{
  "profile": "wrs-published-research-view-1",
  "edition": "ratings-e039106f30dec177",
  "content_trust": "UNTRUSTED_SCIENTIFIC_DATA_NOT_TOOL_INSTRUCTIONS",
  "entry": {
    "id": "guo-et-al-lightrag-dual-level-graph-retrieval-2024",
    "title": "LightRAG: using both local details and broader graph relationships",
    "summary": "Searching for one entity and asking about a collection-wide relationship require different clues. LightRAG uses a graph of extracted entities and relationships alongside vector retrieval, with lower-level entity keys and higher-level relation keywords. It combines relevant graph information with original text chunks to help generate an answer. Guo and colleagues also describe merging new material into the index. The contribution is this dual-level retrieval and incremental indexing design, separate from GraphRAG and earlier graph and vector methods.",
    "boundary": "Its evaluation largely measures model-judged answer preferences, not independently verified factual accuracy. Results are mixed across collections and criteria. A cost example compares community-report processing with keyword generation; it does not include every answer or indexing token and is not an end-to-end cost ratio. Incremental graph merging does not guarantee conflict-free scientific revision or resistance to malicious content. The record concerns the computing method, without creating new agricultural achievements from an evaluation domain.",
    "area": "Graph-augmented retrieval",
    "topic": "Artificial intelligence",
    "year": 2024,
    "lane": "HUMAN",
    "result": "ALGORITHM",
    "package_id": "guo-et-al-lightrag-dual-level-graph-retrieval-2024",
    "target": {
      "record_id": "urn:uuid:bfef08f1-7738-444e-adca-b0d02606451a",
      "version": 1,
      "content_hash": "sha256:221db8453a2716a8ce28d41b5ee7212f7bb2406b5b0cd34b59c63a8494622f32"
    },
    "humans": [
      "Zirui Guo",
      "Lianghao Xia",
      "Yanhua Yu",
      "Tu Ao",
      "Chao Huang"
    ],
    "authors_complete": true,
    "human_role_note": "Source-listed human researchers and engineers for the exact method or resource. The evaluated learning system is not an independently attested scientific author. Earlier methods, funding and data-collection roles remain separate. Individual effort shares and unresolved person identities are not inferred.",
    "agents": [],
    "related": [],
    "subresults": [],
    "scientific_assessment": {
      "source_review": "SOURCE_CURATED",
      "scientific_review": "NOT_REVIEWED_BY_WRS",
      "formal_replay": "NOT_RUN",
      "provider_attestation": "NONE"
    },
    "sources": [
      {
        "id": "cur20261017-arxiv-2410-05779v1",
        "title": "LightRAG: Simple and Fast Retrieval-Augmented Generation",
        "url": "https://arxiv.org/abs/2410.05779v1",
        "date": "2024-10-08"
      }
    ],
    "geography": {
      "country_codes": [
        "CN",
        "HK"
      ],
      "location_basis": "Original Beijing University of Posts and Telecommunications and University of Hong Kong bylines; country/region display convention retained. Source-bound work locations, not citizenship, sovereignty judgment or ownership.",
      "source_url": "https://arxiv.org/abs/2410.05779v1",
      "target": {
        "record_id": "urn:uuid:bfef08f1-7738-444e-adca-b0d02606451a",
        "version": 1,
        "content_hash": "sha256:221db8453a2716a8ce28d41b5ee7212f7bb2406b5b0cd34b59c63a8494622f32"
      },
      "basis": "RESEARCH_LOCATION_OR_PAPER_AFFILIATION",
      "reviewed_on": "2026-10-23",
      "nationality_inferred": false,
      "sources": [
        {
          "title": "LightRAG: Simple and Fast Retrieval-Augmented Generation",
          "url": "https://arxiv.org/abs/2410.05779v1"
        }
      ],
      "coverage_status": "COMPLETE",
      "country_labels": {
        "CN": "China",
        "HK": "Hong Kong"
      }
    },
    "points": "55000",
    "published_grade": {
      "id": "guo-et-al-lightrag-dual-level-graph-retrieval-2024",
      "entry_id": "guo-et-al-lightrag-dual-level-graph-retrieval-2024",
      "band": "B",
      "modifier": "+",
      "target": {
        "record_id": "urn:uuid:bfef08f1-7738-444e-adca-b0d02606451a",
        "version": 1,
