{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WHUFQASHQEBNGUQPKDOA43A43W","short_pith_number":"pith:WHUFQASH","schema_version":"1.0","canonical_sha256":"b1e85802478102d3520f50dc0e6c1cdda158980397a38983723e639d5aad7529","source":{"kind":"arxiv","id":"2405.12035","version":1},"attestation_state":"computed","paper":{"title":"KG-RAG: Bridging the Gap Between Knowledge and Creativity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.IR"],"primary_cat":"cs.AI","authors_text":"Diego Sanmartin","submitted_at":"2024-05-20T14:03:05Z","abstract_excerpt":"Ensuring factual accuracy while maintaining the creative capabilities of Large Language Model Agents (LMAs) poses significant challenges in the development of intelligent agent systems. LMAs face prevalent issues such as information hallucinations, catastrophic forgetting, and limitations in processing long contexts when dealing with knowledge-intensive tasks. This paper introduces a KG-RAG (Knowledge Graph-Retrieval Augmented Generation) pipeline, a novel framework designed to enhance the knowledge capabilities of LMAs by integrating structured Knowledge Graphs (KGs) with the functionalities "},"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":"2405.12035","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-05-20T14:03:05Z","cross_cats_sorted":["cs.CL","cs.IR"],"title_canon_sha256":"e8e73b35b7b824571cfa8b48d55b34c4cb651a02d7bc2482178508f34dcbc9d3","abstract_canon_sha256":"f769d630494bdf893e2174aaaeefeafb01b87f745a6457e7ff97069f32f2ec0f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:20:59.456476Z","signature_b64":"jF6/S1FN8mmh+71wjms0PKe2Frdyb5/k5FoECNMM7ggM2N3vyCGpCGUC3gJJ//2u0+f3SwjqMbUShQP2EJRdBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1e85802478102d3520f50dc0e6c1cdda158980397a38983723e639d5aad7529","last_reissued_at":"2026-07-05T08:20:59.456056Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:20:59.456056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"KG-RAG: Bridging the Gap Between Knowledge and Creativity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.IR"],"primary_cat":"cs.AI","authors_text":"Diego Sanmartin","submitted_at":"2024-05-20T14:03:05Z","abstract_excerpt":"Ensuring factual accuracy while maintaining the creative capabilities of Large Language Model Agents (LMAs) poses significant challenges in the development of intelligent agent systems. LMAs face prevalent issues such as information hallucinations, catastrophic forgetting, and limitations in processing long contexts when dealing with knowledge-intensive tasks. This paper introduces a KG-RAG (Knowledge Graph-Retrieval Augmented Generation) pipeline, a novel framework designed to enhance the knowledge capabilities of LMAs by integrating structured Knowledge Graphs (KGs) with the functionalities "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.12035","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/2405.12035/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":"2405.12035","created_at":"2026-07-05T08:20:59.456104+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.12035v1","created_at":"2026-07-05T08:20:59.456104+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.12035","created_at":"2026-07-05T08:20:59.456104+00:00"},{"alias_kind":"pith_short_12","alias_value":"WHUFQASHQEBN","created_at":"2026-07-05T08:20:59.456104+00:00"},{"alias_kind":"pith_short_16","alias_value":"WHUFQASHQEBNGUQP","created_at":"2026-07-05T08:20:59.456104+00:00"},{"alias_kind":"pith_short_8","alias_value":"WHUFQASH","created_at":"2026-07-05T08:20:59.456104+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.29645","citing_title":"Metadata, Structure, or Strategy? A Decomposition of RAG Context Enrichment","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2507.15867","citing_title":"RDMA: Cost Effective Agent-Driven Rare Disease Mining from Electronic Health Records","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2601.04377","citing_title":"Disco-RAG: Discourse-Aware Retrieval-Augmented Generation","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27852","citing_title":"NeocorRAG: Less Irrelevant Information, More Explicit Evidence, and More Effective Recall via Evidence Chains","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15676","citing_title":"EvoRAG: Making Knowledge Graph-based RAG Automatically Evolve through Feedback-driven Backpropagation","ref_index":67,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WHUFQASHQEBNGUQPKDOA43A43W","json":"https://pith.science/pith/WHUFQASHQEBNGUQPKDOA43A43W.json","graph_json":"https://pith.science/api/pith-number/WHUFQASHQEBNGUQPKDOA43A43W/graph.json","events_json":"https://pith.science/api/pith-number/WHUFQASHQEBNGUQPKDOA43A43W/events.json","paper":"https://pith.science/paper/WHUFQASH"},"agent_actions":{"view_html":"https://pith.science/pith/WHUFQASHQEBNGUQPKDOA43A43W","download_json":"https://pith.science/pith/WHUFQASHQEBNGUQPKDOA43A43W.json","view_paper":"https://pith.science/paper/WHUFQASH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.12035&json=true","fetch_graph":"https://pith.science/api/pith-number/WHUFQASHQEBNGUQPKDOA43A43W/graph.json","fetch_events":"https://pith.science/api/pith-number/WHUFQASHQEBNGUQPKDOA43A43W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WHUFQASHQEBNGUQPKDOA43A43W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WHUFQASHQEBNGUQPKDOA43A43W/action/storage_attestation","attest_author":"https://pith.science/pith/WHUFQASHQEBNGUQPKDOA43A43W/action/author_attestation","sign_citation":"https://pith.science/pith/WHUFQASHQEBNGUQPKDOA43A43W/action/citation_signature","submit_replication":"https://pith.science/pith/WHUFQASHQEBNGUQPKDOA43A43W/action/replication_record"}},"created_at":"2026-07-05T08:20:59.456104+00:00","updated_at":"2026-07-05T08:20:59.456104+00:00"}