{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:IYRKK2F7ED3MJ3PVFG7MEUCXFC","short_pith_number":"pith:IYRKK2F7","schema_version":"1.0","canonical_sha256":"4622a568bf20f6c4edf529bec25057288ee9f51e75e5171a2e23f153a507b307","source":{"kind":"arxiv","id":"2605.24914","version":1},"attestation_state":"computed","paper":{"title":"MVR-cache: Optimizing Semantic Caching via Multi-Vector Retrieval and Learned Prompt Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DB","cs.LG"],"primary_cat":"cs.IR","authors_text":"Ali Noshad, Yinjun Wu, Zishan Zheng","submitted_at":"2026-05-24T07:33:46Z","abstract_excerpt":"To reduce LLM costs and latency, semantic caching systems must accurately identify when a new prompt matches a cached one. Current methods often rely on simplistic similarity measures, which limit their effectiveness. We introduce MVR-cache, a novel semantic caching approach that significantly improves retrieval accuracy by integrating Multi-Vector Retrieval (MVR). MVR-cache is built upon a learnable segmentation model that intelligently splits prompts, enabling fine-grained similarity comparisons via MaxSim. We derive the model's training objective from a rigorous theoretical analysis. This c"},"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":"2605.24914","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-05-24T07:33:46Z","cross_cats_sorted":["cs.DB","cs.LG"],"title_canon_sha256":"c48d57ade6305cef36ed05419405a4ab78f9781b7ed5cff15e5ecd70519cbbcc","abstract_canon_sha256":"eb0957c30a050d78c088b4d9991e350c8647a8486c76cf2978025be922874e58"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:04:05.549929Z","signature_b64":"wIfy98Vq80Gg5VtXuqp9yqRlq3mdHqiOBXl9MtX2FE88LeU8coXWxETAa3G4FflBuMBVqCEopJp3DrWBIustAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4622a568bf20f6c4edf529bec25057288ee9f51e75e5171a2e23f153a507b307","last_reissued_at":"2026-05-26T01:04:05.549234Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:04:05.549234Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MVR-cache: Optimizing Semantic Caching via Multi-Vector Retrieval and Learned Prompt Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DB","cs.LG"],"primary_cat":"cs.IR","authors_text":"Ali Noshad, Yinjun Wu, Zishan Zheng","submitted_at":"2026-05-24T07:33:46Z","abstract_excerpt":"To reduce LLM costs and latency, semantic caching systems must accurately identify when a new prompt matches a cached one. Current methods often rely on simplistic similarity measures, which limit their effectiveness. We introduce MVR-cache, a novel semantic caching approach that significantly improves retrieval accuracy by integrating Multi-Vector Retrieval (MVR). MVR-cache is built upon a learnable segmentation model that intelligently splits prompts, enabling fine-grained similarity comparisons via MaxSim. We derive the model's training objective from a rigorous theoretical analysis. This c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24914","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/2605.24914/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":"2605.24914","created_at":"2026-05-26T01:04:05.549371+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.24914v1","created_at":"2026-05-26T01:04:05.549371+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24914","created_at":"2026-05-26T01:04:05.549371+00:00"},{"alias_kind":"pith_short_12","alias_value":"IYRKK2F7ED3M","created_at":"2026-05-26T01:04:05.549371+00:00"},{"alias_kind":"pith_short_16","alias_value":"IYRKK2F7ED3MJ3PV","created_at":"2026-05-26T01:04:05.549371+00:00"},{"alias_kind":"pith_short_8","alias_value":"IYRKK2F7","created_at":"2026-05-26T01:04:05.549371+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/IYRKK2F7ED3MJ3PVFG7MEUCXFC","json":"https://pith.science/pith/IYRKK2F7ED3MJ3PVFG7MEUCXFC.json","graph_json":"https://pith.science/api/pith-number/IYRKK2F7ED3MJ3PVFG7MEUCXFC/graph.json","events_json":"https://pith.science/api/pith-number/IYRKK2F7ED3MJ3PVFG7MEUCXFC/events.json","paper":"https://pith.science/paper/IYRKK2F7"},"agent_actions":{"view_html":"https://pith.science/pith/IYRKK2F7ED3MJ3PVFG7MEUCXFC","download_json":"https://pith.science/pith/IYRKK2F7ED3MJ3PVFG7MEUCXFC.json","view_paper":"https://pith.science/paper/IYRKK2F7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.24914&json=true","fetch_graph":"https://pith.science/api/pith-number/IYRKK2F7ED3MJ3PVFG7MEUCXFC/graph.json","fetch_events":"https://pith.science/api/pith-number/IYRKK2F7ED3MJ3PVFG7MEUCXFC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IYRKK2F7ED3MJ3PVFG7MEUCXFC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IYRKK2F7ED3MJ3PVFG7MEUCXFC/action/storage_attestation","attest_author":"https://pith.science/pith/IYRKK2F7ED3MJ3PVFG7MEUCXFC/action/author_attestation","sign_citation":"https://pith.science/pith/IYRKK2F7ED3MJ3PVFG7MEUCXFC/action/citation_signature","submit_replication":"https://pith.science/pith/IYRKK2F7ED3MJ3PVFG7MEUCXFC/action/replication_record"}},"created_at":"2026-05-26T01:04:05.549371+00:00","updated_at":"2026-05-26T01:04:05.549371+00:00"}