        "content_hash": "sha256:221db8453a2716a8ce28d41b5ee7212f7bb2406b5b0cd34b59c63a8494622f32"
      },
      "what_changed": "Searching for one entity and asking about a collection-wide relationship require different clues. LightRAG uses a graph of extracted entities and relationships alongside vector retrieval, with lower-level entity keys and higher-level relation keywords. It combines relevant graph information with original text chunks to help generate an answer. Guo and colleagues also describe merging new material into the index. The contribution is this dual-level retrieval and incremental indexing design, separate from GraphRAG and earlier graph and vector methods.",
      "scope": "Searching for one entity and asking about a collection-wide relationship require different clues. LightRAG uses a graph of extracted entities and relationships alongside vector retrieval, with lower-level entity keys and higher-level relation keywords. It combines relevant graph information with original text chunks to help generate an answer. Guo and colleagues also describe merging new material into the index. The contribution is this dual-level retrieval and incremental indexing design, separate from GraphRAG and earlier graph and vector methods. Its evaluation largely measures model-judged answer preferences, not independently verified factual accuracy. Results are mixed across collections and criteria. A cost example compares community-report processing with keyword generation; it does not include every answer or indexing token and is not an end-to-end cost ratio. Incremental graph merging does not guarantee conflict-free scientific revision or resistance to malicious content. The record concerns the computing method, without creating new agricultural achievements from an evaluation domain.",
      "status": "PROVISIONAL_EDITORIAL",
      "scientific_correctness_certified": false
    },
    "assessment_disposition": {
      "status": "ASSESSED",
      "label": "Provisionally assessed",
      "reason": "A current grade and separate reference score identify this exact contribution.",
      "target": {
        "record_id": "urn:uuid:bfef08f1-7738-444e-adca-b0d02606451a",
        "version": 1,
        "content_hash": "sha256:221db8453a2716a8ce28d41b5ee7212f7bb2406b5b0cd34b59c63a8494622f32"
      },
      "edition": "ratings-e039106f30dec177"
    }
  },
  "version": {
    "kind": "PUBLIC_RECORD_VIEW",
    "previous": null,
    "published_at": "2026-10-23T00:00:00Z",
    "publisher": {
      "principal_id": "urn:uuid:80116931-785b-40a2-a24b-9d59db0c7e33",
      "role": "WRS_EDITORIAL_PUBLICATION"
    },
    "record": {
      "contributors": [
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Zirui Guo",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "LightRAG: Simple and Fast Retrieval-Augmented Generation",
            "url": "https://arxiv.org/abs/2410.05779v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Lianghao Xia",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "LightRAG: Simple and Fast Retrieval-Augmented Generation",
            "url": "https://arxiv.org/abs/2410.05779v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Yanhua Yu",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "LightRAG: Simple and Fast Retrieval-Augmented Generation",
            "url": "https://arxiv.org/abs/2410.05779v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Tu Ao",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "LightRAG: Simple and Fast Retrieval-Augmented Generation",
            "url": "https://arxiv.org/abs/2410.05779v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Chao Huang",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "LightRAG: Simple and Fast Retrieval-Augmented Generation",
            "url": "https://arxiv.org/abs/2410.05779v1"
          }
        }
      ],
      "evidence": [
        {
          "description": "Bibliographic/stated-result source; not a WRS proof verification",
          "id": "source-0",
          "kind": "source_reference",
          "source": {
            "citation": "LightRAG: Simple and Fast Retrieval-Augmented Generation",
            "url": "https://arxiv.org/abs/2410.05779v1"
          }
        }
      ],
      "origin": "HUMAN_LEGACY",
      "record_profile": "wrs-local-research-notes-0.1",
