{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VHCWCQQB7NHUEPLF7TRSF4KH4S","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":"8eb2cf0565afe0620ef3e9ed2ddf9da13d927cc03b2c6e1307288de56aa1d7d5","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-02T06:34:11Z","title_canon_sha256":"8631924632fd6048d8e4d086ef74d7f76496b7162ca07138bc26e0655b3da686"},"schema_version":"1.0","source":{"id":"2402.01173","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.01173","created_at":"2026-07-05T07:40:31Z"},{"alias_kind":"arxiv_version","alias_value":"2402.01173v1","created_at":"2026-07-05T07:40:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.01173","created_at":"2026-07-05T07:40:31Z"},{"alias_kind":"pith_short_12","alias_value":"VHCWCQQB7NHU","created_at":"2026-07-05T07:40:31Z"},{"alias_kind":"pith_short_16","alias_value":"VHCWCQQB7NHUEPLF","created_at":"2026-07-05T07:40:31Z"},{"alias_kind":"pith_short_8","alias_value":"VHCWCQQB","created_at":"2026-07-05T07:40:31Z"}],"graph_snapshots":[{"event_id":"sha256:c3fd5c9ad7d7e44269c587f7e6245f8de3ce0a024a379db2eecb15200d8595fb","target":"graph","created_at":"2026-07-05T07:40:31Z","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/2402.01173/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have achieved huge success in numerous natural language process (NLP) tasks. However, it faces the challenge of significant resource consumption during inference. In this paper, we aim to improve the inference efficiency of LLMs by prompt caching, i.e., if the current prompt can be answered by the same response of a previous prompt, one can directly utilize that previous response without calling the LLM. Specifically, we focus on the prediction accuracy of prompt caching for single-round question-answering tasks via embedding similarity. The existing embeddings of ","authors_text":"Banghua Zhu, Hanlin Zhu, Jiantao Jiao","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-02T06:34:11Z","title":"Efficient Prompt Caching via Embedding Similarity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.01173","kind":"arxiv","version":1},"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":"sha256:736d06074d5aec0d70304da6a2d536ec51411b75b60d9b52542d386ced6349e7","target":"record","created_at":"2026-07-05T07:40:31Z","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":"8eb2cf0565afe0620ef3e9ed2ddf9da13d927cc03b2c6e1307288de56aa1d7d5","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-02T06:34:11Z","title_canon_sha256":"8631924632fd6048d8e4d086ef74d7f76496b7162ca07138bc26e0655b3da686"},"schema_version":"1.0","source":{"id":"2402.01173","kind":"arxiv","version":1}},"canonical_sha256":"a9c5614201fb4f423d65fce322f147e4a8c0f03684494b4f59ed6c9ca89091b7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a9c5614201fb4f423d65fce322f147e4a8c0f03684494b4f59ed6c9ca89091b7","first_computed_at":"2026-07-05T07:40:31.745976Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:40:31.745976Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LTvKmmF7eb7s3VhlZk2kSprDMJ+G6m3KM9F6dQipP24WwKvLk+iN+gdrcTfOXcm/j4zjJXT3vtyLfo8np/N6Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T07:40:31.746401Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.01173","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:736d06074d5aec0d70304da6a2d536ec51411b75b60d9b52542d386ced6349e7","sha256:c3fd5c9ad7d7e44269c587f7e6245f8de3ce0a024a379db2eecb15200d8595fb"],"state_sha256":"6b7d563a80b6646e93f7393cede7b884acd87aeaa193620670503860b9b0fc5b"}