{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:HJGG4FJUMZX4IQJTRCR5LJEEXS","short_pith_number":"pith:HJGG4FJU","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"},"canonical_sha256":"3a4c6e1534666fc4413388a3d5a484bc93ceb7d5005e3a57b56fcced13688210","source":{"kind":"arxiv","id":"2604.26176","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.26176","created_at":"2026-06-02T03:04:41Z"},{"alias_kind":"arxiv_version","alias_value":"2604.26176v2","created_at":"2026-06-02T03:04:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.26176","created_at":"2026-06-02T03:04:41Z"},{"alias_kind":"pith_short_12","alias_value":"HJGG4FJUMZX4","created_at":"2026-06-02T03:04:41Z"},{"alias_kind":"pith_short_16","alias_value":"HJGG4FJUMZX4IQJT","created_at":"2026-06-02T03:04:41Z"},{"alias_kind":"pith_short_8","alias_value":"HJGG4FJU","created_at":"2026-06-02T03:04:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:HJGG4FJUMZX4IQJTRCR5LJEEXS","target":"record","payload":{"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"},"canonical_sha256":"3a4c6e1534666fc4413388a3d5a484bc93ceb7d5005e3a57b56fcced13688210","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"},"source_kind":"arxiv","source_id":"2604.26176","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-02T03:04:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b4TgJPCUTapU/Yzf46UfaRBZUFrDked4IFV4ttYTE1SvWsqEKl1Ia+80c2qQCfA/DLf3A73rbLmd6NVeuEc+DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T17:06:08.616954Z"},"content_sha256":"daf6a57d3986871708ce481fd7060306634a69d59547350d63e02ddd9e81731c","schema_version":"1.0","event_id":"sha256:daf6a57d3986871708ce481fd7060306634a69d59547350d63e02ddd9e81731c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:HJGG4FJUMZX4IQJTRCR5LJEEXS","target":"graph","payload":{"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"},"verdict_id":"74cba861-951e-4f37-b46c-416e095aee18"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-02T03:04:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yQ0UMgXyv7rCB1xuGPfqD4m+rtJuiOADwV5tSB+lv8rLF97K76u2FfM6sj9ZIKmxwsXd2iMETPSivWfzH9QsCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T17:06:08.617463Z"},"content_sha256":"698ead87b263d4ac14f8c7c0e2688357ebffa226f502f08757686f0dfb6d5f46","schema_version":"1.0","event_id":"sha256:698ead87b263d4ac14f8c7c0e2688357ebffa226f502f08757686f0dfb6d5f46"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HJGG4FJUMZX4IQJTRCR5LJEEXS/bundle.json","state_url":"https://pith.science/pith/HJGG4FJUMZX4IQJTRCR5LJEEXS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HJGG4FJUMZX4IQJTRCR5LJEEXS/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-02T17:06:08Z","links":{"resolver":"https://pith.science/pith/HJGG4FJUMZX4IQJTRCR5LJEEXS","bundle":"https://pith.science/pith/HJGG4FJUMZX4IQJTRCR5LJEEXS/bundle.json","state":"https://pith.science/pith/HJGG4FJUMZX4IQJTRCR5LJEEXS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HJGG4FJUMZX4IQJTRCR5LJEEXS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:HJGG4FJUMZX4IQJTRCR5LJEEXS","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"7f51c31b076311b5f7d212ffdc33cba645f714ba68c406cac031304497eba5fb","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2026-04-28T23:46:47Z","title_canon_sha256":"7c173da619f0326e1d6aa8b3673b563e48c83d3268af691926e8ca026385a46e"},"schema_version":"1.0","source":{"id":"2604.26176","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.26176","created_at":"2026-06-02T03:04:41Z"},{"alias_kind":"arxiv_version","alias_value":"2604.26176v2","created_at":"2026-06-02T03:04:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.26176","created_at":"2026-06-02T03:04:41Z"},{"alias_kind":"pith_short_12","alias_value":"HJGG4FJUMZX4","created_at":"2026-06-02T03:04:41Z"},{"alias_kind":"pith_short_16","alias_value":"HJGG4FJUMZX4IQJT","created_at":"2026-06-02T03:04:41Z"},{"alias_kind":"pith_short_8","alias_value":"HJGG4FJU","created_at":"2026-06-02T03:04:41Z"}],"graph_snapshots":[{"event_id":"sha256:698ead87b263d4ac14f8c7c0e2688357ebffa226f502f08757686f0dfb6d5f46","target":"graph","created_at":"2026-06-02T03:04:41Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"CacheRAG significantly outperforms state-of-the-art baselines (e.g., +13.2% accuracy and +17.5% truthfulness on the CRAG dataset)."