{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NXJUEOLE3O3KST4RIFRRSNVYZP","short_pith_number":"pith:NXJUEOLE","schema_version":"1.0","canonical_sha256":"6dd3423964dbb6a94f9141631936b8cbd8ac63dbe153f8445ab58138a9add877","source":{"kind":"arxiv","id":"2502.12442","version":2},"attestation_state":"computed","paper":{"title":"HopRAG: Multi-Hop Reasoning for Logic-Aware Retrieval-Augmented Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Feiyu Xiong, Hao Liu, Qinhan Yu, Wentao Zhang, Xi Chen, Zhengren Wang, Zhiyu Li","submitted_at":"2025-02-18T02:24:42Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) systems often struggle with imperfect retrieval, as traditional retrievers focus on lexical or semantic similarity rather than logical relevance. To address this, we propose \\textbf{HopRAG}, a novel RAG framework that augments retrieval with logical reasoning through graph-structured knowledge exploration. During indexing, HopRAG constructs a passage graph, with text chunks as vertices and logical connections established via LLM-generated pseudo-queries as edges. During retrieval, it employs a \\textit{retrieve-reason-prune} mechanism: starting with lexicall"},"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":"2502.12442","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-02-18T02:24:42Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"791fca52a30dfe9cdb29953793a6f6601706e850bb9b6b10630704d10c9dbe12","abstract_canon_sha256":"7a4ccc9f2a823d56a9e5d2097e9d1957c8a2e27c82f44cce5877414fd26d428b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:08.663408Z","signature_b64":"1EQ6uCbT/Xl3ZgLXytSxNnFd0Ti0JWpfT9T0CFcJhVfUN+EPjeDmJ22AKd0FX7+yZnbzoVk+3hTL1nDJ1FeuBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6dd3423964dbb6a94f9141631936b8cbd8ac63dbe153f8445ab58138a9add877","last_reissued_at":"2026-07-05T11:09:08.662968Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:08.662968Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HopRAG: Multi-Hop Reasoning for Logic-Aware Retrieval-Augmented Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Feiyu Xiong, Hao Liu, Qinhan Yu, Wentao Zhang, Xi Chen, Zhengren Wang, Zhiyu Li","submitted_at":"2025-02-18T02:24:42Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) systems often struggle with imperfect retrieval, as traditional retrievers focus on lexical or semantic similarity rather than logical relevance. To address this, we propose \\textbf{HopRAG}, a novel RAG framework that augments retrieval with logical reasoning through graph-structured knowledge exploration. During indexing, HopRAG constructs a passage graph, with text chunks as vertices and logical connections established via LLM-generated pseudo-queries as edges. During retrieval, it employs a \\textit{retrieve-reason-prune} mechanism: starting with lexicall"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.12442","kind":"arxiv","version":2},"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/2502.12442/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":"2502.12442","created_at":"2026-07-05T11:09:08.663022+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.12442v2","created_at":"2026-07-05T11:09:08.663022+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.12442","created_at":"2026-07-05T11:09:08.663022+00:00"},{"alias_kind":"pith_short_12","alias_value":"NXJUEOLE3O3K","created_at":"2026-07-05T11:09:08.663022+00:00"},{"alias_kind":"pith_short_16","alias_value":"NXJUEOLE3O3KST4R","created_at":"2026-07-05T11:09:08.663022+00:00"},{"alias_kind":"pith_short_8","alias_value":"NXJUEOLE","created_at":"2026-07-05T11:09:08.663022+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05415","citing_title":"Executable Schema Contracts: From Automatic Ingestion to Multi-Source Retrieval","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2506.04390","citing_title":"Through the Stealth Lens: Attention-Aware Defenses Against Poisoning in RAG","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22843","citing_title":"Structure Guided Retrieval-Augmented Generation for Factual Queries","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NXJUEOLE3O3KST4RIFRRSNVYZP","json":"https://pith.science/pith/NXJUEOLE3O3KST4RIFRRSNVYZP.json","graph_json":"https://pith.science/api/pith-number/NXJUEOLE3O3KST4RIFRRSNVYZP/graph.json","events_json":"https://pith.science/api/pith-number/NXJUEOLE3O3KST4RIFRRSNVYZP/events.json","paper":"https://pith.science/paper/NXJUEOLE"},"agent_actions":{"view_html":"https://pith.science/pith/NXJUEOLE3O3KST4RIFRRSNVYZP","download_json":"https://pith.science/pith/NXJUEOLE3O3KST4RIFRRSNVYZP.json","view_paper":"https://pith.science/paper/NXJUEOLE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.12442&json=true","fetch_graph":"https://pith.science/api/pith-number/NXJUEOLE3O3KST4RIFRRSNVYZP/graph.json","fetch_events":"https://pith.science/api/pith-number/NXJUEOLE3O3KST4RIFRRSNVYZP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NXJUEOLE3O3KST4RIFRRSNVYZP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NXJUEOLE3O3KST4RIFRRSNVYZP/action/storage_attestation","attest_author":"https://pith.science/pith/NXJUEOLE3O3KST4RIFRRSNVYZP/action/author_attestation","sign_citation":"https://pith.science/pith/NXJUEOLE3O3KST4RIFRRSNVYZP/action/citation_signature","submit_replication":"https://pith.science/pith/NXJUEOLE3O3KST4RIFRRSNVYZP/action/replication_record"}},"created_at":"2026-07-05T11:09:08.663022+00:00","updated_at":"2026-07-05T11:09:08.663022+00:00"}