{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CTM4TSVVDKKV43GQ4GCDKO273K","short_pith_number":"pith:CTM4TSVV","schema_version":"1.0","canonical_sha256":"14d9c9cab51a955e6cd0e184353b5fda97cd2e9374d3500ecaef5c78ce7f5499","source":{"kind":"arxiv","id":"2503.10677","version":2},"attestation_state":"computed","paper":{"title":"A Survey on Knowledge-Oriented Retrieval-Augmented Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bohou Zhang, Daoyu Wang, Enhong Chen, Huijie Liu, Jiawei Cao, Jie Ma, Jie Ouyang, Li Li, Mingyue Cheng, Qi Liu, Shuo Yu, Yucong Luo","submitted_at":"2025-03-11T01:59:35Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) has gained significant attention in recent years for its potential to enhance natural language understanding and generation by combining large-scale retrieval systems with generative models. RAG leverages external knowledge sources, such as documents, databases, or structured data, to improve model performance and generate more accurate and contextually relevant outputs. This survey aims to provide a comprehensive overview of RAG by examining its fundamental components, including retrieval mechanisms, generation processes, and the integration between the tw"},"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":"2503.10677","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-11T01:59:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0dd221839afd21d8fa1192aab5cf0ba683888d5ad396537378a49c4b31174eb7","abstract_canon_sha256":"7b8a8fc58d525a5dc0bfc932b5160ab5e28960cc97984e2d365d5cf35d2041f1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:32:41.682216Z","signature_b64":"Iupm1ek+B60Ed8EAsG/bTBh7JwD0pishROPY6sL0by5Ho+XyuuGExrAuVPYKBN9c1xo99oowU065VSu7SK4WCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14d9c9cab51a955e6cd0e184353b5fda97cd2e9374d3500ecaef5c78ce7f5499","last_reissued_at":"2026-07-05T10:32:41.681274Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:32:41.681274Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey on Knowledge-Oriented Retrieval-Augmented Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bohou Zhang, Daoyu Wang, Enhong Chen, Huijie Liu, Jiawei Cao, Jie Ma, Jie Ouyang, Li Li, Mingyue Cheng, Qi Liu, Shuo Yu, Yucong Luo","submitted_at":"2025-03-11T01:59:35Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) has gained significant attention in recent years for its potential to enhance natural language understanding and generation by combining large-scale retrieval systems with generative models. RAG leverages external knowledge sources, such as documents, databases, or structured data, to improve model performance and generate more accurate and contextually relevant outputs. This survey aims to provide a comprehensive overview of RAG by examining its fundamental components, including retrieval mechanisms, generation processes, and the integration between the tw"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.10677","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/2503.10677/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":"2503.10677","created_at":"2026-07-05T10:32:41.681407+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.10677v2","created_at":"2026-07-05T10:32:41.681407+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.10677","created_at":"2026-07-05T10:32:41.681407+00:00"},{"alias_kind":"pith_short_12","alias_value":"CTM4TSVVDKKV","created_at":"2026-07-05T10:32:41.681407+00:00"},{"alias_kind":"pith_short_16","alias_value":"CTM4TSVVDKKV43GQ","created_at":"2026-07-05T10:32:41.681407+00:00"},{"alias_kind":"pith_short_8","alias_value":"CTM4TSVV","created_at":"2026-07-05T10:32:41.681407+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06641","citing_title":"Healthier LLMs: Retrieval-Augmented Generation for Public Health Question Answering","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2606.25338","citing_title":"Hybrid-IR: Dual-Path Hybrid Retrieval with Iterative Reasoning for Complex Medical Question Answering","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00508","citing_title":"When RAG Meets Query Planning: Logical Query Trees for Resolving Exploratory Reasoning Problems","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00013","citing_title":"GRACE-RAG: Governed Retrieval Architecture for Canonical Evidence Synthesis, Enabling Lightweight Deployment in Closed-Domain Institutional Settings","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00508","citing_title":"When RAG Meets Query Planning: Logical Query Trees for Resolving Exploratory Reasoning Problems","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01413","citing_title":"Differentially Private Datastore Generation for Retrieval-Augmented Inference","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27826","citing_title":"NormAct: A Benchmark for Hidden Social Norm Compliance in Embodied Planning","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2502.13957","citing_title":"Supervising the search process produces reliable and generalizable information-seeking agents","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2511.11653","citing_title":"GroupRank: A Groupwise Paradigm for Effective and Efficient Passage Reranking with LLMs","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2601.15170","citing_title":"Multi-Dimensional Knowledge Profiling with Large-Scale Literature Database and Hierarchical Retrieval","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2507.13334","citing_title":"A Survey of Context Engineering for Large Language Models","ref_index":170,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01965","citing_title":"Retrieval with Multiple Query Vectors through Anomalous Pattern Detection","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10384","citing_title":"Context-KG: Context-Aware Knowledge Graph Visualization with User Preferences and Ontological Guidance","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CTM4TSVVDKKV43GQ4GCDKO273K","json":"https://pith.science/pith/CTM4TSVVDKKV43GQ4GCDKO273K.json","graph_json":"https://pith.science/api/pith-number/CTM4TSVVDKKV43GQ4GCDKO273K/graph.json","events_json":"https://pith.science/api/pith-number/CTM4TSVVDKKV43GQ4GCDKO273K/events.json","paper":"https://pith.science/paper/CTM4TSVV"},"agent_actions":{"view_html":"https://pith.science/pith/CTM4TSVVDKKV43GQ4GCDKO273K","download_json":"https://pith.science/pith/CTM4TSVVDKKV43GQ4GCDKO273K.json","view_paper":"https://pith.science/paper/CTM4TSVV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.10677&json=true","fetch_graph":"https://pith.science/api/pith-number/CTM4TSVVDKKV43GQ4GCDKO273K/graph.json","fetch_events":"https://pith.science/api/pith-number/CTM4TSVVDKKV43GQ4GCDKO273K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CTM4TSVVDKKV43GQ4GCDKO273K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CTM4TSVVDKKV43GQ4GCDKO273K/action/storage_attestation","attest_author":"https://pith.science/pith/CTM4TSVVDKKV43GQ4GCDKO273K/action/author_attestation","sign_citation":"https://pith.science/pith/CTM4TSVVDKKV43GQ4GCDKO273K/action/citation_signature","submit_replication":"https://pith.science/pith/CTM4TSVVDKKV43GQ4GCDKO273K/action/replication_record"}},"created_at":"2026-07-05T10:32:41.681407+00:00","updated_at":"2026-07-05T10:32:41.681407+00:00"}