{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DQFQPTTBN7KHV4QGL2RBA25L3P","short_pith_number":"pith:DQFQPTTB","schema_version":"1.0","canonical_sha256":"1c0b07ce616fd47af2065ea2106babdbfd550997de03b56df5cb24ab62654f7e","source":{"kind":"arxiv","id":"2410.12837","version":1},"attestation_state":"computed","paper":{"title":"A Comprehensive Survey of Retrieval-Augmented Generation (RAG): Evolution, Current Landscape and Future Directions","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Rajesh Ranjan, Shailja Gupta, Surya Narayan Singh","submitted_at":"2024-10-03T22:29:47Z","abstract_excerpt":"This paper presents a comprehensive study of Retrieval-Augmented Generation (RAG), tracing its evolution from foundational concepts to the current state of the art. RAG combines retrieval mechanisms with generative language models to enhance the accuracy of outputs, addressing key limitations of LLMs. The study explores the basic architecture of RAG, focusing on how retrieval and generation are integrated to handle knowledge-intensive tasks. A detailed review of the significant technological advancements in RAG is provided, including key innovations in retrieval-augmented language models and a"},"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":"2410.12837","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-03T22:29:47Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"222624256c1965e9ac2ed0a64472c93158f8e9c2555ec1b9da4d3968b72e3472","abstract_canon_sha256":"c89b23cf0eb5accdba92cb939d5c29ae03527989b11d80e3e8e82d0bf46ede69"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:21:51.634920Z","signature_b64":"Z20yY9uJMFinA2Na8Aam28co+rBt5qP+YgLU2MD8Ev0VXAh3EcmE9yk5jcZb97clSYKxTun4BZDk1wxjX5bLBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c0b07ce616fd47af2065ea2106babdbfd550997de03b56df5cb24ab62654f7e","last_reissued_at":"2026-07-05T09:21:51.634448Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:21:51.634448Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Comprehensive Survey of Retrieval-Augmented Generation (RAG): Evolution, Current Landscape and Future Directions","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Rajesh Ranjan, Shailja Gupta, Surya Narayan Singh","submitted_at":"2024-10-03T22:29:47Z","abstract_excerpt":"This paper presents a comprehensive study of Retrieval-Augmented Generation (RAG), tracing its evolution from foundational concepts to the current state of the art. RAG combines retrieval mechanisms with generative language models to enhance the accuracy of outputs, addressing key limitations of LLMs. The study explores the basic architecture of RAG, focusing on how retrieval and generation are integrated to handle knowledge-intensive tasks. A detailed review of the significant technological advancements in RAG is provided, including key innovations in retrieval-augmented language models and a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12837","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/2410.12837/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":"2410.12837","created_at":"2026-07-05T09:21:51.634506+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.12837v1","created_at":"2026-07-05T09:21:51.634506+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12837","created_at":"2026-07-05T09:21:51.634506+00:00"},{"alias_kind":"pith_short_12","alias_value":"DQFQPTTBN7KH","created_at":"2026-07-05T09:21:51.634506+00:00"},{"alias_kind":"pith_short_16","alias_value":"DQFQPTTBN7KHV4QG","created_at":"2026-07-05T09:21:51.634506+00:00"},{"alias_kind":"pith_short_8","alias_value":"DQFQPTTB","created_at":"2026-07-05T09:21:51.634506+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":16,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07858","citing_title":"Agentic AI and Retrieval-Augmented Models in Straight-Through Underwriting","ref_index":47,"is_internal_anchor":true},{"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":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28349","citing_title":"HMARS: A Hierarchical Multi-Agent Memory System for Long-Context Reasoning","ref_index":81,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20173","citing_title":"Qiskit Code Migration with LLMs","ref_index":99,"is_internal_anchor":false},{"citing_arxiv_id":"2504.01990","citing_title":"Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems","ref_index":150,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18760","citing_title":"DOTRAG: Retrieval-Time Reasoning Along Paths","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2510.02657","citing_title":"Less LLM, More Documents: Searching for Improved RAG","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2511.09282","citing_title":"End-to-end Contrastive Language-Speech Pretraining Model For Long-form Spoken Question Answering","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16316","citing_title":"CrossTraffic: An Open-Source Framework for Reproducible and Executable Transportation Analysis and Knowledge Management","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2603.17418","citing_title":"PowerDAG: Supervisory Agentic AI System for Automating Distribution Grid Analysis","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14192","citing_title":"Why Retrieval-Augmented Generation Fails: A Graph Perspective","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00943","citing_title":"ARIS: Agentic and Relationship Intelligence System for Social Robots","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00060","citing_title":"TADI: Tool-Augmented Drilling Intelligence via Agentic LLM Orchestration over Heterogeneous Wellsite Data","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21679","citing_title":"A Sociotechnical, Practitioner-Centered Approach to Technology Adoption in Cybersecurity Operations: An LLM Case","ref_index":50,"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":10,"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":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DQFQPTTBN7KHV4QGL2RBA25L3P","json":"https://pith.science/pith/DQFQPTTBN7KHV4QGL2RBA25L3P.json","graph_json":"https://pith.science/api/pith-number/DQFQPTTBN7KHV4QGL2RBA25L3P/graph.json","events_json":"https://pith.science/api/pith-number/DQFQPTTBN7KHV4QGL2RBA25L3P/events.json","paper":"https://pith.science/paper/DQFQPTTB"},"agent_actions":{"view_html":"https://pith.science/pith/DQFQPTTBN7KHV4QGL2RBA25L3P","download_json":"https://pith.science/pith/DQFQPTTBN7KHV4QGL2RBA25L3P.json","view_paper":"https://pith.science/paper/DQFQPTTB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.12837&json=true","fetch_graph":"https://pith.science/api/pith-number/DQFQPTTBN7KHV4QGL2RBA25L3P/graph.json","fetch_events":"https://pith.science/api/pith-number/DQFQPTTBN7KHV4QGL2RBA25L3P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DQFQPTTBN7KHV4QGL2RBA25L3P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DQFQPTTBN7KHV4QGL2RBA25L3P/action/storage_attestation","attest_author":"https://pith.science/pith/DQFQPTTBN7KHV4QGL2RBA25L3P/action/author_attestation","sign_citation":"https://pith.science/pith/DQFQPTTBN7KHV4QGL2RBA25L3P/action/citation_signature","submit_replication":"https://pith.science/pith/DQFQPTTBN7KHV4QGL2RBA25L3P/action/replication_record"}},"created_at":"2026-07-05T09:21:51.634506+00:00","updated_at":"2026-07-05T09:21:51.634506+00:00"}