{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YINYNYWOMYC2KLPF75U633HYXP","short_pith_number":"pith:YINYNYWO","schema_version":"1.0","canonical_sha256":"c21b86e2ce6605a52de5ff69edecf8bbeda93952eab27bc8bcd5904e2d4daf49","source":{"kind":"arxiv","id":"2506.08074","version":1},"attestation_state":"computed","paper":{"title":"Hierarchical Lexical Graph for Enhanced Multi-Hop Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Abdellah Ghassel, Bryan Thompson, Gabriel Tanase, Hal Cooper, Huzefa Rangwala, Ian Robinson, Soji Adeshina, Vassilis N. Ioannidis, Zhen Han","submitted_at":"2025-06-09T17:58:35Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) grounds large language models in external evidence, yet it still falters when answers must be pieced together across semantically distant documents. We close this gap with the Hierarchical Lexical Graph (HLG), a three-tier index that (i) traces every atomic proposition to its source, (ii) clusters propositions into latent topics, and (iii) links entities and relations to expose cross-document paths. On top of HLG we build two complementary, plug-and-play retrievers: StatementGraphRAG, which performs fine-grained entity-aware beam search over propositions fo"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2506.08074","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-06-09T17:58:35Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"708b96720c37dd7552f0801e72762d34f89ebce9068922911b756186ff749d56","abstract_canon_sha256":"43635830f946a1efc3c5c0e61b24ac5306549040206b391cbde3c0cba9c76506"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:44.448211Z","signature_b64":"gKW5rvfD5C42/ly/F7F3qB4JyIHThD9Q4p2nvK8zuVYIy6MihPdmW19r6oFZbMxAXAkDuIR42D7sSXWDfnVnAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c21b86e2ce6605a52de5ff69edecf8bbeda93952eab27bc8bcd5904e2d4daf49","last_reissued_at":"2026-07-05T11:18:44.447750Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:44.447750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchical Lexical Graph for Enhanced Multi-Hop Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Abdellah Ghassel, Bryan Thompson, Gabriel Tanase, Hal Cooper, Huzefa Rangwala, Ian Robinson, Soji Adeshina, Vassilis N. Ioannidis, Zhen Han","submitted_at":"2025-06-09T17:58:35Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) grounds large language models in external evidence, yet it still falters when answers must be pieced together across semantically distant documents. We close this gap with the Hierarchical Lexical Graph (HLG), a three-tier index that (i) traces every atomic proposition to its source, (ii) clusters propositions into latent topics, and (iii) links entities and relations to expose cross-document paths. On top of HLG we build two complementary, plug-and-play retrievers: StatementGraphRAG, which performs fine-grained entity-aware beam search over propositions fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.08074","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2506.08074/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2506.08074","created_at":"2026-07-05T11:18:44.447802+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.08074v1","created_at":"2026-07-05T11:18:44.447802+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.08074","created_at":"2026-07-05T11:18:44.447802+00:00"},{"alias_kind":"pith_short_12","alias_value":"YINYNYWOMYC2","created_at":"2026-07-05T11:18:44.447802+00:00"},{"alias_kind":"pith_short_16","alias_value":"YINYNYWOMYC2KLPF","created_at":"2026-07-05T11:18:44.447802+00:00"},{"alias_kind":"pith_short_8","alias_value":"YINYNYWO","created_at":"2026-07-05T11:18:44.447802+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YINYNYWOMYC2KLPF75U633HYXP","json":"https://pith.science/pith/YINYNYWOMYC2KLPF75U633HYXP.json","graph_json":"https://pith.science/api/pith-number/YINYNYWOMYC2KLPF75U633HYXP/graph.json","events_json":"https://pith.science/api/pith-number/YINYNYWOMYC2KLPF75U633HYXP/events.json","paper":"https://pith.science/paper/YINYNYWO"},"agent_actions":{"view_html":"https://pith.science/pith/YINYNYWOMYC2KLPF75U633HYXP","download_json":"https://pith.science/pith/YINYNYWOMYC2KLPF75U633HYXP.json","view_paper":"https://pith.science/paper/YINYNYWO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.08074&json=true","fetch_graph":"https://pith.science/api/pith-number/YINYNYWOMYC2KLPF75U633HYXP/graph.json","fetch_events":"https://pith.science/api/pith-number/YINYNYWOMYC2KLPF75U633HYXP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YINYNYWOMYC2KLPF75U633HYXP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YINYNYWOMYC2KLPF75U633HYXP/action/storage_attestation","attest_author":"https://pith.science/pith/YINYNYWOMYC2KLPF75U633HYXP/action/author_attestation","sign_citation":"https://pith.science/pith/YINYNYWOMYC2KLPF75U633HYXP/action/citation_signature","submit_replication":"https://pith.science/pith/YINYNYWOMYC2KLPF75U633HYXP/action/replication_record"}},"created_at":"2026-07-05T11:18:44.447802+00:00","updated_at":"2026-07-05T11:18:44.447802+00:00"}