{"id":"https://openalex.org/W7207636859","doi":"https://doi.org/10.48550/arxiv.2609.02056","title":"HyGRAIL: Cost-Aware and Evidence-Grounded Scientific Hypothesis Discovery over Knowledge Graphs","display_name":"HyGRAIL: Cost-Aware and Evidence-Grounded Scientific Hypothesis Discovery over Knowledge Graphs","publication_year":2026,"publication_date":"2026-09-02","ids":{"openalex":"https://openalex.org/W7207636859","doi":"https://doi.org/10.48550/arxiv.2609.02056"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.02056","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.02056","pdf_url":"https://arxiv.org/pdf/2609.02056","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","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.02056","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5149835643","display_name":"Yihang Sun","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sun, Yihang","raw_affiliation_strings":["University of Illinois Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5149725059","display_name":"Zhihan Zhu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhu, Zhihan","raw_affiliation_strings":["University of Illinois Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147329755","display_name":"Zhiyuan Jiang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiang, Zhiyuan","raw_affiliation_strings":["University of Illinois Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017996571","display_name":"Jingyi Ge","orcid":"https://orcid.org/0009-0007-0299-575X","observed_orcids":["https://orcid.org/0009-0007-0299-575X"]},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ge, Jingyi","raw_affiliation_strings":["University of Illinois Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122939358","display_name":"Zixuan Li","orcid":"https://orcid.org/0009-0007-9962-6917","observed_orcids":["https://orcid.org/0009-0007-9962-6917"]},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li, Zixuan","raw_affiliation_strings":["University of Illinois Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003491365","display_name":"Jiaxuan You","orcid":"https://orcid.org/0000-0003-1812-7598","observed_orcids":["https://orcid.org/0000-0003-1812-7598"]},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"You, Jiaxuan","raw_affiliation_strings":["University of Illinois Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157725225"],"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.8500999808311462,"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"}},"topics":[{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.8500999808311462,"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"}},{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.03689999878406525,"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":0.031199999153614044,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/scientific-knowledge-graphs","display_name":"scientific knowledge graphs","score":0.8579999804496765},{"id":"https://openalex.org/keywords/missing-links","display_name":"missing links","score":0.5109999775886536},{"id":"https://openalex.org/keywords/graph-neural-networks","display_name":"graph neural networks","score":0.8090000152587891},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9380000233650208},{"id":"https://openalex.org/keywords/evidence-grounding","display_name":"evidence grounding","score":0.7099999785423279},{"id":"https://openalex.org/keywords/hypothesis-validation","display_name":"hypothesis verification","score":0.46000000834465027}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6506999731063843},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.5414999723434448},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4934000074863434},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.47440001368522644},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4223000109195709},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.40639999508857727},{"id":"https://openalex.org/C2777120189","wikidata":"https://www.wikidata.org/wiki/Q780067","display_name":"Triage","level":2,"score":0.38260000944137573},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37310001254081726},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.3628000020980835},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.3490000069141388},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3465000092983246},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3294999897480011},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.30550000071525574},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.29589998722076416},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.2937000095844269},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2849999964237213},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.2831000089645386},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.2777999937534332},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C195732255","wikidata":"https://www.wikidata.org/wiki/Q981008","display_name":"Sociology