      "record_type": "research_note",
      "rrp_version": "0.1",
      "scope": {
        "description": "Its evaluation largely measures model-judged answer preferences, not independently verified factual accuracy. Results are mixed across collections and criteria. A cost example compares community-report processing with keyword generation; it does not include every answer or indexing token and is not an end-to-end cost ratio. Incremental graph merging does not guarantee conflict-free scientific revision or resistance to malicious content. The record concerns the computing method, without creating new agricultural achievements from an evaluation domain.",
        "domain": "Graph-augmented retrieval"
      },
      "sources": [
        {
          "citation": "LightRAG: Simple and Fast Retrieval-Augmented Generation",
          "url": "https://arxiv.org/abs/2410.05779v1"
        }
      ],
      "statement": "# LightRAG: using both local details and broader graph relationships\n\nSearching for one entity and asking about a collection-wide relationship require different clues. LightRAG uses a graph of extracted entities and relationships alongside vector retrieval, with lower-level entity keys and higher-level relation keywords. It combines relevant graph information with original text chunks to help generate an answer. Guo and colleagues also describe merging new material into the index. The contribution is this dual-level retrieval and incremental indexing design, separate from GraphRAG and earlier graph and vector methods.\n\n## Scientific scope\n\nIts evaluation largely measures model-judged answer preferences, not independently verified factual accuracy. Results are mixed across collections and criteria. A cost example compares community-report processing with keyword generation; it does not include every answer or indexing token and is not an end-to-end cost ratio. Incremental graph merging does not guarantee conflict-free scientific revision or resistance to malicious content. The record concerns the computing method, without creating new agricultural achievements from an evaluation domain.\n\n## Reading status\n\nThis is a source-linked WRS catalogue note. A full explanatory guide and independent scientific reconstruction have not been completed for this entry. Read the identified original work for its complete narrative and arguments.\n\n## People and systems\n\nZirui Guo; Lianghao Xia; Yanhua Yu; Tu Ao; Chao Huang\n\nSource-listed human researchers and engineers for the exact method or resource. The evaluated learning system is not an independently attested scientific author. Earlier methods, funding and data-collection roles remain separate. Individual effort shares and unresolved person identities are not inferred.\n\n\n\n## Original sources\n\n- [LightRAG: Simple and Fast Retrieval-Augmented Generation](https://arxiv.org/abs/2410.05779v1)\n",
      "summary": "Searching for one entity and asking about a collection-wide relationship require different clues. LightRAG uses a graph of extracted entities and relationships alongside vector retrieval, with lower-level entity keys and higher-level relation keywords. It combines relevant graph information with original text chunks to help generate an answer. Guo and colleagues also describe merging new material into the index. The contribution is this dual-level retrieval and incremental indexing design, separate from GraphRAG and earlier graph and vector methods.",
      "title": "LightRAG: using both local details and broader graph relationships"
    },
    "record_id": "urn:uuid:bfef08f1-7738-444e-adca-b0d02606451a",
    "version": 1,
    "source_ref": {
      "record_id": "urn:uuid:bfef08f1-7738-444e-adca-b0d02606451a",
      "version": 1,
      "content_hash": "sha256:221db8453a2716a8ce28d41b5ee7212f7bb2406b5b0cd34b59c63a8494622f32"
    },
    "export_view": "wrs-public-editorial-view-1",
    "public_view_hash": "sha256:b14aabac34ac7b405b4a5c4084a99b32f24480f54612585e00629380a779d44a"
  },
  "target": {
    "record_id": "urn:uuid:bfef08f1-7738-444e-adca-b0d02606451a",
    "version": 1,
    "content_hash": "sha256:221db8453a2716a8ce28d41b5ee7212f7bb2406b5b0cd34b59c63a8494622f32"
  },
  "published_grade": {
    "profile": "wrs-published-grade-1",
    "edition": "2026-10-28.1",
