{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JJJQY4EWVWD545XWQRYDAV7YLI","short_pith_number":"pith:JJJQY4EW","schema_version":"1.0","canonical_sha256":"4a530c7096ad87de76f684703057f85a0786d30c3cc64cf4ae5125dd7e13f908","source":{"kind":"arxiv","id":"2508.06401","version":3},"attestation_state":"computed","paper":{"title":"A Systematic Literature Review of Retrieval-Augmented Generation: Techniques, Metrics, and Challenges","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.IR"],"primary_cat":"cs.DL","authors_text":"Andrew Brown, Barry Devereux, Muhammad Roman","submitted_at":"2025-08-08T15:37:14Z","abstract_excerpt":"This systematic review of the research literature on retrieval-augmented generation (RAG) provides a focused analysis of the most highly cited studies published between 2020 and May 2025. A total of 128 articles met our inclusion criteria. The records were retrieved from ACM Digital Library, IEEE Xplore, Scopus, ScienceDirect, and the Digital Bibliography and Library Project (DBLP). RAG couples a neural retriever with a generative language model, grounding output in up-to-date, non-parametric memory while retaining the semantic generalisation stored in model weights. Guided by the PRISMA 2020 "},"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":"2508.06401","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DL","submitted_at":"2025-08-08T15:37:14Z","cross_cats_sorted":["cs.AI","cs.CL","cs.IR"],"title_canon_sha256":"fb16c3317c83d7e99a7790f72950aef3e6c9cdb47a12a7c903850a617f923130","abstract_canon_sha256":"dd56eca9ef7b3ce699cbb436f0b6bfa2e1565ef42bdcf4b0d23300890ae4f230"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:07:40.435798Z","signature_b64":"i3Rc6JUozEkpkjgBXD3e1HWLAKaSWwNNXEekP2Nv440Tmxl9aJcAmFj4qeqXGr7AIJWetMtdQWrM9BFQ2qgwBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a530c7096ad87de76f684703057f85a0786d30c3cc64cf4ae5125dd7e13f908","last_reissued_at":"2026-07-05T12:07:40.435393Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:07:40.435393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Systematic Literature Review of Retrieval-Augmented Generation: Techniques, Metrics, and Challenges","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.IR"],"primary_cat":"cs.DL","authors_text":"Andrew Brown, Barry Devereux, Muhammad Roman","submitted_at":"2025-08-08T15:37:14Z","abstract_excerpt":"This systematic review of the research literature on retrieval-augmented generation (RAG) provides a focused analysis of the most highly cited studies published between 2020 and May 2025. A total of 128 articles met our inclusion criteria. The records were retrieved from ACM Digital Library, IEEE Xplore, Scopus, ScienceDirect, and the Digital Bibliography and Library Project (DBLP). RAG couples a neural retriever with a generative language model, grounding output in up-to-date, non-parametric memory while retaining the semantic generalisation stored in model weights. Guided by the PRISMA 2020 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.06401","kind":"arxiv","version":3},"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/2508.06401/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":"2508.06401","created_at":"2026-07-05T12:07:40.435445+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.06401v3","created_at":"2026-07-05T12:07:40.435445+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.06401","created_at":"2026-07-05T12:07:40.435445+00:00"},{"alias_kind":"pith_short_12","alias_value":"JJJQY4EWVWD5","created_at":"2026-07-05T12:07:40.435445+00:00"},{"alias_kind":"pith_short_16","alias_value":"JJJQY4EWVWD545XW","created_at":"2026-07-05T12:07:40.435445+00:00"},{"alias_kind":"pith_short_8","alias_value":"JJJQY4EW","created_at":"2026-07-05T12:07:40.435445+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25533","citing_title":"Security and Privacy in Retrieval-Augmented Generation: Architectures, Threats, Defenses, and Future Directions for Building Trustworthy Systems","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2606.23195","citing_title":"Memory Contagion: Cross-Temporal Propagation of Evaluator Bias via Agent Memory","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JJJQY4EWVWD545XWQRYDAV7YLI","json":"https://pith.science/pith/JJJQY4EWVWD545XWQRYDAV7YLI.json","graph_json":"https://pith.science/api/pith-number/JJJQY4EWVWD545XWQRYDAV7YLI/graph.json","events_json":"https://pith.science/api/pith-number/JJJQY4EWVWD545XWQRYDAV7YLI/events.json","paper":"https://pith.science/paper/JJJQY4EW"},"agent_actions":{"view_html":"https://pith.science/pith/JJJQY4EWVWD545XWQRYDAV7YLI","download_json":"https://pith.science/pith/JJJQY4EWVWD545XWQRYDAV7YLI.json","view_paper":"https://pith.science/paper/JJJQY4EW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.06401&json=true","fetch_graph":"https://pith.science/api/pith-number/JJJQY4EWVWD545XWQRYDAV7YLI/graph.json","fetch_events":"https://pith.science/api/pith-number/JJJQY4EWVWD545XWQRYDAV7YLI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JJJQY4EWVWD545XWQRYDAV7YLI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JJJQY4EWVWD545XWQRYDAV7YLI/action/storage_attestation","attest_author":"https://pith.science/pith/JJJQY4EWVWD545XWQRYDAV7YLI/action/author_attestation","sign_citation":"https://pith.science/pith/JJJQY4EWVWD545XWQRYDAV7YLI/action/citation_signature","submit_replication":"https://pith.science/pith/JJJQY4EWVWD545XWQRYDAV7YLI/action/replication_record"}},"created_at":"2026-07-05T12:07:40.435445+00:00","updated_at":"2026-07-05T12:07:40.435445+00:00"}