{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HJGG4FJUMZX4IQJTRCR5LJEEXS","short_pith_number":"pith:HJGG4FJU","schema_version":"1.0","canonical_sha256":"3a4c6e1534666fc4413388a3d5a484bc93ceb7d5005e3a57b56fcced13688210","source":{"kind":"arxiv","id":"2604.26176","version":2},"attestation_state":"computed","paper":{"title":"CacheRAG: A Semantic Caching System for Retrieval-Augmented Generation in Knowledge Graph Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"CacheRAG adds semantic caching to turn stateless LLM planners for knowledge graph questions into continual learners.","cross_cats":["cs.CL"],"primary_cat":"cs.DB","authors_text":"Lei Chen, Yushi Sun","submitted_at":"2026-04-28T23:46:47Z","abstract_excerpt":"The integration of Large Language Models (LLMs) with Retrieval-Augmented Generation (RAG) has significantly advanced Knowledge Graph Question Answering (KGQA). However, existing LLM-driven KGQA systems act as stateless planners, generating retrieval plans in isolation without exploiting historical query patterns: analogous to a database system that optimizes every query from scratch without a plan cache. This fundamental design flaw leads to schema hallucinations and limited retrieval coverage. We propose CacheRAG, a systematic cache-augmented architecture for LLM-based KGQA that transforms st"},"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":"2604.26176","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2026-04-28T23:46:47Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"7c173da619f0326e1d6aa8b3673b563e48c83d3268af691926e8ca026385a46e","abstract_canon_sha256":"7f51c31b076311b5f7d212ffdc33cba645f714ba68c406cac031304497eba5fb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T03:04:41.615109Z","signature_b64":"qELim+QOdxf+92zAULFZsNSx1v3vNsJOeCcJaSdCMRqA1auv1slNY6KhNuKbUO7E2MtM/rHh8AKZgTOGa1ayCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a4c6e1534666fc4413388a3d5a484bc93ceb7d5005e3a57b56fcced13688210","last_reissued_at":"2026-06-02T03:04:41.614720Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T03:04:41.614720Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CacheRAG: A Semantic Caching System for Retrieval-Augmented Generation in Knowledge Graph Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"CacheRAG adds semantic caching to turn stateless LLM planners for knowledge graph questions into continual learners.","cross_cats":["cs.CL"],"primary_cat":"cs.DB","authors_text":"Lei Chen, Yushi Sun","submitted_at":"2026-04-28T23:46:47Z","abstract_excerpt":"The integration of Large Language Models (LLMs) with Retrieval-Augmented Generation (RAG) has significantly advanced Knowledge Graph Question Answering (KGQA). However, existing LLM-driven KGQA systems act as stateless planners, generating retrieval plans in isolation without exploiting historical query patterns: analogous to a database system that optimizes every query from scratch without a plan cache. This fundamental design flaw leads to schema hallucinations and limited retrieval coverage. We propose CacheRAG, a systematic cache-augmented architecture for LLM-based KGQA that transforms st"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"CacheRAG significantly outperforms state-of-the-art baselines (e.g., +13.2% accuracy and +17.5% truthfulness on the CRAG dataset).","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the three proposed design principles (schema-agnostic ISR interface, MMR-based diversity retrieval, and bounded heuristic expansion) can be realized without introducing new failure modes or requiring extensive manual tuning of cache policies.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"CacheRAG turns stateless LLM planners for KGQA into continual learners via schema-agnostic parsing, diversity-optimized hierarchical caching, and bounded subgraph expansion, yielding up to 13.2% accuracy gains on benchmarks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"CacheRAG adds semantic caching to turn stateless LLM planners for knowledge graph questions into continual learners.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"05dbbf56c6a7cdc133da1f8e01aec45738e361af5addb7950dd5126552bba8f7"},"source":{"id":"2604.26176","kind":"arxiv","version":2},"verdict":{"id":"74cba861-951e-4f37-b46c-416e095aee18","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-07T13:44:20.183890Z","strongest_claim":"CacheRAG significantly outperforms state-of-the-art baselines (e.g., +13.2% accuracy and +17.5% truthfulness on the CRAG dataset).","one_line_summary":"CacheRAG turns stateless LLM planners for KGQA into continual learners via schema-agnostic parsing, diversity-optimized hierarchical caching, and bounded subgraph expansion, yielding up to 13.2% accuracy gains on benchmarks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the three proposed design principles (schema-agnostic ISR interface, MMR-based diversity retrieval, and bounded heuristic expansion) can be realized without introducing new failure modes or requiring extensive manual tuning of cache policies.","pith_extraction_headline":"CacheRAG adds semantic caching to turn stateless LLM planners for knowledge graph questions into continual learners."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.26176/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-21T03:33:41.849476Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T20:26:07.153365Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"8ccd88ac3ce4e258d15813830b286ce769033665cdc263488d3c43f0e019d048"},"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":"2604.26176","created_at":"2026-06-02T03:04:41.614773+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.26176v2","created_at":"2026-06-02T03:04:41.614773+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.26176","created_at":"2026-06-02T03:04:41.614773+00:00"},{"alias_kind":"pith_short_12","alias_value":"HJGG4FJUMZX4","created_at":"2026-06-02T03:04:41.614773+00:00"},{"alias_kind":"pith_short_16","alias_value":"HJGG4FJUMZX4IQJT","created_at":"2026-06-02T03:04:41.614773+00:00"},{"alias_kind":"pith_short_8","alias_value":"HJGG4FJU","created_at":"2026-06-02T03:04:41.614773+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.00394","citing_title":"When Classic Cache Policies Fail: Learning-Augmented Replacement for Semantic Retrieval Buffers","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HJGG4FJUMZX4IQJTRCR5LJEEXS","json":"https://pith.science/pith/HJGG4FJUMZX4IQJTRCR5LJEEXS.json","graph_json":"https://pith.science/api/pith-number/HJGG4FJUMZX4IQJTRCR5LJEEXS/graph.json","events_json":"https://pith.science/api/pith-number/HJGG4FJUMZX4IQJTRCR5LJEEXS/events.json","paper":"https://pith.science/paper/HJGG4FJU"},"agent_actions":{"view_html":"https://pith.science/pith/HJGG4FJUMZX4IQJTRCR5LJEEXS","download_json":"https://pith.science/pith/HJGG4FJUMZX4IQJTRCR5LJEEXS.json","view_paper":"https://pith.science/paper/HJGG4FJU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.26176&json=true","fetch_graph":"https://pith.science/api/pith-number/HJGG4FJUMZX4IQJTRCR5LJEEXS/graph.json","fetch_events":"https://pith.science/api/pith-number/HJGG4FJUMZX4IQJTRCR5LJEEXS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HJGG4FJUMZX4IQJTRCR5LJEEXS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HJGG4FJUMZX4IQJTRCR5LJEEXS/action/storage_attestation","attest_author":"https://pith.science/pith/HJGG4FJUMZX4IQJTRCR5LJEEXS/action/author_attestation","sign_citation":"https://pith.science/pith/HJGG4FJUMZX4IQJTRCR5LJEEXS/action/citation_signature","submit_replication":"https://pith.science/pith/HJGG4FJUMZX4IQJTRCR5LJEEXS/action/replication_record"}},"created_at":"2026-06-02T03:04:41.614773+00:00","updated_at":"2026-06-02T03:04:41.614773+00:00"}