{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:H6EYXKZMIWG3W3LOBJPMBH6HSL","short_pith_number":"pith:H6EYXKZM","schema_version":"1.0","canonical_sha256":"3f898bab2c458dbb6d6e0a5ec09fc792dd83f2de866764c699d3b378fa3e3ba2","source":{"kind":"arxiv","id":"2411.05276","version":3},"attestation_state":"computed","paper":{"title":"GPT Semantic Cache: Reducing LLM Costs and Latency via Semantic Embedding Caching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chetan Phakami Pun, Sajal Regmi","submitted_at":"2024-11-08T02:21:19Z","abstract_excerpt":"Large Language Models (LLMs), such as GPT, have revolutionized artificial intelligence by enabling nuanced understanding and generation of human-like text across a wide range of applications. However, the high computational and financial costs associated with frequent API calls to these models present a substantial bottleneck, especially for applications like customer service chatbots that handle repetitive queries. In this paper, we introduce GPT Semantic Cache, a method that leverages semantic caching of query embeddings in in-memory storage (Redis). By storing embeddings of user queries, ou"},"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":"2411.05276","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-08T02:21:19Z","cross_cats_sorted":[],"title_canon_sha256":"de1b86f29443fab3c352f8f99650010e54b6e3d7a651da4ccf542fa48354737e","abstract_canon_sha256":"616876792248a9cd0e254bf19530adb1f2bd4a19ee6f164fd4b7141a717e5fc5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:45:57.392989Z","signature_b64":"bpHo7CFPJSWpF+3vsVT0wBPrgSEB0Hu72/Bp5qYDVIt8O6boF1QBiaUu06oV5Xo5y/Tj3RUzBfQ/wAh0DshBDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f898bab2c458dbb6d6e0a5ec09fc792dd83f2de866764c699d3b378fa3e3ba2","last_reissued_at":"2026-07-05T09:45:57.392450Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:45:57.392450Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GPT Semantic Cache: Reducing LLM Costs and Latency via Semantic Embedding Caching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chetan Phakami Pun, Sajal Regmi","submitted_at":"2024-11-08T02:21:19Z","abstract_excerpt":"Large Language Models (LLMs), such as GPT, have revolutionized artificial intelligence by enabling nuanced understanding and generation of human-like text across a wide range of applications. However, the high computational and financial costs associated with frequent API calls to these models present a substantial bottleneck, especially for applications like customer service chatbots that handle repetitive queries. In this paper, we introduce GPT Semantic Cache, a method that leverages semantic caching of query embeddings in in-memory storage (Redis). By storing embeddings of user queries, ou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.05276","kind":"arxiv","version":3},"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/2411.05276/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":"2411.05276","created_at":"2026-07-05T09:45:57.392510+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.05276v3","created_at":"2026-07-05T09:45:57.392510+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.05276","created_at":"2026-07-05T09:45:57.392510+00:00"},{"alias_kind":"pith_short_12","alias_value":"H6EYXKZMIWG3","created_at":"2026-07-05T09:45:57.392510+00:00"},{"alias_kind":"pith_short_16","alias_value":"H6EYXKZMIWG3W3LO","created_at":"2026-07-05T09:45:57.392510+00:00"},{"alias_kind":"pith_short_8","alias_value":"H6EYXKZM","created_at":"2026-07-05T09:45:57.392510+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.25401","citing_title":"DGAI: Decoupled On-Disk Graph-Based ANN Index for Efficient Updates and Queries","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H6EYXKZMIWG3W3LOBJPMBH6HSL","json":"https://pith.science/pith/H6EYXKZMIWG3W3LOBJPMBH6HSL.json","graph_json":"https://pith.science/api/pith-number/H6EYXKZMIWG3W3LOBJPMBH6HSL/graph.json","events_json":"https://pith.science/api/pith-number/H6EYXKZMIWG3W3LOBJPMBH6HSL/events.json","paper":"https://pith.science/paper/H6EYXKZM"},"agent_actions":{"view_html":"https://pith.science/pith/H6EYXKZMIWG3W3LOBJPMBH6HSL","download_json":"https://pith.science/pith/H6EYXKZMIWG3W3LOBJPMBH6HSL.json","view_paper":"https://pith.science/paper/H6EYXKZM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.05276&json=true","fetch_graph":"https://pith.science/api/pith-number/H6EYXKZMIWG3W3LOBJPMBH6HSL/graph.json","fetch_events":"https://pith.science/api/pith-number/H6EYXKZMIWG3W3LOBJPMBH6HSL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H6EYXKZMIWG3W3LOBJPMBH6HSL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H6EYXKZMIWG3W3LOBJPMBH6HSL/action/storage_attestation","attest_author":"https://pith.science/pith/H6EYXKZMIWG3W3LOBJPMBH6HSL/action/author_attestation","sign_citation":"https://pith.science/pith/H6EYXKZMIWG3W3LOBJPMBH6HSL/action/citation_signature","submit_replication":"https://pith.science/pith/H6EYXKZMIWG3W3LOBJPMBH6HSL/action/replication_record"}},"created_at":"2026-07-05T09:45:57.392510+00:00","updated_at":"2026-07-05T09:45:57.392510+00:00"}