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"CacheRAG adds semantic caching to turn stateless LLM planners for knowledge graph questions into continual learners."}],"snapshot_sha256":"05dbbf56c6a7cdc133da1f8e01aec45738e361af5addb7950dd5126552bba8f7"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"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"}],"endpoint":"/pith/2604.26176/integrity.json","findings":[],"snapshot_sha256":"8ccd88ac3ce4e258d15813830b286ce769033665cdc263488d3c43f0e019d048","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Lei Chen, Yushi Sun","cross_cats":["cs.CL"],"headline":"CacheRAG adds semantic caching to turn stateless LLM planners for knowledge graph questions into continual learners.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2026-04-28T23:46:47Z","title":"CacheRAG: A Semantic Caching System for Retrieval-Augmented Generation in Knowledge Graph Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.26176","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-07T13:44:20.183890Z","id":"74cba861-951e-4f37-b46c-416e095aee18","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"CacheRAG adds semantic caching to turn stateless LLM planners for knowledge graph questions into continual learners.","strongest_claim":"CacheRAG significantly outperforms state-of-the-art baselines (e.g., +13.2% accuracy and +17.5% truthfulness on the CRAG dataset).","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."}},"verdict_id":"74cba861-951e-4f37-b46c-416e095aee18"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:daf6a57d3986871708ce481fd7060306634a69d59547350d63e02ddd9e81731c","target":"record","created_at":"2026-06-02T03:04:41Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"7f51c31b076311b5f7d212ffdc33cba645f714ba68c406cac031304497eba5fb","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2026-04-28T23:46:47Z","title_canon_sha256":"7c173da619f0326e1d6aa8b3673b563e48c83d3268af691926e8ca026385a46e"},"schema_version":"1.0","source":{"id":"2604.26176","kind":"arxiv","version":2}},"canonical_sha256":"3a4c6e1534666fc4413388a3d5a484bc93ceb7d5005e3a57b56fcced13688210","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3a4c6e1534666fc4413388a3d5a484bc93ceb7d5005e3a57b56fcced13688210","first_computed_at":"2026-06-02T03:04:41.614720Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T03:04:41.614720Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qELim+QOdxf+92zAULFZsNSx1v3vNsJOeCcJaSdCMRqA1auv1slNY6KhNuKbUO7E2MtM/rHh8AKZgTOGa1ayCA==","signature_status":"signed_v1","signed_at":"2026-06-02T03:04:41.615109Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.26176","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:daf6a57d3986871708ce481fd7060306634a69d59547350d63e02ddd9e81731c","sha256:698ead87b263d4ac14f8c7c0e2688357ebffa226f502f08757686f0dfb6d5f46"],"state_sha256":"426f65e2820bb7cda54926268b58e8332ce65a7e907d7fdfaad0ea2ebb21b90d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t8ZTFZ1k/Y8H5uTDdNiAW/DmVqGNW3ugvuqRuntZ7rfU6lb9HsikHf8o2E4e50IP8MCrrAq8o3t6v9XzRk/hAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-02T17:06:08.619718Z","bundle_sha256":"f092e790d3135183244ce837905c1d866dbc36c04ab079071463c742170b2803"}}