{"id":"https://openalex.org/W7134050807","doi":"https://doi.org/10.48550/arxiv.2603.04818","title":"LLM-Grounded Explainable AI for Supply Chain Risk Early Warning via Temporal Graph Attention Networks","display_name":"LLM-Grounded Explainable AI for Supply Chain Risk Early Warning via Temporal Graph Attention Networks","publication_year":2026,"publication_date":"2026-03-05","ids":{"openalex":"https://openalex.org/W7134050807","doi":"https://doi.org/10.48550/arxiv.2603.04818"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2603.04818","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":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"type":"article","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/A5128270093","display_name":"Zhiming Xue","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xue, Zhiming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128219022","display_name":"Yujue Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yujue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5128720075","display_name":"Menghao Huo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huo, Menghao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21548173,"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/T11223","display_name":"Maritime Ports and Logistics","score":0.40700000524520874,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11223","display_name":"Maritime Ports and Logistics","score":0.40700000524520874,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11622","display_name":"Maritime Navigation and Safety","score":0.3375000059604645,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12126","display_name":"Maritime Transport Emissions and Efficiency","score":0.10740000009536743,"subfield":{"id":"https://openalex.org/subfields/2305","display_name":"Environmental Engineering"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/attention-network","display_name":"Attention network","score":0.492000013589859},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4666999876499176},{"id":"https://openalex.org/keywords/port","display_name":"Port (circuit theory)","score":0.43549999594688416},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.3756999969482422},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.35920000076293945},{"id":"https://openalex.org/keywords/traffic-congestion","display_name":"Traffic congestion","score":0.3472999930381775},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.337799996137619},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.32739999890327454},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.3183000087738037}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7247999906539917},{"id":"https://openalex.org/C2993807640","wikidata":"https://www.wikidata.org/wiki/Q103709453","display_name":"Attention network","level":2,"score":0.492000013589859},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4674000144004822},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4666999876499176},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45750001072883606},{"id":"https://openalex.org/C32802771","wikidata":"https://www.wikidata.org/wiki/Q2443617","display_name":"Port (circuit theory)","level":2,"score":0.43549999594688416},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4162999987602234},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.3756999969482422},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.35920000076293945},{"id":"https://openalex.org/C2779888511","wikidata":"https://www.wikidata.org/wiki/Q244156","display_name":"Traffic congestion","level":2,"score":0.3472999930381775},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.337799996137619},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.32739999890327454},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.3183000087738037},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.31130000948905945},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.30709999799728394},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3068999946117401},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.30399999022483826},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.27059999108314514},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C104122410","wikidata":"https://www.wikidata.org/wiki/Q1416406","display_name":"Network model","level":2,"score":0.25609999895095825},{"id":"https://openalex.org/C85847156","wikidata":"https://www.wikidata.org/wiki/Q59015987","display_name":"Verifiable secret sharing","level":3,"score":0.2542000114917755},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2540000081062317},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2533999979496002},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2603.04818","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":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2603.04818","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.04818","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":"Preprint"}],"best_oa_location":{"id":"pmh:doi:10.48550/arxiv.2603.04818","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":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[{"score":0.5369779467582703,"display_name":"Life below water","id":"https://metadata.un.org/sdg/14"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Disruptions":[0],"at":[1],"critical":[2],"logistics":[3,155],"nodes":[4],"pose":[5],"severe":[6],"risks":[7],"to":[8,123],"global":[9,71],"supply":[10,36,72,223],"chains,":[11],"yet":[12],"existing":[13],"risk":[14,43,100,143,205,225],"prediction":[15,39],"systems":[16],"typically":[17],"prioritize":[18],"forecasting":[19],"accuracy":[20],"without":[21,207],"providing":[22],"operationally":[23,218],"interpretable":[24,202],"early":[25,185,226],"warnings.":[26],"This":[27],"paper":[28],"proposes":[29],"an":[30],"evidence-grounded":[31],"framework":[32,161,212],"that":[33,119,137,158,194],"jointly":[34],"performs":[35],"chain":[37,73,224],"bottleneck":[38],"and":[40,109,145,174,203,228],"faithful":[41],"natural-language":[42],"explanation":[44],"by":[45],"coupling":[46],"a":[47,54,66,133,166,179,214],"Temporal":[48],"Graph":[49],"Attention":[50],"Network":[51],"(TGAT)":[52],"with":[53,188],"structured":[55,117],"large":[56],"language":[57],"model":[58,125],"(LLM)":[59],"reasoning":[60,122],"module.":[61],"Using":[62],"maritime":[63],"hubs":[64],"as":[65],"representative":[67],"case":[68],"study":[69],"for":[70,222],"nodes,":[74],"daily":[75],"spatial":[76],"graphs":[77],"are":[78,89],"constructed":[79],"from":[80],"Automatic":[81],"Identification":[82],"System":[83],"(AIS)":[84],"broadcasts,":[85],"where":[86],"inter-node":[87],"interactions":[88],"modeled":[90],"through":[91],"attention-based":[92],"message":[93],"passing.":[94],"The":[95,211],"TGAT":[96],"predictor":[97],"captures":[98],"spatiotemporal":[99],"dynamics,":[101],"while":[102,183],"model-internal":[103],"evidence":[104,200],"--":[105,113],"including":[106],"feature":[107],"z-scores":[108],"attention-derived":[110],"neighbor":[111],"influence":[112],"is":[114],"transformed":[115],"into":[116],"prompts":[118],"constrain":[120],"LLM":[121,196],"verifiable":[124],"outputs.":[126],"To":[127],"evaluate":[128],"explanatory":[129],"reliability,":[130],"we":[131],"introduce":[132],"directional-consistency":[134],"validation":[135],"protocol":[136],"quantitatively":[138],"measures":[139],"agreement":[140],"between":[141],"generated":[142],"narratives":[144],"underlying":[146],"statistical":[147],"evidence.":[148],"Experiments":[149],"on":[150],"six":[151],"months":[152],"of":[153,169,172,176],"real-world":[154],"data":[156],"demonstrate":[157],"the":[159],"proposed":[160],"outperforms":[162],"baseline":[163],"models,":[164],"achieving":[165],"test":[167],"AUC":[168],"0.761,":[170],"AP":[171],"0.344,":[173],"recall":[175],"0.504":[177],"under":[178],"strict":[180],"chronological":[181],"split":[182],"producing":[184],"warning":[186,227],"explanations":[187],"99.6\\%":[189],"directional":[190],"consistency.":[191],"Results":[192],"show":[193],"grounding":[195],"generation":[197],"in":[198],"graph-model":[199],"enables":[201],"auditable":[204],"reporting":[206],"sacrificing":[208],"predictive":[209],"performance.":[210],"provides":[213],"practical":[215],"pathway":[216],"toward":[217],"deployable":[219],"explainable":[220],"AI":[221],"resilience":[229],"management.":[230]},"counts_by_year":[],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2026-03-07T00:00:00"}