of scientific knowledge","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C146380142","wikidata":"https://www.wikidata.org/wiki/Q1137726","display_name":"Directed graph","level":2,"score":0.2547000050544739}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.02056","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.02056","pdf_url":"https://arxiv.org/pdf/2609.02056","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.2609.02056","doi":"https://doi.org/10.48550/arxiv.2609.02056","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.02056","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:2609.02056","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.02056","pdf_url":"https://arxiv.org/pdf/2609.02056","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7207636859.pdf","grobid_xml":"https://content.openalex.org/works/W7207636859.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3164202548","https://openalex.org/W6968175081","https://openalex.org/W4413799855","https://openalex.org/W7162549249","https://openalex.org/W7202162107","https://openalex.org/W7103493262","https://openalex.org/W7163530977","https://openalex.org/W7160313645","https://openalex.org/W7162216330","https://openalex.org/W7154838479"],"abstract_inverted_index":{"Scientific":[0],"knowledge":[1,137],"graphs":[2,21],"organize":[3],"entities":[4],"and":[5,34,76,89,110,131,166,190,223],"relations":[6],"extracted":[7],"from":[8,135],"scientific":[9,26,37],"literature,":[10],"but":[11,58,70],"they":[12],"remain":[13],"inherently":[14],"incomplete.":[15],"Missing":[16],"typed":[17,49],"links":[18],"in":[19,81],"such":[20,28],"can":[22],"therefore":[23],"represent":[24],"plausible":[25],"hypotheses,":[27],"as":[29],"unexplored":[30],"associations":[31,130],"between":[32],"materials":[33],"applications.":[35],"However,":[36],"hypothesis":[38,99,161,221],"discovery":[39],"is":[40,217,228],"challenging":[41],"because":[42],"true":[43],"discoveries":[44],"are":[45,56,68,77],"extremely":[46],"sparse":[47],"among":[48],"candidate":[50,108],"pairs:":[51],"graph":[52,82,138,215],"neural":[53],"networks":[54],"(GNNs)":[55],"efficient":[57],"unreliable":[59],"for":[60,219],"ambiguous":[61,114],"cases,":[62],"while":[63],"large":[64],"language":[65,147],"models":[66],"(LLMs)":[67],"knowledgeable":[69],"too":[71],"costly":[72],"to":[73,106,120],"apply":[74],"exhaustively":[75],"not":[78],"naturally":[79],"grounded":[80],"structures.":[83],"We":[84],"propose":[85],"HyGRAIL,":[86],"a":[87,104,112],"cost-aware":[88],"evidence-grounded":[90],"framework":[91],"that":[92,213,224],"combines":[93],"heterogeneous":[94],"GNN":[95,105,198],"triage":[96,199],"with":[97],"LLM-based":[98,151],"review.":[100,122],"HyGRAIL":[101,127,172],"first":[102],"uses":[103],"score":[107,177],"hypotheses":[109],"identify":[111],"validation-calibrated":[113],"region,":[115],"routing":[116],"only":[117],"graph-uncertain":[118],"cases":[119],"LLM":[121,154,202],"For":[123],"each":[124,159],"routed":[125],"hypothesis,":[126],"retrieves":[128],"node-level":[129],"multi-hop":[132],"relational":[133],"paths":[134],"the":[136,163,174,182,192,201],"(KG),":[139],"then":[140],"converts":[141],"this":[142],"structured":[143],"evidence":[144,165,216,227],"into":[145],"natural":[146],"through":[148],"template-based":[149],"or":[150],"naturalization.":[152],"An":[153],"review":[155],"agent":[156],"finally":[157],"judges":[158],"hard":[160],"using":[162],"naturalized":[164],"validation-selected":[167],"decision":[168],"criteria.":[169],"On":[170],"MatKG,":[171],"achieves":[173],"best":[175],"F1":[176,188],"of":[178],"0.429,":[179],"improving":[180],"over":[181,191],"strongest":[183],"prior":[184],"baseline":[185,194],"by":[186,195,205],"0.242":[187],"points":[189],"GNN-only":[193],"0.322.":[196],"Meanwhile,":[197],"reduces":[200],"call":[203],"rate":[204],"54.36%":[206],"on":[207],"average.":[208],"Ablation":[209],"studies":[210],"further":[211],"show":[212],"retrieved":[214],"crucial":[218],"reliable":[220],"verification":[222],"compact,":[225],"two-sided":[226],"more":[229],"effective":[230],"than":[231],"simply":[232],"increasing":[233],"retrieval":[234],"quantity.":[235]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-09-04T00:00:00"}