{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VYDWJZTHQYS373C2BRAG5OPRK2","short_pith_number":"pith:VYDWJZTH","schema_version":"1.0","canonical_sha256":"ae0764e6678625bfec5a0c406eb9f156bd96c28fce5e26ebef60e861c13d40de","source":{"kind":"arxiv","id":"2401.14887","version":4},"attestation_state":"computed","paper":{"title":"The Power of Noise: Redefining Retrieval for RAG Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Cesare Campagnano, Fabrizio Silvestri, Federico Siciliano, Florin Cuconasu, Giovanni Trappolini, Nicola Tonellotto, Simone Filice, Yoelle Maarek","submitted_at":"2024-01-26T14:14:59Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) has recently emerged as a method to extend beyond the pre-trained knowledge of Large Language Models by augmenting the original prompt with relevant passages or documents retrieved by an Information Retrieval (IR) system. RAG has become increasingly important for Generative AI solutions, especially in enterprise settings or in any domain in which knowledge is constantly refreshed and cannot be memorized in the LLM. We argue here that the retrieval component of RAG systems, be it dense or sparse, deserves increased attention from the research community, and "},"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":"2401.14887","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-01-26T14:14:59Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"b98a11ae4abac53abb02056a74e2163be0c93c6d092da62ed6c385efef5c34d5","abstract_canon_sha256":"7b43dac53eb00097c9f751141509999d5b76b70451b585e145ea1f8a8b54edec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:14:03.546154Z","signature_b64":"ipZ+y5HQ1acHUhAUcbj+QYY73vXzKHT5GzSFQpGfECOiXO9mecFZpIArGG4/IJtJ9CP9f1v9QqZWXGR+c1nAAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae0764e6678625bfec5a0c406eb9f156bd96c28fce5e26ebef60e861c13d40de","last_reissued_at":"2026-07-05T08:14:03.545739Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:14:03.545739Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Power of Noise: Redefining Retrieval for RAG Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Cesare Campagnano, Fabrizio Silvestri, Federico Siciliano, Florin Cuconasu, Giovanni Trappolini, Nicola Tonellotto, Simone Filice, Yoelle Maarek","submitted_at":"2024-01-26T14:14:59Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) has recently emerged as a method to extend beyond the pre-trained knowledge of Large Language Models by augmenting the original prompt with relevant passages or documents retrieved by an Information Retrieval (IR) system. RAG has become increasingly important for Generative AI solutions, especially in enterprise settings or in any domain in which knowledge is constantly refreshed and cannot be memorized in the LLM. We argue here that the retrieval component of RAG systems, be it dense or sparse, deserves increased attention from the research community, and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.14887","kind":"arxiv","version":4},"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/2401.14887/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":"2401.14887","created_at":"2026-07-05T08:14:03.545795+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.14887v4","created_at":"2026-07-05T08:14:03.545795+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.14887","created_at":"2026-07-05T08:14:03.545795+00:00"},{"alias_kind":"pith_short_12","alias_value":"VYDWJZTHQYS3","created_at":"2026-07-05T08:14:03.545795+00:00"},{"alias_kind":"pith_short_16","alias_value":"VYDWJZTHQYS373C2","created_at":"2026-07-05T08:14:03.545795+00:00"},{"alias_kind":"pith_short_8","alias_value":"VYDWJZTH","created_at":"2026-07-05T08:14:03.545795+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2312.10997","citing_title":"Retrieval-Augmented Generation for Large Language Models: A Survey","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2404.10981","citing_title":"A Survey on Retrieval-Augmented Text Generation for Large Language Models","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09174","citing_title":"Facet-Level Tracing of Evidence Uncertainty and Hallucination in RAG","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2503.23278","citing_title":"Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directions","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2311.05232","citing_title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09174","citing_title":"Facet-Level Tracing of Evidence Uncertainty and Hallucination in RAG","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VYDWJZTHQYS373C2BRAG5OPRK2","json":"https://pith.science/pith/VYDWJZTHQYS373C2BRAG5OPRK2.json","graph_json":"https://pith.science/api/pith-number/VYDWJZTHQYS373C2BRAG5OPRK2/graph.json","events_json":"https://pith.science/api/pith-number/VYDWJZTHQYS373C2BRAG5OPRK2/events.json","paper":"https://pith.science/paper/VYDWJZTH"},"agent_actions":{"view_html":"https://pith.science/pith/VYDWJZTHQYS373C2BRAG5OPRK2","download_json":"https://pith.science/pith/VYDWJZTHQYS373C2BRAG5OPRK2.json","view_paper":"https://pith.science/paper/VYDWJZTH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.14887&json=true","fetch_graph":"https://pith.science/api/pith-number/VYDWJZTHQYS373C2BRAG5OPRK2/graph.json","fetch_events":"https://pith.science/api/pith-number/VYDWJZTHQYS373C2BRAG5OPRK2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VYDWJZTHQYS373C2BRAG5OPRK2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VYDWJZTHQYS373C2BRAG5OPRK2/action/storage_attestation","attest_author":"https://pith.science/pith/VYDWJZTHQYS373C2BRAG5OPRK2/action/author_attestation","sign_citation":"https://pith.science/pith/VYDWJZTHQYS373C2BRAG5OPRK2/action/citation_signature","submit_replication":"https://pith.science/pith/VYDWJZTHQYS373C2BRAG5OPRK2/action/replication_record"}},"created_at":"2026-07-05T08:14:03.545795+00:00","updated_at":"2026-07-05T08:14:03.545795+00:00"}