[9],"knowledge,":[10],"yet":[11],"much":[12],"it":[14],"is":[15,79],"buried":[16],"in":[17,36,188],"unstructured":[18],"text":[19],"inconsistent":[21],"terminology,":[22],"making":[23],"systematic":[24],"retrieval":[25,87,129,228],"reasoning":[27],"difficult.":[28],"Existing":[29],"tools":[30],"typically":[31],"extract":[32,209],"narrow,":[33],"study-specific":[34],"facts":[35],"isolation,":[37],"failing":[38],"to":[39,45,57,194,208],"preserve":[40],"the":[41,171,196],"cross-study":[42],"context":[43],"required":[44],"answer":[46],"broader":[47,161],"scientific":[48],"questions.":[49],"Retrieval-augmented":[50],"generation":[51],"(RAG)":[52],"offers":[53],"promising":[55],"way":[56],"overcome":[58],"this":[59,82,213],"limitation":[60],"by":[61,144],"combining":[62],"language":[64],"models":[65,234],"(LLMs)":[66],"with":[67,132,180],"external":[68],"retrieval,":[69],"but":[70],"its":[71],"effectiveness":[72],"depends":[73],"strongly":[74],"on":[75,232],"how":[76],"domain":[77,146,182],"knowledge":[78,115],"represented.":[80],"In":[81],"work,":[83],"we":[84,106],"develop":[85],"two":[86],"pipelines:":[88],"dense":[90],"semantic":[91],"vector-based":[92],"approach":[93,98],"(VectorRAG)":[94],"graph-based":[97],"(GraphRAG).":[99],"Using":[100],"over":[101],"1,000":[102],"polyhydroxyalkanoate":[103],"(PHA)":[104],"papers,":[105],"construct":[107],"context-preserving":[108],"paragraph":[109],"embeddings":[110],"canonicalized":[113],"structured":[114],"graph":[116],"supporting":[117],"entity":[118],"disambiguation":[119],"multi-hop":[121],"reasoning.":[122],"We":[123],"evaluate":[124],"these":[125,190],"pipelines":[126],"through":[127],"standard":[128],"metrics,":[130],"comparisons":[131],"general":[133],"state-of-the-art":[134],"systems":[135,191],"such":[136],"as":[137],"GPT":[138],"Gemini,":[140],"qualitative":[142],"validation":[143,167],"chemist.":[147],"The":[148],"results":[149],"show":[150],"that":[151,170,205],"GraphRAG":[152],"achieves":[153],"higher":[154],"precision":[155],"interpretability,":[157],"while":[158,235],"VectorRAG":[159],"provides":[160],"recall,":[162],"highlighting":[163],"complementary":[164],"trade-offs.":[165],"Expert":[166],"further":[168],"confirms":[169],"tailored":[172],"pipelines,":[173],"particularly":[174],"GraphRAG,":[175],"produce":[176],"well-grounded,":[177],"citation-reliable":[178],"responses":[179],"strong":[181],"relevance.":[183],"By":[184],"grounding":[185],"every":[186],"statement":[187],"evidence,":[189],"enable":[192],"researchers":[193],"navigate":[195],"literature,":[197],"compare":[198],"findings":[199],"across":[200],"studies,":[201],"uncover":[203],"patterns":[204],"are":[206],"difficult":[207],"manually.":[210],"More":[211],"broadly,":[212],"work":[214],"establishes":[215],"practical":[217],"framework":[218],"for":[219],"building":[220],"materials":[221],"science":[222],"assistants":[223],"using":[224],"curated":[225],"corpora":[226],"design,":[229],"reducing":[230],"reliance":[231],"proprietary":[233],"enabling":[236],"trustworthy":[237],"analysis":[239],"at":[240],"scale.":[241]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2026-02-20T00:00:00"}