{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KNUHEYPFKYCHQ37BVS2FU3UBJU","short_pith_number":"pith:KNUHEYPF","schema_version":"1.0","canonical_sha256":"53687261e55604786fe1acb45a6e814d2b8ffbd074f2fb7421b2cf7de7294c7e","source":{"kind":"arxiv","id":"2510.10129","version":2},"attestation_state":"computed","paper":{"title":"CacheClip: Accelerating RAG with Effective KV Cache Reuse","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bin Yang, Jun Zeng, Qiuyu Leng, Zhenhua Wu","submitted_at":"2025-10-11T09:28:26Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) systems suffer from severe time-to-first-token (TTFT) bottlenecks due to long input sequences. Existing KV cache reuse methods face a fundamental trade-off: prefix caching requires identical prefixes that rarely occur in RAG scenarios, while direct precomputation sacrifices quality due to missing inter-chunk attention and repeated attention sinks. Recent methods like APE and CacheBlend partially address these issues but remain inadequate for robust RAG applications. This paper presents CacheClip, a novel framework that achieves both fast TTFT and high gener"},"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":"2510.10129","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-11T09:28:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e1d3b61ec2794f68905a307080813c82a93b98662b9d00658171c4ddebea512d","abstract_canon_sha256":"9be42e487ef974b4ddaf95cb027191d962cc1c91cebbd93dc9ca31217a336eb0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:03:48.164160Z","signature_b64":"yJRQS+zkwF/q9Ov+QG9FhJE6QiWf2GaoffovhVUumFd4BgVGHCGpeFynr7nHZ1kAh+Qa35HeLqKFvOv+uLldBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53687261e55604786fe1acb45a6e814d2b8ffbd074f2fb7421b2cf7de7294c7e","last_reissued_at":"2026-05-22T01:03:48.163209Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:03:48.163209Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CacheClip: Accelerating RAG with Effective KV Cache Reuse","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bin Yang, Jun Zeng, Qiuyu Leng, Zhenhua Wu","submitted_at":"2025-10-11T09:28:26Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) systems suffer from severe time-to-first-token (TTFT) bottlenecks due to long input sequences. Existing KV cache reuse methods face a fundamental trade-off: prefix caching requires identical prefixes that rarely occur in RAG scenarios, while direct precomputation sacrifices quality due to missing inter-chunk attention and repeated attention sinks. Recent methods like APE and CacheBlend partially address these issues but remain inadequate for robust RAG applications. This paper presents CacheClip, a novel framework that achieves both fast TTFT and high gener"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.10129","kind":"arxiv","version":2},"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/2510.10129/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":"2510.10129","created_at":"2026-05-22T01:03:48.163371+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.10129v2","created_at":"2026-05-22T01:03:48.163371+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.10129","created_at":"2026-05-22T01:03:48.163371+00:00"},{"alias_kind":"pith_short_12","alias_value":"KNUHEYPFKYCH","created_at":"2026-05-22T01:03:48.163371+00:00"},{"alias_kind":"pith_short_16","alias_value":"KNUHEYPFKYCHQ37B","created_at":"2026-05-22T01:03:48.163371+00:00"},{"alias_kind":"pith_short_8","alias_value":"KNUHEYPF","created_at":"2026-05-22T01:03:48.163371+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.10098","citing_title":"Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation","ref_index":62,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KNUHEYPFKYCHQ37BVS2FU3UBJU","json":"https://pith.science/pith/KNUHEYPFKYCHQ37BVS2FU3UBJU.json","graph_json":"https://pith.science/api/pith-number/KNUHEYPFKYCHQ37BVS2FU3UBJU/graph.json","events_json":"https://pith.science/api/pith-number/KNUHEYPFKYCHQ37BVS2FU3UBJU/events.json","paper":"https://pith.science/paper/KNUHEYPF"},"agent_actions":{"view_html":"https://pith.science/pith/KNUHEYPFKYCHQ37BVS2FU3UBJU","download_json":"https://pith.science/pith/KNUHEYPFKYCHQ37BVS2FU3UBJU.json","view_paper":"https://pith.science/paper/KNUHEYPF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.10129&json=true","fetch_graph":"https://pith.science/api/pith-number/KNUHEYPFKYCHQ37BVS2FU3UBJU/graph.json","fetch_events":"https://pith.science/api/pith-number/KNUHEYPFKYCHQ37BVS2FU3UBJU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KNUHEYPFKYCHQ37BVS2FU3UBJU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KNUHEYPFKYCHQ37BVS2FU3UBJU/action/storage_attestation","attest_author":"https://pith.science/pith/KNUHEYPFKYCHQ37BVS2FU3UBJU/action/author_attestation","sign_citation":"https://pith.science/pith/KNUHEYPFKYCHQ37BVS2FU3UBJU/action/citation_signature","submit_replication":"https://pith.science/pith/KNUHEYPFKYCHQ37BVS2FU3UBJU/action/replication_record"}},"created_at":"2026-05-22T01:03:48.163371+00:00","updated_at":"2026-05-22T01:03:48.163371+00:00"}