{"paper":{"title":"Hypergraph Enterprise Agentic Reasoner over Heterogeneous Business Systems","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"HEAR uses a stratified hypergraph ontology to reach up to 94.7% accuracy on supply-chain root cause analysis without retraining LLMs.","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Cheng cheng, Duogong Yan, Enyu Li, Jianan Wang, Jiangyi Chen, Jiangyong Xie, Ling Wang, Songnan Liu, Xin Liu, Yihan Zhu, Yu Xiao","submitted_at":"2026-05-14T01:57:59Z","abstract_excerpt":"Applying Large Language Models (LLMs) to heterogeneous enterprise systems is hindered by hallucinations and failures in multi-hop, n-ary reasoning. Existing paradigms (e.g., GraphRAG, NL2SQL) lack the semantic grounding and auditable execution required for these complex environments. We introduce HEAR, an enterprise agentic reasoner built on a Stratified Hypergraph Ontology. Its base Graph Layer virtualizes provenance-aware data interfaces, while the Hyperedge Layer encodes n-ary business rules and procedural protocols. Operating an evidence-driven reasoning loop, HEAR dynamically orchestrates"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Evaluations on supply-chain tasks, including order fulfillment blockage root cause analysis (RCA), show HEAR achieves up to 94.7% accuracy.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That a Stratified Hypergraph Ontology can be constructed and maintained at scale for arbitrary heterogeneous business systems while preserving both semantic grounding and procedural fidelity.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"HEAR uses a stratified hypergraph ontology to orchestrate evidence-driven multi-hop reasoning over heterogeneous business systems, reaching 94.7% accuracy on supply-chain root-cause tasks with open-weight models.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"HEAR uses a stratified hypergraph ontology to reach up to 94.7% accuracy on supply-chain root cause analysis without retraining LLMs.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"170b4edcd368637863c17ad3a4b87fd94ba70ca1d30f5d369335ea40daaecef7"},"source":{"id":"2605.14259","kind":"arxiv","version":1},"verdict":{"id":"debd234c-f58d-442f-9ffb-d0dc09ec4604","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T02:31:28.659975Z","strongest_claim":"Evaluations on supply-chain tasks, including order fulfillment blockage root cause analysis (RCA), show HEAR achieves up to 94.7% accuracy.","one_line_summary":"HEAR uses a stratified hypergraph ontology to orchestrate evidence-driven multi-hop reasoning over heterogeneous business systems, reaching 94.7% accuracy on supply-chain root-cause tasks with open-weight models.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That a Stratified Hypergraph Ontology can be constructed and maintained at scale for arbitrary heterogeneous business systems while preserving both semantic grounding and procedural fidelity.","pith_extraction_headline":"HEAR uses a stratified hypergraph ontology to reach up to 94.7% accuracy on supply-chain root cause analysis without retraining LLMs."},"references":{"count":82,"sample":[{"doi":"","year":1975,"title":"Efficient string matching: an aid to bibliographic search","work_id":"15e93e30-a10f-418a-bb6c-4aec1f942b82","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"arXiv preprint arXiv:2510.06265 (2025)","work_id":"2f7f0af1-9a86-47d0-9963-13cfcf3058ee","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"A survey on hypergraph representation learning.ACM Computing Surveys (CSUR), 2023","work_id":"43491a4e-9741-4533-b7e5-e58c09887d33","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2026,"title":"When Iterative RAG Beats Ideal Evidence: A Diagnostic Study in Scientific Multi-hop Question Answering","work_id":"69e23a73-669e-4f0a-a03b-86b919baa15e","ref_index":4,"cited_arxiv_id":"2601.19827","is_internal_anchor":true},{"doi":"","year":2016,"title":"Bartholdi, III and Steven T","work_id":"61be268f-3c7e-4c50-b2c7-b12ff20d7bc9","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":82,"snapshot_sha256":"c0f9f27e1013c8dccd091135bf78994d0516cc6f58bd9a620944b08f373a0dcd","internal_anchors":5},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}