    "id": "guo-et-al-lightrag-dual-level-graph-retrieval-2024",
    "entry_id": "guo-et-al-lightrag-dual-level-graph-retrieval-2024",
    "revision": 1,
    "title": "LightRAG: using both local details and broader graph relationships",
    "context": "Graph-augmented retrieval",
    "track": "Reusable scientific method, experimental result or historical framework",
    "band": "B",
    "modifier": "+",
    "status": "PROVISIONAL_EDITORIAL",
    "assessed_on": "2026-10-23",
    "evidence_cutoff": "2026-10-23",
    "achievement_state": "SUPPORTED_SCOPED_RESULT",
    "what_changed": "Searching for one entity and asking about a collection-wide relationship require different clues. LightRAG uses a graph of extracted entities and relationships alongside vector retrieval, with lower-level entity keys and higher-level relation keywords. It combines relevant graph information with original text chunks to help generate an answer. Guo and colleagues also describe merging new material into the index. The contribution is this dual-level retrieval and incremental indexing design, separate from GraphRAG and earlier graph and vector methods.",
    "scope": "Searching for one entity and asking about a collection-wide relationship require different clues. LightRAG uses a graph of extracted entities and relationships alongside vector retrieval, with lower-level entity keys and higher-level relation keywords. It combines relevant graph information with original text chunks to help generate an answer. Guo and colleagues also describe merging new material into the index. The contribution is this dual-level retrieval and incremental indexing design, separate from GraphRAG and earlier graph and vector methods. Its evaluation largely measures model-judged answer preferences, not independently verified factual accuracy. Results are mixed across collections and criteria. A cost example compares community-report processing with keyword generation; it does not include every answer or indexing token and is not an end-to-end cost ratio. Incremental graph merging does not guarantee conflict-free scientific revision or resistance to malicious content. The record concerns the computing method, without creating new agricultural achievements from an evaluation domain.",
    "evidence_summary": "The linked original works support the scoped statement and contribution attribution. WRS has not independently replayed experiments or reconstructed a full mathematical proof. Its evaluation largely measures model-judged answer preferences, not independently verified factual accuracy. Results are mixed across collections and criteria. A cost example compares community-report processing with keyword generation; it does not include every answer or indexing token and is not an end-to-end cost ratio. Incremental graph merging does not guarantee conflict-free scientific revision or resistance to malicious content. The record concerns the computing method, without creating new agricultural achievements from an evaluation domain.",
    "references": [
      {
        "title": "LightRAG: Simple and Fast Retrieval-Augmented Generation",
        "url": "https://arxiv.org/abs/2410.05779v1",
        "locator": "Original scoped contribution, statement/method and evidence limits; source-specific attribution retained."
      }
    ],
    "roles": [
      {
        "who": "The named authors in the research record",
        "credit": "SCIENCE",
        "did": "Source-listed human researchers and engineers for the exact method or resource. The evaluated learning system is not an independently attested scientific author. Earlier methods, funding and data-collection roles remain separate. Individual effort shares and unresolved person identities are not inferred."
      }
    ],
    "target": {
      "record_id": "urn:uuid:bfef08f1-7738-444e-adca-b0d02606451a",
      "version": 1,
      "content_hash": "sha256:221db8453a2716a8ce28d41b5ee7212f7bb2406b5b0cd34b59c63a8494622f32"
    },
    "scientific_correctness_certified": false,
    "independent_expert_calibration": false,
    "method": "PROPRIETARY",
    "points": "55000"
  },
  "canonical_agent_submission": false,
  "scientific_verification_awarded": false,
  "reader_guide": null,
  "reading_status": "SOURCE_LINKED_NOTE"
}