{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Q32VU7BR3HWZ7DQUPYUQLIEOCN","short_pith_number":"pith:Q32VU7BR","schema_version":"1.0","canonical_sha256":"86f55a7c31d9ed9f8e147e2905a08e134071a9515d9c34e20f606b5fc88af08b","source":{"kind":"arxiv","id":"2506.00054","version":1},"attestation_state":"computed","paper":{"title":"Retrieval-Augmented Generation: A Comprehensive Survey of Architectures, Enhancements, and Robustness Frontiers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Chaitanya Sharma","submitted_at":"2025-05-28T22:57:04Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) has emerged as a powerful paradigm to enhance large language models (LLMs) by conditioning generation on external evidence retrieved at inference time. While RAG addresses critical limitations of parametric knowledge storage-such as factual inconsistency and domain inflexibility-it introduces new challenges in retrieval quality, grounding fidelity, pipeline efficiency, and robustness against noisy or adversarial inputs. This survey provides a comprehensive synthesis of recent advances in RAG systems, offering a taxonomy that categorizes architectures into r"},"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":"2506.00054","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-05-28T22:57:04Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"19d13871a3bcf8cb4a35035bb7b2bb3e98e61bb85bd8a1ec03372745d66c7a36","abstract_canon_sha256":"53a7620f5f9321225caf159ca1d91f2a84c35eba98236fff1c98090769c721bd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:28.221401Z","signature_b64":"vZhagqQhUrBES/bH6u6hDwu3UYIOZL2UjiAgq6uFvuGDwPNq7Plh2AibyCNDIqohCUgit2wKzqyMv/pMPvoRDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86f55a7c31d9ed9f8e147e2905a08e134071a9515d9c34e20f606b5fc88af08b","last_reissued_at":"2026-07-05T11:13:28.220923Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:28.220923Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Retrieval-Augmented Generation: A Comprehensive Survey of Architectures, Enhancements, and Robustness Frontiers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Chaitanya Sharma","submitted_at":"2025-05-28T22:57:04Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) has emerged as a powerful paradigm to enhance large language models (LLMs) by conditioning generation on external evidence retrieved at inference time. While RAG addresses critical limitations of parametric knowledge storage-such as factual inconsistency and domain inflexibility-it introduces new challenges in retrieval quality, grounding fidelity, pipeline efficiency, and robustness against noisy or adversarial inputs. This survey provides a comprehensive synthesis of recent advances in RAG systems, offering a taxonomy that categorizes architectures into r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00054","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/2506.00054/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":"2506.00054","created_at":"2026-07-05T11:13:28.220982+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.00054v1","created_at":"2026-07-05T11:13:28.220982+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00054","created_at":"2026-07-05T11:13:28.220982+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q32VU7BR3HWZ","created_at":"2026-07-05T11:13:28.220982+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q32VU7BR3HWZ7DQU","created_at":"2026-07-05T11:13:28.220982+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q32VU7BR","created_at":"2026-07-05T11:13:28.220982+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06641","citing_title":"Healthier LLMs: Retrieval-Augmented Generation for Public Health Question Answering","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2606.28387","citing_title":"Schema-First Retrieval: Embedding Catalogs for Natural Language Analytics","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29640","citing_title":"VikingMem: A Memory Base Management System for Stateful LLM-based Applications","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17830","citing_title":"Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2508.03306","citing_title":"Reliable Evaluation Protocol for Low-Precision Retrieval","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2511.09803","citing_title":"Retrieval as a Decision: Training-Free Adaptive Gating for Efficient RAG","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2512.20136","citing_title":"M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2603.18196","citing_title":"Retrieval-Augmented LLMs for Security Incident Analysis","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08304","citing_title":"Securing Retrieval-Augmented Generation: A Taxonomy of Attacks, Defenses, and Future Directions","ref_index":14,"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":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03140","citing_title":"Evaluating Retrieval-Augmented Generation for Explainable Malware Analysis","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q32VU7BR3HWZ7DQUPYUQLIEOCN","json":"https://pith.science/pith/Q32VU7BR3HWZ7DQUPYUQLIEOCN.json","graph_json":"https://pith.science/api/pith-number/Q32VU7BR3HWZ7DQUPYUQLIEOCN/graph.json","events_json":"https://pith.science/api/pith-number/Q32VU7BR3HWZ7DQUPYUQLIEOCN/events.json","paper":"https://pith.science/paper/Q32VU7BR"},"agent_actions":{"view_html":"https://pith.science/pith/Q32VU7BR3HWZ7DQUPYUQLIEOCN","download_json":"https://pith.science/pith/Q32VU7BR3HWZ7DQUPYUQLIEOCN.json","view_paper":"https://pith.science/paper/Q32VU7BR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.00054&json=true","fetch_graph":"https://pith.science/api/pith-number/Q32VU7BR3HWZ7DQUPYUQLIEOCN/graph.json","fetch_events":"https://pith.science/api/pith-number/Q32VU7BR3HWZ7DQUPYUQLIEOCN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q32VU7BR3HWZ7DQUPYUQLIEOCN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q32VU7BR3HWZ7DQUPYUQLIEOCN/action/storage_attestation","attest_author":"https://pith.science/pith/Q32VU7BR3HWZ7DQUPYUQLIEOCN/action/author_attestation","sign_citation":"https://pith.science/pith/Q32VU7BR3HWZ7DQUPYUQLIEOCN/action/citation_signature","submit_replication":"https://pith.science/pith/Q32VU7BR3HWZ7DQUPYUQLIEOCN/action/replication_record"}},"created_at":"2026-07-05T11:13:28.220982+00:00","updated_at":"2026-07-05T11:13:28.220982+00:00"}