{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QZ4YWNREFXWSNTNRGAIS4LPP75","short_pith_number":"pith:QZ4YWNRE","schema_version":"1.0","canonical_sha256":"86798b36242ded26cdb130112e2defff43d47be3aaec912947c8967bf8026942","source":{"kind":"arxiv","id":"2507.18910","version":1},"attestation_state":"computed","paper":{"title":"A Systematic Review of Key Retrieval-Augmented Generation (RAG) Systems: Progress, Gaps, and Future Directions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Ademola Glory Folashade, Agada Joseph Oche, Arpan Biswas, Tirthankar Ghosal","submitted_at":"2025-07-25T03:05:46Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) represents a major advancement in natural language processing (NLP), combining large language models (LLMs) with information retrieval systems to enhance factual grounding, accuracy, and contextual relevance. This paper presents a comprehensive systematic review of RAG, tracing its evolution from early developments in open domain question answering to recent state-of-the-art implementations across diverse applications. The review begins by outlining the motivations behind RAG, particularly its ability to mitigate hallucinations and outdated knowledge in par"},"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":"2507.18910","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-25T03:05:46Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"324c13b92421ad7a3df8251cc5e578868011d47dbb464c9c0db93cd003cc8a78","abstract_canon_sha256":"d4a93324add4c7cb14d41c269d88d0f9ea988168003c395f366d43fbc6b399c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:43:16.021346Z","signature_b64":"ovjuXFgJehacyv8frF9UXiH+WmelmZ9p9eqpkZXwlE857e61EC2MJp7cmWJFItEy8WUc7mlBetTofqN+JOYcDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86798b36242ded26cdb130112e2defff43d47be3aaec912947c8967bf8026942","last_reissued_at":"2026-07-05T11:43:16.020818Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:43:16.020818Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Systematic Review of Key Retrieval-Augmented Generation (RAG) Systems: Progress, Gaps, and Future Directions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Ademola Glory Folashade, Agada Joseph Oche, Arpan Biswas, Tirthankar Ghosal","submitted_at":"2025-07-25T03:05:46Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) represents a major advancement in natural language processing (NLP), combining large language models (LLMs) with information retrieval systems to enhance factual grounding, accuracy, and contextual relevance. This paper presents a comprehensive systematic review of RAG, tracing its evolution from early developments in open domain question answering to recent state-of-the-art implementations across diverse applications. The review begins by outlining the motivations behind RAG, particularly its ability to mitigate hallucinations and outdated knowledge in par"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.18910","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/2507.18910/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":"2507.18910","created_at":"2026-07-05T11:43:16.020883+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.18910v1","created_at":"2026-07-05T11:43:16.020883+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.18910","created_at":"2026-07-05T11:43:16.020883+00:00"},{"alias_kind":"pith_short_12","alias_value":"QZ4YWNREFXWS","created_at":"2026-07-05T11:43:16.020883+00:00"},{"alias_kind":"pith_short_16","alias_value":"QZ4YWNREFXWSNTNR","created_at":"2026-07-05T11:43:16.020883+00:00"},{"alias_kind":"pith_short_8","alias_value":"QZ4YWNRE","created_at":"2026-07-05T11:43:16.020883+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.19776","citing_title":"Development and Preliminary Evaluation of a Domain-Specific Large Language Model for Tuberculosis Care in South Africa","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05538","citing_title":"AgenticRAG: Agentic Retrieval for Enterprise Knowledge Bases","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01302","citing_title":"Beyond Semantic Relevance: Counterfactual Risk Minimization for Robust Retrieval-Augmented Generation","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19516","citing_title":"From Experience to Skill: Multi-Agent Generative Engine Optimization via Reusable Strategy Learning","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14222","citing_title":"Adaptive Query Routing: A Tier-Based Framework for Hybrid Retrieval Across Financial, Legal, and Medical Documents","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17843","citing_title":"Learning from AVA: Early Lessons from a Curated and Trustworthy Generative AI for Policy and Development Research","ref_index":77,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QZ4YWNREFXWSNTNRGAIS4LPP75","json":"https://pith.science/pith/QZ4YWNREFXWSNTNRGAIS4LPP75.json","graph_json":"https://pith.science/api/pith-number/QZ4YWNREFXWSNTNRGAIS4LPP75/graph.json","events_json":"https://pith.science/api/pith-number/QZ4YWNREFXWSNTNRGAIS4LPP75/events.json","paper":"https://pith.science/paper/QZ4YWNRE"},"agent_actions":{"view_html":"https://pith.science/pith/QZ4YWNREFXWSNTNRGAIS4LPP75","download_json":"https://pith.science/pith/QZ4YWNREFXWSNTNRGAIS4LPP75.json","view_paper":"https://pith.science/paper/QZ4YWNRE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.18910&json=true","fetch_graph":"https://pith.science/api/pith-number/QZ4YWNREFXWSNTNRGAIS4LPP75/graph.json","fetch_events":"https://pith.science/api/pith-number/QZ4YWNREFXWSNTNRGAIS4LPP75/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QZ4YWNREFXWSNTNRGAIS4LPP75/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QZ4YWNREFXWSNTNRGAIS4LPP75/action/storage_attestation","attest_author":"https://pith.science/pith/QZ4YWNREFXWSNTNRGAIS4LPP75/action/author_attestation","sign_citation":"https://pith.science/pith/QZ4YWNREFXWSNTNRGAIS4LPP75/action/citation_signature","submit_replication":"https://pith.science/pith/QZ4YWNREFXWSNTNRGAIS4LPP75/action/replication_record"}},"created_at":"2026-07-05T11:43:16.020883+00:00","updated_at":"2026-07-05T11:43:16.020883+00:00"}