{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:H6EYXKZMIWG3W3LOBJPMBH6HSL","short_pith_number":"pith:H6EYXKZM","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"},"canonical_sha256":"3f898bab2c458dbb6d6e0a5ec09fc792dd83f2de866764c699d3b378fa3e3ba2","source":{"kind":"arxiv","id":"2411.05276","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.05276","created_at":"2026-07-05T09:45:57Z"},{"alias_kind":"arxiv_version","alias_value":"2411.05276v3","created_at":"2026-07-05T09:45:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.05276","created_at":"2026-07-05T09:45:57Z"},{"alias_kind":"pith_short_12","alias_value":"H6EYXKZMIWG3","created_at":"2026-07-05T09:45:57Z"},{"alias_kind":"pith_short_16","alias_value":"H6EYXKZMIWG3W3LO","created_at":"2026-07-05T09:45:57Z"},{"alias_kind":"pith_short_8","alias_value":"H6EYXKZM","created_at":"2026-07-05T09:45:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:H6EYXKZMIWG3W3LOBJPMBH6HSL","target":"record","payload":{"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"},"canonical_sha256":"3f898bab2c458dbb6d6e0a5ec09fc792dd83f2de866764c699d3b378fa3e3ba2","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"},"source_kind":"arxiv","source_id":"2411.05276","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:45:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2oR4zhmudxsQuhoi34ySKOqs6oGL+MXqUZ/sK3gIYd/ucDb4fhiT5eOwR4kueY/QvDGIN2DU2DIZQ5bdm+znDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T11:52:51.637564Z"},"content_sha256":"9daf7ea9ca0aa36ca85d08261d415c4a4a213a9914a985b41c237b375c61d757","schema_version":"1.0","event_id":"sha256:9daf7ea9ca0aa36ca85d08261d415c4a4a213a9914a985b41c237b375c61d757"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:H6EYXKZMIWG3W3LOBJPMBH6HSL","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:45:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EpIJ4WebaJY7mZkWfIJKKiSmY06ONhMlXbZl4yC3/4BkhQ6cq74POvOZenUrC1i+UV8X6OyJMjNuYfSubFe1Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T11:52:51.638428Z"},"content_sha256":"cd41cbe0f4b07b2214dc54431d3a5b2951f8ee9d682670d70fdd5fb20aaf0758","schema_version":"1.0","event_id":"sha256:cd41cbe0f4b07b2214dc54431d3a5b2951f8ee9d682670d70fdd5fb20aaf0758"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H6EYXKZMIWG3W3LOBJPMBH6HSL/bundle.json","state_url":"https://pith.science/pith/H6EYXKZMIWG3W3LOBJPMBH6HSL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H6EYXKZMIWG3W3LOBJPMBH6HSL/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":"2026-08-05T11:52:51Z","links":{"resolver":"https://pith.science/pith/H6EYXKZMIWG3W3LOBJPMBH6HSL","bundle":"https://pith.science/pith/H6EYXKZMIWG3W3LOBJPMBH6HSL/bundle.json","state":"https://pith.science/pith/H6EYXKZMIWG3W3LOBJPMBH6HSL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H6EYXKZMIWG3W3LOBJPMBH6HSL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:H6EYXKZMIWG3W3LOBJPMBH6HSL","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":"616876792248a9cd0e254bf19530adb1f2bd4a19ee6f164fd4b7141a717e5fc5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-08T02:21:19Z","title_canon_sha256":"de1b86f29443fab3c352f8f99650010e54b6e3d7a651da4ccf542fa48354737e"},"schema_version":"1.0","source":{"id":"2411.05276","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.05276","created_at":"2026-07-05T09:45:57Z"},{"alias_kind":"arxiv_version","alias_value":"2411.05276v3","created_at":"2026-07-05T09:45:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.05276","created_at":"2026-07-05T09:45:57Z"},{"alias_kind":"pith_short_12","alias_value":"H6EYXKZMIWG3","created_at":"2026-07-05T09:45:57Z"},{"alias_kind":"pith_short_16","alias_value":"H6EYXKZMIWG3W3LO","created_at":"2026-07-05T09:45:57Z"},{"alias_kind":"pith_short_8","alias_value":"H6EYXKZM","created_at":"2026-07-05T09:45:57Z"}],"graph_snapshots":[{"event_id":"sha256:cd41cbe0f4b07b2214dc54431d3a5b2951f8ee9d682670d70fdd5fb20aaf0758","target":"graph","created_at":"2026-07-05T09:45:57Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2411.05276/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chetan Phakami Pun, Sajal Regmi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-08T02:21:19Z","title":"GPT Semantic Cache: Reducing LLM Costs and Latency via Semantic Embedding Caching"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.05276","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:9daf7ea9ca0aa36ca85d08261d415c4a4a213a9914a985b41c237b375c61d757","target":"record","created_at":"2026-07-05T09:45:57Z","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":"616876792248a9cd0e254bf19530adb1f2bd4a19ee6f164fd4b7141a717e5fc5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-08T02:21:19Z","title_canon_sha256":"de1b86f29443fab3c352f8f99650010e54b6e3d7a651da4ccf542fa48354737e"},"schema_version":"1.0","source":{"id":"2411.05276","kind":"arxiv","version":3}},"canonical_sha256":"3f898bab2c458dbb6d6e0a5ec09fc792dd83f2de866764c699d3b378fa3e3ba2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3f898bab2c458dbb6d6e0a5ec09fc792dd83f2de866764c699d3b378fa3e3ba2","first_computed_at":"2026-07-05T09:45:57.392450Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:45:57.392450Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bpHo7CFPJSWpF+3vsVT0wBPrgSEB0Hu72/Bp5qYDVIt8O6boF1QBiaUu06oV5Xo5y/Tj3RUzBfQ/wAh0DshBDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:45:57.392989Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.05276","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9daf7ea9ca0aa36ca85d08261d415c4a4a213a9914a985b41c237b375c61d757","sha256:cd41cbe0f4b07b2214dc54431d3a5b2951f8ee9d682670d70fdd5fb20aaf0758"],"state_sha256":"47caf1419404157070c6672a325e7a1bd32aa08ee4a96249114d32130359fa0e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xpnD/DVi0eTAp4KYPdZseu7VpVLGRdxhD0YdbxRibDPUgbuRVqcMDUWkn9NAe3ePGsH5BsPdt2Sw9efbMywjBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T11:52:51.650570Z","bundle_sha256":"12ce1fcf4f77047f990fe4a5f16392b178654cd9ae06debc384ce2f2156f5532"}}