{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EP4I2DVBYOSVXMAWJMPU6E57GT","short_pith_number":"pith:EP4I2DVB","schema_version":"1.0","canonical_sha256":"23f88d0ea1c3a55bb0164b1f4f13bf34c8b9233fb25b3078c20eeba1a6f3a157","source":{"kind":"arxiv","id":"2412.15272","version":2},"attestation_state":"computed","paper":{"title":"SimGRAG: Leveraging Similar Subgraphs for Knowledge Graphs Driven Retrieval-Augmented Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Wanrui Bian, Weiguo Zheng, Yiwen Pei, Yuzheng Cai, Zhenyue Guo","submitted_at":"2024-12-17T15:40:08Z","abstract_excerpt":"Recent advancements in large language models (LLMs) have shown impressive versatility across various tasks. To eliminate their hallucinations, retrieval-augmented generation (RAG) has emerged as a powerful approach, leveraging external knowledge sources like knowledge graphs (KGs). In this paper, we study the task of KG-driven RAG and propose a novel Similar Graph Enhanced Retrieval-Augmented Generation (SimGRAG) method. It effectively addresses the challenge of aligning query texts and KG structures through a two-stage process: (1) query-to-pattern, which uses an LLM to transform queries into"},"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":"2412.15272","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-17T15:40:08Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"381e9a866963ee545ee8afa95dbd77bfdb31236a1a356a509ae9be3475e3a252","abstract_canon_sha256":"45e84310936341b576f49580e75982e8d262c1f41f59f3add6b17f2a7439a935"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:38.691142Z","signature_b64":"6QfSvjub831hJbqdrsp51IaQqoGBbwBT79A93UqFycA1LUMdURwjioedf+z4WjVnaoTNFsF6eDg+cXiLOvX9Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23f88d0ea1c3a55bb0164b1f4f13bf34c8b9233fb25b3078c20eeba1a6f3a157","last_reissued_at":"2026-07-05T11:11:38.690550Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:38.690550Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SimGRAG: Leveraging Similar Subgraphs for Knowledge Graphs Driven Retrieval-Augmented Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Wanrui Bian, Weiguo Zheng, Yiwen Pei, Yuzheng Cai, Zhenyue Guo","submitted_at":"2024-12-17T15:40:08Z","abstract_excerpt":"Recent advancements in large language models (LLMs) have shown impressive versatility across various tasks. To eliminate their hallucinations, retrieval-augmented generation (RAG) has emerged as a powerful approach, leveraging external knowledge sources like knowledge graphs (KGs). In this paper, we study the task of KG-driven RAG and propose a novel Similar Graph Enhanced Retrieval-Augmented Generation (SimGRAG) method. It effectively addresses the challenge of aligning query texts and KG structures through a two-stage process: (1) query-to-pattern, which uses an LLM to transform queries into"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.15272","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/2412.15272/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":"2412.15272","created_at":"2026-07-05T11:11:38.690606+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.15272v2","created_at":"2026-07-05T11:11:38.690606+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.15272","created_at":"2026-07-05T11:11:38.690606+00:00"},{"alias_kind":"pith_short_12","alias_value":"EP4I2DVBYOSV","created_at":"2026-07-05T11:11:38.690606+00:00"},{"alias_kind":"pith_short_16","alias_value":"EP4I2DVBYOSVXMAW","created_at":"2026-07-05T11:11:38.690606+00:00"},{"alias_kind":"pith_short_8","alias_value":"EP4I2DVB","created_at":"2026-07-05T11:11:38.690606+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/EP4I2DVBYOSVXMAWJMPU6E57GT","json":"https://pith.science/pith/EP4I2DVBYOSVXMAWJMPU6E57GT.json","graph_json":"https://pith.science/api/pith-number/EP4I2DVBYOSVXMAWJMPU6E57GT/graph.json","events_json":"https://pith.science/api/pith-number/EP4I2DVBYOSVXMAWJMPU6E57GT/events.json","paper":"https://pith.science/paper/EP4I2DVB"},"agent_actions":{"view_html":"https://pith.science/pith/EP4I2DVBYOSVXMAWJMPU6E57GT","download_json":"https://pith.science/pith/EP4I2DVBYOSVXMAWJMPU6E57GT.json","view_paper":"https://pith.science/paper/EP4I2DVB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.15272&json=true","fetch_graph":"https://pith.science/api/pith-number/EP4I2DVBYOSVXMAWJMPU6E57GT/graph.json","fetch_events":"https://pith.science/api/pith-number/EP4I2DVBYOSVXMAWJMPU6E57GT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EP4I2DVBYOSVXMAWJMPU6E57GT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EP4I2DVBYOSVXMAWJMPU6E57GT/action/storage_attestation","attest_author":"https://pith.science/pith/EP4I2DVBYOSVXMAWJMPU6E57GT/action/author_attestation","sign_citation":"https://pith.science/pith/EP4I2DVBYOSVXMAWJMPU6E57GT/action/citation_signature","submit_replication":"https://pith.science/pith/EP4I2DVBYOSVXMAWJMPU6E57GT/action/replication_record"}},"created_at":"2026-07-05T11:11:38.690606+00:00","updated_at":"2026-07-05T11:11:38.690606+00:00"}