{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:VHCWCQQB7NHUEPLF7TRSF4KH4S","short_pith_number":"pith:VHCWCQQB","canonical_record":{"source":{"id":"2402.01173","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-02T06:34:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8631924632fd6048d8e4d086ef74d7f76496b7162ca07138bc26e0655b3da686","abstract_canon_sha256":"8eb2cf0565afe0620ef3e9ed2ddf9da13d927cc03b2c6e1307288de56aa1d7d5"},"schema_version":"1.0"},"canonical_sha256":"a9c5614201fb4f423d65fce322f147e4a8c0f03684494b4f59ed6c9ca89091b7","source":{"kind":"arxiv","id":"2402.01173","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:VHCWCQQB7NHUEPLF7TRSF4KH4S","target":"record","payload":{"canonical_record":{"source":{"id":"2402.01173","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-02T06:34:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8631924632fd6048d8e4d086ef74d7f76496b7162ca07138bc26e0655b3da686","abstract_canon_sha256":"8eb2cf0565afe0620ef3e9ed2ddf9da13d927cc03b2c6e1307288de56aa1d7d5"},"schema_version":"1.0"},"canonical_sha256":"a9c5614201fb4f423d65fce322f147e4a8c0f03684494b4f59ed6c9ca89091b7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:40:31.746401Z","signature_b64":"LTvKmmF7eb7s3VhlZk2kSprDMJ+G6m3KM9F6dQipP24WwKvLk+iN+gdrcTfOXcm/j4zjJXT3vtyLfo8np/N6Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9c5614201fb4f423d65fce322f147e4a8c0f03684494b4f59ed6c9ca89091b7","last_reissued_at":"2026-07-05T07:40:31.745976Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:40:31.745976Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.01173","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:40:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QQmh/58Yoc4IbnbswxUQ1SlFEF65xPTdnvejH+VvZqI+vjn1j1ki2AwiPkcY5uZAdoJyPlITq1XuDiuFanVIAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:46:47.649624Z"},"content_sha256":"736d06074d5aec0d70304da6a2d536ec51411b75b60d9b52542d386ced6349e7","schema_version":"1.0","event_id":"sha256:736d06074d5aec0d70304da6a2d536ec51411b75b60d9b52542d386ced6349e7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:VHCWCQQB7NHUEPLF7TRSF4KH4S","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient Prompt Caching via Embedding Similarity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Banghua Zhu, Hanlin Zhu, Jiantao Jiao","submitted_at":"2024-02-02T06:34:11Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.01173","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/2402.01173/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":"2026-07-05T07:40:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FAtWg7FFTWkbsO6Gf2s7kA/J6DBUDvGCiimbyqgPrKIhh+Kx8w7jRcP7R2bycrGItHapbcWmct33kzPu3JZHBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:46:47.650111Z"},"content_sha256":"c3fd5c9ad7d7e44269c587f7e6245f8de3ce0a024a379db2eecb15200d8595fb","schema_version":"1.0","event_id":"sha256:c3fd5c9ad7d7e44269c587f7e6245f8de3ce0a024a379db2eecb15200d8595fb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VHCWCQQB7NHUEPLF7TRSF4KH4S/bundle.json","state_url":"https://pith.science/pith/VHCWCQQB7NHUEPLF7TRSF4KH4S/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VHCWCQQB7NHUEPLF7TRSF4KH4S/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":"2026-08-07T19:46:47Z","links":{"resolver":"https://pith.science/pith/VHCWCQQB7NHUEPLF7TRSF4KH4S","bundle":"https://pith.science/pith/VHCWCQQB7NHUEPLF7TRSF4KH4S/bundle.json","state":"https://pith.science/pith/VHCWCQQB7NHUEPLF7TRSF4KH4S/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VHCWCQQB7NHUEPLF7TRSF4KH4S/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O6b37zV3XEv3jqpCqR7NNd34QXpVQLmb30FyBt6KOZepjaOKFAgP2kXKyhntGLfvyv4grHUog6hjIVekgf8ZDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T19:46:47.653926Z","bundle_sha256":"6017cf83fc479f94b7de6899ab2ff1acd51ead551b8e65a3a75943fe7a4096d4"}}