{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CQMCYORBREL6544UHDF37E5B5X","short_pith_number":"pith:CQMCYORB","schema_version":"1.0","canonical_sha256":"14182c3a218917eef39438cbbf93a1edce9e12872d31d8fc9e7f7ffca9d1cbbd","source":{"kind":"arxiv","id":"2505.01164","version":1},"attestation_state":"computed","paper":{"title":"CaGR-RAG: Context-aware Query Grouping for Disk-based Vector Search in RAG Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Hyunji Cho, Kyuli Park, Sungyong Park, Yeonwoo Jeong","submitted_at":"2025-05-02T10:13:12Z","abstract_excerpt":"Modern embedding models capture both semantic and syntactic structures of queries, often mapping different queries to similar regions in vector space. This results in non-uniform cluster access patterns in disk-based vector search systems, particularly in Retrieval Augmented Generation (RAG) framework. While existing approaches optimize individual queries, they overlook the impact of cluster access patterns, failing to account for the locality effects of queries that access similar clusters. This oversight reduces cache efficiency and increases search latency due to excessive disk I/O. To addr"},"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":"2505.01164","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-05-02T10:13:12Z","cross_cats_sorted":[],"title_canon_sha256":"8a27ad569ff186ed454e973c6f79f9438298c6f34d7b864c8f7a6c340cd0fbec","abstract_canon_sha256":"b973c9c2bd6e444c3833ef62da913e6a9289c93994849934a686008a09550998"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:57:46.487490Z","signature_b64":"sRcxrJZamDhuqNux6ROpAYJxJij9J2lh/i4Ztt3ve6zefoY9cfx5oUNBNgZ3JldACT6lwO54pbCNyllAjIfYDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14182c3a218917eef39438cbbf93a1edce9e12872d31d8fc9e7f7ffca9d1cbbd","last_reissued_at":"2026-07-05T10:57:46.486926Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:57:46.486926Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CaGR-RAG: Context-aware Query Grouping for Disk-based Vector Search in RAG Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Hyunji Cho, Kyuli Park, Sungyong Park, Yeonwoo Jeong","submitted_at":"2025-05-02T10:13:12Z","abstract_excerpt":"Modern embedding models capture both semantic and syntactic structures of queries, often mapping different queries to similar regions in vector space. This results in non-uniform cluster access patterns in disk-based vector search systems, particularly in Retrieval Augmented Generation (RAG) framework. While existing approaches optimize individual queries, they overlook the impact of cluster access patterns, failing to account for the locality effects of queries that access similar clusters. This oversight reduces cache efficiency and increases search latency due to excessive disk I/O. To addr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.01164","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/2505.01164/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":"2505.01164","created_at":"2026-07-05T10:57:46.486989+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.01164v1","created_at":"2026-07-05T10:57:46.486989+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.01164","created_at":"2026-07-05T10:57:46.486989+00:00"},{"alias_kind":"pith_short_12","alias_value":"CQMCYORBREL6","created_at":"2026-07-05T10:57:46.486989+00:00"},{"alias_kind":"pith_short_16","alias_value":"CQMCYORBREL6544U","created_at":"2026-07-05T10:57:46.486989+00:00"},{"alias_kind":"pith_short_8","alias_value":"CQMCYORB","created_at":"2026-07-05T10:57:46.486989+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CQMCYORBREL6544UHDF37E5B5X","json":"https://pith.science/pith/CQMCYORBREL6544UHDF37E5B5X.json","graph_json":"https://pith.science/api/pith-number/CQMCYORBREL6544UHDF37E5B5X/graph.json","events_json":"https://pith.science/api/pith-number/CQMCYORBREL6544UHDF37E5B5X/events.json","paper":"https://pith.science/paper/CQMCYORB"},"agent_actions":{"view_html":"https://pith.science/pith/CQMCYORBREL6544UHDF37E5B5X","download_json":"https://pith.science/pith/CQMCYORBREL6544UHDF37E5B5X.json","view_paper":"https://pith.science/paper/CQMCYORB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.01164&json=true","fetch_graph":"https://pith.science/api/pith-number/CQMCYORBREL6544UHDF37E5B5X/graph.json","fetch_events":"https://pith.science/api/pith-number/CQMCYORBREL6544UHDF37E5B5X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CQMCYORBREL6544UHDF37E5B5X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CQMCYORBREL6544UHDF37E5B5X/action/storage_attestation","attest_author":"https://pith.science/pith/CQMCYORBREL6544UHDF37E5B5X/action/author_attestation","sign_citation":"https://pith.science/pith/CQMCYORBREL6544UHDF37E5B5X/action/citation_signature","submit_replication":"https://pith.science/pith/CQMCYORBREL6544UHDF37E5B5X/action/replication_record"}},"created_at":"2026-07-05T10:57:46.486989+00:00","updated_at":"2026-07-05T10:57:46.486989+00:00"}